Review and testing

Portable, reproducible agent workflows, skills, and MCP setup for modern coding agents. wagent (main) + wagent-hacker (authorized offensive…

Reusable skills and lifecycle skills (/spec to /ship) for software projects, including PR review, memory, and planning workflows

Cross-harness delivery, review, Agent-Native, visual, and software-factory skills for production work.

Provider-neutral software production system with proportional engineering workflows, specialist skills, evidence gates, bounded parallel…

pstack-mod is takahudi's personal pstack port for Codex and Claude Code. Original pstack by Lauren Tan; host adaptation based on Michael…

Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery,…

pstack engineering workflows adapted for Codex, based on irg1008/cstack.

Evidence-based coding workflows: 46 skills, 241 domain recipes, scoped implementation and verification.

Comprehensive .NET development skills and specialist agents from Aaron Stannard's dotnet-skills: C#, Akka.NET, Aspire, EF Core, testing,…

Personal and research assistant combining model guidance with machine-executable Python

Personal indie hacker workflow: spec-driven pipeline with living journal, autonomous conductor, git, and project management skills

skraft SDLC pipeline — agents, skills and instructions for outside-in TDD, Clean Architecture and the RESEARCH→DESIGN→DISTILL→DELIVER…

The Moe skill library — brainstorming, planning, TDD, systematic debugging, code review, worktrees, parallel dispatch, plugin authoring,…

面向中文开发者的软件工程 Agent Skills，覆盖方案澄清、规格与任务拆分、TDD、系统化调试、代码评审、并行实现和完成验证。

Pinned, portable engineering workflows for AI coding agents.

Multi-agent engineering orchestration with planning, parallel execution, evaluation loops, debugging, TDD, and executive/technical review…

CometWeb Labs specialist skills for research, quality workflows, adversarial review, product operations, QA, release readiness, and…

keel 文档驱动开发流程（需求→设计→测试→开发→验证）+ 配套质量 / 测试 / 重构 skill

Specs as the source of truth, a chunked delivery loop, and decided-and-enforced code conventions — as portable agent skills.

Plugin de ingenieria de software: 8 agentes de nucleo, Selina si hay frontend y Lucius bajo demanda. Memoria persistente por proyecto,…

End-to-end guidance for full-stack applications, from focused context, requirements, and planning through architecture, design patterns,…

Inconvenient agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more.

Composable AI skills framework covering the full software delivery lifecycle — design, architecture, implementation, testing, and review.

Unofficial Codex packaging of Matt Pocock's 27 original skills at commit d81f3a1, with only required host interface adaptations.

Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more.

Skills for running, generating, analyzing, and improving tests: test execution, filtering, platform detection, coverage, testability, and…

Production-grade Go programming skills for AI coding agents.

Plan work and have agents execute it, in a repo and across a fleet of them

Reusable Agent Skills for TYPO3 project templates, site-package development, DDEV worktrees, configuration, frontend integration, testing,…

Feedback-based control system for coding agents.

Matt Pocock's engineering and productivity agent skills, from https://www.aihero.dev/skills, repackaged unchanged for Kiro. A battle-tested…

Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play,…

A human-governed, resumable engineering workflow for coding agents.

Twenty portable agent skills for software research, planning, task handoffs, retrospectives, code and test review, verification harnesses,…

Long-running task patterns distilled from OpenAI Codex harness v0.149.0 — tool output budgeting, context pressure compaction, parallel…

A deliberately small collection of personal Agent Skills.

SDLC Harness — an agent-driven multi-agent system that orchestrates your entire software development lifecycle with harness-quality QA, 21…

The Data-First Engineering Protocol as an installable asset set: 22 skills that put design before implementation and tests before code.

A guild of specialist agent prompts, and an inspector that can stop the job. 22 skills covering review and verification, prompt…

Self-contained engineering workflow, architecture, learning loops, and native Agent Plugin updates.

Code quality, smells, refactoring signals, and consistency skills.

Engineering skills for issue backlog burn-down with runbook-driven validation and workspace setup, product mapping, build-failure…

An artifact-led, five-stage workflow: Scope, Plan, Implement, Verify, Close. Skills that let a fresh session continue work without…

Maxxing skills for coding agents: an engineering doctrine (dx for design priorities, writing-code for…

Workflow rules from CLAUDE.md turned into hooks and skills that actually fire

사용자 의도를 먼저 판별하고, 제품·기능·연구 실험·버그에 맞는 서로 다른 승인 흐름을 적용하는 한국어 워크플로우입니다.

Writing skills for structured article creation, review, revision, ideation, strategy, copy, SEO, cover images, practice playgrounds, and…

Agent-neutral AI testing skills for Katalon True Platform covering the full software testing lifecycle: test planning, test design, test…

Personal agent skills tailored to my workflows (Go, TUIs, code review, documentation, and more), plus skills synced from upstream projects.

Agent workflow skills that behave the same in Claude Code and Codex CLI, with a portability contract enforced in CI.

Vendor-neutral React Native skills for developers and AI agents. Spec/Skill-Driven Development from spec authoring through code review.

Siemens TIA Portal engineering automation for GitHub Copilot in VS Code and compatible agents. Provides routed skills for Python TIA…

Build, run and operate agentic automations on your VibeTasking workspaces: the VibeTasking connector and the skills that teach your…

The portable minimum for disciplined, proportional software engineering

Beau's rigorous agent workflow. beau-mode routes each task to a playbook and the principles; skills for understanding (how, why, teach,…

功能開發工作流 — 以 .spec/ 做本地規劃，涵蓋需求、DB、架構、實作、驗證、審查與結案。

Agent Skills for Java development: code review, testing, architecture, Spring Boot, JPA, concurrency, security and release workflows.

Project fitness review skills (architecture, security, reliability, testing, performance, algorithms, data, accessibility, usability,…

Privacy-first email inboxes and workspace automation for AI agents through Mermail MCP.

nobrainer-tech-flow: portable agentic workflows from task to checked result.

A clan of orcs hauling a solo dev's mundane chores, so the code wins the glory.

Utilidades para el desarrollo de SDD (Spec-Driven Development): ADRs, historias de usuario, planificacion e implementacion de tareas…

Vitest test data, coverage analysis, TDD orchestration and notes for LLM coding agents, served by the vitest-agent MCP server and recorded…

Skills-first portable plugin that routes repository work through the smallest valid planning stages and agent roles, using project Markdown…

Versioned engineering playbook for AI coding agents: skills for code review, over-engineering audits, prose voice, planning, and TDD…

A curated collection of Matt Pocock's skills for grilling, handoffs, specifications, tickets, implementation, triage, retrospectives,…

Companion plugin for @savvy-web/silk — changeset, commit, lint, and Turborepo conventions, skills, and agents for the Silk Suite

Expert skills for building n8n workflows with the n8n-mcp MCP server

Agent skills for managing a repository — issues, dependency PRs, GitHub Pages, repo setup, and npm trusted publishing.

让 AI Agent 直连 Workflow（workflow.games）：本地优先规划与拆解需求、自动查重和补全依赖、按权限模式受控并发上传、规划需求与需求室、记 bug、查任务、拿单执行与证据回写、跨仓库交接纪要、线上 QA 验收、查文档、经确认后向平台方匿名反馈问题与建议

Coordinate engineering workflows, create and maintain project verification skills, and investigate, plan, review, simplify, and harden…

Planning workflows with evidence-gated research, fluid collaborative shaping, explicit promotion gates, breadboarding, bounded…

Git-based specification-driven development with central workflow coordination, design, specification, planning, task lists, documentation,…

The knowledge layer of a public agent-harness reference: 15 dense, opinionated engineering skills covering AWS infrastructure, React/Vite…

Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and…

バランス — deliberate before executing, verify after. Fourteen governance skills covering the full development lifecycle.

cms-platform's operational skills for its Jekyll + Decap CMS + AWS sites: admin config render, publish-loop and stuck-PR triage, cutting a…

A self-contained workflow for planning, building, verifying, and shipping features and fixes.

An execution posture for substantial agent work: parallel agents in phases and waves, adversarial red-teaming, looping until confident,…

Engineering workflow skills for decision mapping, adversarial design review, dependency maintenance, durable terminology, decision records,…

Flux Point engineering harness: one Definition of Done, one Evidence discipline, two drivers. Loop mode runs a deterministic Stop-hook DoD…

Issue-to-PR workflow for any tech stack: fetch stories from Jira/Linear/GitHub/Azure and Figma designs, plan-approval gate, adaptive…

Personal workflows for engineering, review, investigation, verification, and craft.

Fourteen guided journeys that orchestrate the whole skill library step by step — create, improve, and grow a business, website, or app,…

Fourteen guided journeys that orchestrate the whole skill library step by step — create, improve, and grow a business, website, or app,…

Infiquetra lifecycle plugin: one automatic run per issue — admission, plan, plan review, a build loop, a lensed code review, merge, release…

The Superpowers development methodology by Jesse Vincent and Prime Radiant, repackaged unchanged for Kiro. Superpowers is a complete,…

Evidence-driven code audits, root-cause diagnosis, simplification, remediation, improvement plans, and repository instruction policy.

Verification-first accessibility engineering skills for finding regressions, repairing source, and proving the repair.

Auriga's end-to-end engineering workflow: clarification, diagnosis, implementation, maintenance, review, and Git lifecycle guardrails.

Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS…

Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS…

Reusable engineering skills for planning, diagnosis, review, and handoff.

Task-oriented Jira development workflow plugin using official Atlassian Rovo MCP v2. Skills cover reading tickets, planning (including…

Kiro configuration ported to GitHub Copilot: agent skills, custom agents (with subagents + handoffs), and MCP servers.

Problem-solving and ideation skills for brainstorming, strategic reasoning, business planning, estimation, and adversarial thinking.

Workflow orchestration, verification, and contribution skills for AI coding agents — plan-first execution, evidence-backed completion,…

Playwright testing conventions for this repository: constitution, locators from .agent-kb, and the skill catalog that writes tests the way…

Code and Rust reviews, test-writing guidance, backporting, security audits, project scaffolding, and documentation figures.

Rigorous AI software-engineering toolkit for Kiro, adapted from the Cursor plugins pstack, thermos, continual-learning, and ralph-loop.…

Enterprise harness companion: feature checklists, tests, code review, parallel options and PR pushes the user ticks, level-aware…

OpenSpec skills for proposing, applying, verifying, and archiving spec-driven changes.

Evidence-bound roadmap delivery from idea capture and research through shaping, planning, execution proof, reconciliation, and…

Strict TypeScript, React, and TanStack workflows for project setup, migration, remediation, refactoring, review, web design, and visual…

Run GitHub issues through triage, decomposition, implementation, review, and revision.

A software development workflow for coding agents.

The flipflopslopstack skill set: review with slopguard, deliver, babysit, plan, maintain docs, prepare repos, equip stack skills, audit…

Shane Myrick's reusable workflows for research, planning, code review, and writing.

Manage your wedding from chat: guests, seating, budget, notes, website, Concierge, documents and inspiration. OAuth connects one wedding at…

Wiki-native spec-driven development loop for the llm-wiki agent wiki: bootstrap a project scope, grill intent into a glossary, synthesize…

WinDbg diagnosis workflows and report validation for applications, services, UMDF/user-mode drivers, and kernel-mode drivers.

Portable Agent Skills for AI-harness diagnosis, AGENTS.md guidance, prompt design, IDE-native agents, hooks, slash commands, workflow…

Agentic multi-perspective code review with adversarial validation.

Bug 工作流 — 涵蓋建立、調查、修復、驗證、結案與知識沉澱。

Claude bridge, optional house rules, and general code review skills for Codex.

Concierge: plan, challenge and execute work with native specialists, explicit model choices and an enterprise design-system-first workflow.

Review plans, changes, replies, and prototypes in cueloop Threads

Full software-engineering lifecycle skills: plan, design, build, secure, ship, and operate. 10 skills with deterministic checks.

Event-sourced workflow state machine for a structured task lifecycle.

Review pull requests, fix issues, implement features, refactor code, upgrade dependencies, investigate CI failures, remediate security…

A portable idea-to-merge workflow for coding agents: spec, freeze, stories, build, judge, ship, retro. The human decides three times; a…

Cloud iOS simulators and Android emulators your agent can create, drive, and throw away.

Review workflow skills for scoping pull requests, improving review findings, planning root-cause fixes, managing review disagreements, and…

Adam's general-purpose skills, safe anywhere including cloud sessions: writing voice, GitHub Actions debugging and hardening, ADRs,…

Skills for planning and shipping work with AI agents: stress-test plans, learn new concepts, and take Azure DevOps work items to a tested…

DDD + Hexagonal Architecture + Clean Architecture + SOLID + Design Patterns as one coherent skill set, a multi-agent staff-engineer…

Skills for planning, implementation, review, and repository care

Concord workflows and persistent project charter support for GitHub Copilot.

Task contracts, bounded planning and orchestration, surgical implementation, debugging, research, review, verification, and handoff.

Portable slice-based SDLC skills with stack, design and executor adapters.

Managed persistent, fresh, and existing Chrome sessions with focus-safe browser tools and CLI-first skills.

Plan Forge guardrails for agentic delivery: plan, harden, execute, review and ship skills, the pipeline agents, and scheduled check…

RADAAR social media management platform plugin for AI agents. Publish content, analyze performance, manage inbox conversations, monitor…

RCC v18.19.3 skills for Environment Artifacts, providers, trust, coordination, robots, Robot/RPA Framework, work items, Action Server, CI,…

Set up Sentry, debug production issues, and configure application monitoring.

Capture, scan, publish, and share native AI agent sessions securely.

Spec-driven development workflows for requirements, design, bug fixes, quick specs, task planning, and execution.

Software development skills: product specs, deep planning, root-cause analysis, agent-oriented repo docs, spec-aware rebasing, PR review,…

Trade-Bot engineering workflows for implementation, root-cause debugging, safe OpenAI SDK integration, parallel agent coordination,…

Build, validate, and manage WireMock Cloud API simulations with reusable agent skills and the hosted MCP server.

Generate, run, and consciously update static (pytest) + LLM (@cursor/sdk) evals when AI primitives change — every proposed change requires…

Write, review, and update product requirements documents with ChatPRD from ChatGPT, Codex, and Cursor. Draft PRDs from notes or code…

Reliable Chrome automation, debugging, and performance analysis for AI agents.

Reliable Chrome automation, debugging, and performance analysis for AI agents.

Reliable Chrome automation, debugging, and performance analysis for AI agents.

Reliable Chrome automation, debugging, and performance analysis for AI agents. Ports the ChromeDevTools/chrome-devtools-mcp plugin to a…

Canon for Codex: plan persistence, a verification gate, and evidence-based review -- without a stored state machine.

Agent skills for research, App Store readiness, Codex model routing, repository and Swift review, PR feedback triage, and safe branch…

Git workflow, versioning, worktrees, Justfile recipes, TDD, test shrinking, and best practices

Team planning, leadership, coding, review coordination, feature feedback, and program status workflows.

Operate Duvo from your agent: debug failed Runs, audit Agents and Queues, doctor Connections, and write AOPs — with the Duvo MCP server…

Developer plugin for Heyra engineers, installable in Claude Code, GitHub Copilot CLI, VS Code and the Copilot cloud agent. /commit,…

Maestra skills for marketers: emails in the visual editor (personalization, product rows, letter styles, recipients, test sends), segment…

Use whenever the user asks about QA, testing strategy, CI/CD health, team processes, developer experience, code review practices, test…

Workato recipe skills: base + connector skills that teach an agent to generate valid Workato recipe JSON

The per-ticket delivery procedure as phases you invoke: ticket analysis against an analysis document you refine run by run, the generation…

Agents and skills for WinUI 3 app development. Create new WinUI 3 desktop apps, convert from other frameworks to WinUI 3, or add features…

Protected web data for AI agents via Zenrows MCP — scrape, extract, batch, and browser sessions with cost-aware escalation.

Marketing automation, CRM, and email marketing powered by ActiveCampaign. Manage contacts, campaigns, automations, deals, and get…

基于 Agent Plugins Specification v1.0.0 的中文实践示范仓库：通过高质量 Skill、MCP 及二者组合案例，展示 Agent Plugin 的设计、组织、运行与复用。

Search team documents, collaborate in review threads, and propose changes for human approval in ArtifactBridge.

Capture, run, and diagnose MCP test suites with the botz MCP Swarm CLI.

High-integrity multi-agent orchestration bridge connecting orchestrators with local CLI coding agents (OpenAI Codex, Claude Code, Google…

Code quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of…

Code quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of…

CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring…

Lean verified agentic engineering: plan, implement, verify, doc, doc-edit, wrap and status skills plus deterministic verify/review/docs…

Skills and an orchestrator agent for migrating .NET test frameworks and platforms: MSTest and xUnit version upgrades, xUnit/NUnit-to-MSTest…

Codex-native skills and specialist agents for disciplined software delivery.

Third-party skills enhanced with advisory TypeSafe Jev judgments: two-axis code review, prose humanizing (en/zh-TW), reply checking,…

Code intelligence server: search, navigation, and refactoring across 36 languages

Explicitly activated, context-isolated multi-agent execution with Main-owned planning and bounded review.

Author, run, triage, and repair Momentic end-to-end tests for web, Android, and iOS. Use these skills when an agent must write a new test…

Novus skills for coding agents: UX review and evidence-backed next-work and portfolio investment decisions, powered by Pendo product…

Review and refactor skills for code simplification, deduplication, best-practice audits, frontend refactor planning, and adversarial review.

Project-agnostic security skills for repository audits, diff review, deterministic scanning, supply chain, threat modeling, smart…

범용 유틸리티 skill 모음

Target-bound repository orchestration plus pull-request lifecycle: template, create, refresh, review, and guarded merge.

Tricritical: independently planned intent, runtime, and structure critics, adjudication, authority-gated revision, and one fixed-point loop.

WordPress development, testing, and release skills.

Run AI coding agents unattended, safely: Implement → Review → QA as separate agents, a guard that blocks edits they must never make, and…

Intent-routed DEFINE, PLAN, BUILD, VERIFY, and lean-context skills with measurable local evaluation.

Antigravity CLI (agy) plugin for review, rescue, and autonomous agent workflows.

The architectural constitution (P1-P15), the review/modernize/recover session playbook, the repository baseline, the greenfield initializer…

BLEND task generation, scenario test specification, automation testing, artifact review, implementation planning, and code review workflows.

Shared tasks, file boundaries and durable handoffs for coding agents.

Interview ideas before OpenSpec proposals, capture settled designs, and implement OpenSpec tasks with disciplined review.

Use Hermios CRM in Codex to manage contacts, companies, deals, tasks and notes, prepare follow-ups, review the pipeline, and work with…

Error tracking, debugging, and job monitoring skills for Honeybadger.io

Kaleb's intentionally frozen standalone skills.

How the agent runs itself. Scheduled automations and saved workflows, the assistant that coordinates them, and the user memory that carries…

通用开发项目管理 Agent 框架：主 loop 调度、reviewer 对抗审查、方法论技能集、强制在场的红线规则

Automate native macOS apps with AppleScript, JXA, Swift, and EventKit.

An AI agent orchestration system for working across multi-repo projects, with specialized capabilities for cross-repo dispatch, wiki…

Software engineering toolkit: code review, test generation, documentation, plan grilling, and closeout reviews.

Six-skill Instruction Layer for governed coding agents. The plugin installs skills only. Enforcement Layer guards are separate and are not…

Run this workflow from Codex. Stop hooks that terminate a Claude Code session when the agent's final message contains a kill phrase. Two…

Trent, an AI security engineer. Review code, plans and configs for security problems, run threat models over a repo or website, and track…

Make, review and publish social content: develop formats and your project's own content skill, produce batches, review them in one local…

GitHub Actions diagnosis and review skills for runtime failures, security, optimization, and architecture.

Open-source engineering skills for repository work, Python, host-native MARGOS orchestration, ReThinking audits, and Agent Plugins…

プロパティベーステスト生成、リファクタリング、PR 作成・再レビューなど、日常的な開発作業向けの Agent Skills コレクション。

Repository-agnostic feature planning for GitHub Copilot: a workflow orchestrator, Feature Brief and Sub-Issues planner agents, and reusable…

Review, fix, verify, merge, and close out open pull requests in Jira.

Roadmaps, Epics, Stories, refinement, and sprint planning in Confluence and Jira.

複数リポジトリで共有する Agent Skills。コミット・PR作成、安全なライブラリ自動マージ、テスト規約、Markdownによる計画・進捗管理。

Arcadia's first-party agent skills: CLI design, Gherkin testing with godog, pyramid summaries, specs, and unit testing principles.

ArchDev skills, the ArchDev remote MCP server, and the hooks that report coding-agent sessions to your organization's ArchDev stream.

Odin agent ecosystem — adversarial code review agents for GitHub Copilot CLI

Analyze your application portfolio with CAST Highlight — technical debt, open-source security risk, cloud readiness, and agentic/AI…

Repository delivery, dependency upgrades, cleanup, and independent review workflows for coding agents.

End-to-end GitHub workflow: find issues worth working on, solve one into a pull request, follow up on review feedback, and write comments…

Skills for commits and GitHub or GitLab change-request lifecycles.

Triage PRs, issues, CI, and publish flows.

Triage PRs, issues, CI, and publish flows.

Prepare sourced response dossiers, check evidence, and create review copies in Helvabase.

Less AI. Less slop. Filter likely AI-built websites and inspect local evidence. Optional MCP tools let you browse, read and act with…

Browse and inspect sites in your own Kitsuvo browser through the opt-in authenticated cloud connector.

Skills for long-running agent work — write the completion contract, carry a goal to a verified finish, keep review adversarial, and…

PSModule process guidance and reusable skills for PowerShell module repositories.

AI QA that runs your app in a browser on every pull request: set up a test target, read what it found on a pull request, and plan tests for…

Qodo setup, code intelligence, and review workflows.

Baseline maintainer dev flow as config-driven skills: create-pr (opens PRs only after running the repo's format/lint/build/test…

Professional Roblox and Luau standards for AI agents: server-authoritative, leak-free, framework-agnostic, and laid out the same way in…

Java/Spring rules, clean/hexagonal architecture guidance, COBOL migration and repair, and Maven verification

Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request,…

Use this plugin for adobe Acrobat workflows for PDF reading, forms, signing, reviews, and document handoffs.

Reviewed coding tasks with focused specialist agents, optional PR delivery, and durable autonomous project work.

Close a sprint with debt review, closeout, QA validation, and retrospective workflows.

Let any agent use Arcade — one MCP connection that finds and runs the right tool across every app you've connected. App sign-in happens in…

Create modular walkthroughs and product documentation from web applications.

Skills for differential regression reviews, draw.io diagrams, and narrated pull request walkthroughs.

Investigate mobile and edge production issues, instrument iOS/Android/React Native apps, and operate the bitdrift Capture platform.

Evidence-first Brain workflows for inspecting GitHub repositories, diagnosing failures, and preparing verified changes.

Plan, run and land multi-phase Bernstein builds, and review pull requests with evidence quoted for every finding.

Research your connected CRM, meetings, call transcripts, and email, and safely build clearskies revenue workflows.

Write and review customer communications in your organisation's brand voice with CommScore.

Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests: an agent gets the…

ddv (Design Doc Viewer) workflow skills: Mermaid-first requirements, basic and detailed design with generated test matrices and test IDs.

Build web apps, charts, websites and presentations in plain HTML/CSS/JS with shadcn-style components and defuss - plus task skills to plan…

Cross-tool embedded bring-up, debugging, test, and incident workflows for AI agents.

Plan your circle's week and make asks from a conversation, through your own Gather Rnd account: read the week and its calendars, spot gaps…

Message Grok Bot from Codex, Claude Code, and Cursor. Codex/Claude tools use local sockets on the user's registered machines only (no…

Issues, pull requests and code on GitHub through GitHub's remote MCP server.

Eric's always-on working rules: finding the right repository, issue and sub-issue hygiene, open-source conduct, and plan grilling.

Connect Codex to HarnessMesh collaboration, review, knowledge and MeshCommit tools.

Native Windows screenshots, visual verification and capture-library search through Hotshot.

Visual review for previews and prototypes. Share a link, let reviewers pin comments and record walkthroughs on the live page, and read the…

Rule-based code review skills backed by the jev-flash-review MCP engine — review PRs, arbitrary code, or loop until clean.

Personal agent development skills: pre-ship code review, git work-tree cleanup, log diagnosis, and token-efficient caveman communication.

Build, ship and debug JoyStream agents through the JoyStream MCP server.

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.

Check coding-agent tasks, prepare held read-only drafts, and run a separately consented bounded OpenRouter worker on your connected o8…

Plan and manage delivery work across GitHub and Jira without introducing a third project-management source of truth.

Agent Plugins package (v3.0.1): 4 Playwright E2E skills — test planning by page role, script authoring with video / trace evidence, report…

Practical, tool-optional help for checking work, challenging plans, shaping ideas, and handing off context.

Cross-language project standards: domain modeling, GitHub Actions hygiene, test judgment, and the pre-commit gate.

Coordinate product delivery, manage evidence-backed QA, and author engineering-ready business requirements with Project Manager, Test…

An Agent Plugins 1.0.0 package for evidence-backed implementation plans in Codex. It writes planning documents, not application code, and…

Plans and lands work that spans several pull requests as ordered stacks, with a PR size gate and a stack overlap check

Rebuild and design product UI as self-contained HTML artboards on a local tldraw canvas. Clone a real app from screenshots by measurement,…

28 production-ready MCP servers for coding agents - filesystem, GitHub, npm, research, and more. Ships zero-config servers out of the box…

Host screenshots, GIFs, recordings, and files on uploads.sh and embed them in GitHub PRs and issues.

Use this plugin for linux browser hardening and browser-specific desktop workflows.

Engineering quality, semantic architecture, technical communication, and workflow guidance for autonomous coding agents

读取与编辑 AgentViewer 中的文档、阅读上下文和网页，支持原生鼠标键盘输入。

Generates .gitignore files, runs typecheck, lint, format, security and test checks before you commit, and commits, pushes and opens a PR…

Audits a codebase's user-facing copy, layouts and metadata for AI-written tells and factual errors, such as a privacy policy that misses…

Agent skills for Android motion and design-engineering craft: add motion that belongs, map a codebase's motion language into a MOTION.md,…

Apptension review skills — methodical assessments of code, infrastructure, and security, plus a full project audit with scored, comparable…

Clear, adopt, maintain, replace, and retire exact third-party software components under explicit policy.

Autonomous issue-to-PR pipeline. create-issue is the front door — it turns a rough request into a well-formed, buildable issue by…

Screenshots produced by your agent, from a demo world it builds and cannot leave.

Use this plugin for browser automation, screenshots, and interactive Playwright workflows.

Share Android and iOS builds with testers: install links, QR codes and tester feedback from buildtree.

Agent skills for ConfIT — set up a declarative API test suite, write component tests from your controller and its mocks, and write…

Deep code, test, and documentation refactoring workflows with disciplined proof and delivery.

Sample Kiro Agent Plugin providing code-review and commit-message skills plus team coding-standards steering.

Spec, plan, implement, review: a test-driven development loop for AI coding agents. Three commands map to three gates, one per command…

Configure and run DiffPal reviews locally and in CI.

Intent to implementation: ready, then go.

Experimental autonomous workflows for the e2a agent email gateway. Requires the core e2a plugin for MCP tools and authentication.

Fastmail email skills: browser-driven email workflows (search, read, compose, reply) and sending-identity management via the…

Figma-to-web implementation and evidence-backed UX fidelity repair loops, with bundled Figma and Playwright MCP configurations.

Eric's frontend and React standards for TS/JS UI work, plus browser end-to-end testing.

Lightweight high-agency coding with impact calibration, adaptive model routing, targeted verification, and bounded autonomous iteration for…

Let AI agents capture live website screenshots, render HTML/CSS, and populate reusable templates as images or PDFs - without managing a…

Find, inspect, run, and safely edit iBlueprint Blueprints from ChatGPT, Codex, and GitHub Copilot.

Find, inspect, run, and safely edit iBlueprint Blueprints from ChatGPT and Codex.

An iterative, local-first software-quality score loop for AI coding agents, powered by Jev.

Build a review map of code changes, then walk through it with editor navigation and evidence.

Coordinate explicitly authorized workflows on paired personal devices without giving AI custody of private device data.

Leave Management API team kit: run-and-fix-tests and ef-core-migration skills, Clean Architecture Refactor Expert agent, EF Core migration…

Build, run, and debug n8n workflows using your workspace code and public-client OAuth. Workflow tools require n8n 2.34.0+. Setup supports…

On-device AI: chat with a small language model running entirely in the browser — no server, no API key, no account. Agent skills for…

Connect your agent to 700+ apps through One. One MCP server, three tools, 80,000+ actions with real API documentation, no OAuth tokens to…

Pair-programming with Paireto in VS Code.

Review, fix and explain code changes with concrete verification evidence and plain-language limits.

Production-readiness checks for AI-built apps: scan the repository your builder syncs to, fix what would break, and verify the fix landed.

Use Pippin through MCP or its CLI for Apple mail, calendar, reminders, contacts, notes, memos, messages, and diagnostics.

Drive Porcelain — publish Reviews, manage Tasks, Actions, and profiles, close the evidence loop, and set up a remote daemon.

PRD 全流程工具 — 從用戶訪談建立 PRD，再拆成實作計畫或 GitHub issues。含 write-a-prd、prd-to-plan、prd-to-issues 三個技能。

Code quality skills — refactoring, naming conventions, and project structure

Review Codex changes and running web previews, then send precise feedback back to the conversation.

PRレビューを支援するスキルとメモ用MCPサーバーを同梱したサンプルプラグイン

Portable code review, code style, and module design skills.

Portable Rootloom Agent Skills for inspectable code changes and evidence-backed review with bounded project and artifact context.

Create, tune and record typed configurable logic graphs with Sapho.

Teaches a coding agent to bind tests to spec requirements with [verifies ID~REV] tags and to pass the shallnot traceability gate before…

Self-Improving Agents: evidence-gated workflow and cost-aware multi-agent orchestration with durable state, file-ownership safety, and…

Design verification strategies that unlock higher levels of autonomous software development.

Use mcpdoc and GitHub MCP to verify documentation and source code, with Codex-only restricted DeepWiki access for public OSS, then fix…

Merge-safe planning methodology for staged multi-PR work: authority ladder, repository topology, and merge-safe acceptance criteria.

Project tooling skills — linting/formatting setup, testing, and documentation sync

TYPO3 and DDEV workflows for Playwright setup, frontend verification, and Tailwind CSS v4 migrations.

Build and operate Abstra workflow automations: Python stages, connectors, tables, executions and deploys in your Abstra organization.

Make motion-graphics videos with Codex and plain JavaScript, no video generator: every frame is a pure function of time, Playwright renders…

Answer Ansible questions and review Ansible code using official documentation from the Ansible ecosystem.

Review Ansible code against Red Hat CoP automation good practices.

Create a new Ansible content collection following all Red Hat CoP good practices.

Create a new Ansible execution environment project following good practices.

Scaffold molecule testing for an Ansible role or collection following the current molecule testing philosophy (Ansible-native everything).

Create a new Ansible role following all Red Hat CoP good practices.

Coordinate exclusive Android emulator (AVD), iOS Simulator, and physical device leases across concurrent coding agents with the atc CLI,…

Let your agent use your real, logged-in browser in its own background tab — 46 tools plus the automate-browser skill covering tab…

Review, fix, and demonstrate pull request changes. Monitor a pull request or merge request, fix scoped CI failures and review feedback, and…

AL-aware code review skill and read-only Microsoft Learn documentation lookup for Business Central pull requests.

Prepare document deliverables with Bestie Check before handoff and read the free Claim and Assumption Quick Look. Paid verification is…

Control the currently open Brave browser on the same Windows PC without choosing a device or profile in advance.

Browse, inspect, and test websites in Poracode's isolated in-app browser.

Create, deploy and run AI agents on camelRun, camelAI's hosted agent runtime.

Work with the pages and signed-in sessions already open in Chrome.

Run Claude Code from Codex for adversarial review, feedback triage, and in-scope fixes.

Develop and debug Flutter apps and run cross-platform E2E validation with Cockpit.

Understand unfamiliar code, plan your next change, and keep onboarding docs current with source-grounded guidance.

Run Codex from Claude Code for adversarial review, feedback triage, in-scope fixes, and task delegation.

Connect and operate 1000+ external apps through Composio Connect with managed OAuth and intelligent tool routing.

Composio integration for Sameer AI Workspace with dynamic app discovery, connection management, and tool execution.

Local first, policy bound computer control with verified browser and desktop routes.

Control desktop apps in the background and complete visual workflows.

Agents often drift and waste time on the wrong work. Correction Guy watches from the sidelines and steers them back on track.

Crosspost watches a tweet.app account and reposts new posts to X automatically or after review, using each person's own X developer keys.…

macOS computer-use routing between Orca (interactive) and CuaDriver (background stealth)

Real Chrome DevTools access for AI coding agents: console, network, DOM, source maps, breakpoints and live variables, plus guidance on when…

Gitリポジトリで共通利用する最小限の開発ルールと、証拠に基づく検証・改善の進め方

Configuration-first multi-agent design debate. Agents with different roles (architect, security, performance, simplicity, ...) run…

Drive Distilled's cloud Android phones from a conversation, and watch the phone's screen live while the agent works on it.

Agent-safe embedded flashing and debugging through structured CLI, Skill, and MCP session contracts.

Endform runs your existing Playwright suite in parallel, up to 10x faster, and helps you keep it healthy as it grows. This plugin lets your…

Run coding, file processing and automation tasks in persistent Workspaces and isolated Sandboxes. Reuse task state, inspect outputs and…

Operate all customer-facing Famulor MCP capabilities with tenant-safe, progressive tool guidance.

Verified coding workflows plus a public context-aware commit skill that plan, implement, test, review, and summarize one task in one agent…

Coding collaboration, debugging, verification, logging, and project documentation rules.

Control a paired iPad in a local browser and bring native text, sketches and exported files into Codex.

Persistent goal execution with an autonomous continuation loop.

GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure through MCP.

Guildhall: independent specialist agents, test-first implementation, gated reviews and durable quest plans for capable coding hosts.

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

TypeSafe Jev drives a real browser: one goal, an indexed action space, one systemOne decision per step. Exposes the jev_browse MCP tool.

High-level GOAL→JSON browser automation via TypeSafe Jev indexed controls. Prefer over screenshot computer-use for multi-step website…

An iterative, local-first software-quality score loop for AI coding agents, powered by Jev.

An iterative, local-first software-quality score loop for AI coding agents, powered by Jev.

Connect Browser to Claude, Cursor, and ChatGPT through JoAi's hosted MCP app server.

Read JavaScript-rendered pages with a real browser: render, screenshot, links, and API-call capture as MCP tools, plus a skill that tells…

Inspect Kosh repositories, work, automation, releases and production readiness from ChatGPT and Codex.

Risk-based Kotlin review agents for READMEs, tests, architecture, domain behavior, concurrency, API and data compatibility, security,…

Explicit learning diagnostics, recoverable local evidence and manual task record/application checks.

Connect supported AI clients to explicitly enrolled computers through typed operations, exact-machine routing, local policy, and execution…

Inspect, measure, preview, and verify live web and Electron interfaces with Mesurer Solid.

Inspect and visualize local MiniMax Code session ledgers as privacy-aware trajectories through a dependency-free MCP server.

Inspect and visualize local MiniMax Code session ledgers as privacy-aware trajectories through a dependency-free MCP server.

Mobile app debugging tools and usage guidance for Android and iOS agents.

Mobile automation for AI agents: control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take…

Mobile automation for AI agents: control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take…

Mobile automation for AI agents: control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take…

Playwright CLI and Jupyter notebook scaffolding

Build, validate, and run NodeTool AI workflows, and manage assets, collections, and jobs, from ChatGPT.

Your coding assistant plans, sandboxed workers build, and nomArmy checks every change before it counts: the tests run again in a fresh…

Local Ubuntu, Windows and macOS environments plus local GitHub Actions matrix runs (act) for agents: run commands, sync files, forward…

Pad is a project workspace for tasks, bugs, ideas, plans and docs. This plugin connects ChatGPT to your Pad Cloud workspaces so you can…

Project-scoped marketing operations through Patronage Loop's remote MCP server.

Capture a Mac window, rectangle, or web page through plaiiin App Capture.

Human-like end-to-end acceptance testing for PlotPickle using a portable Agent Skill and Playwright MCP browser automation.

Portable Agent Skills for pull-request review, test sufficiency, quality reporting, and repository intelligence.

Secure AI command center for managing connected WordPress sites through controlled, auditable PressPilot tools.

Playwright-style MCP server for PySide6 apps — see, control, and debug a Python desktop GUI without modifying the app.

Ask QA Wolf for test coverage, run flows, read results, and drive a cloud browser from your editor.

Optional Qodo rules discovery and standards administration workflows.

Rehearsal for AI coding agents: build a sandboxed practice world from a real application, run an AI agent through jobs where the customer…

Read, address, and resolve Remarc comments from supported coding agents.

Build and review software engineering résumés from an evidence chain, not a template, in the manner of Richard Feynman and W. Edwards…

Review code against Eric's standards, prepare GitHub pull requests for review, and produce Guided Review walkthroughs.

Create, remotely build, test, verify, and explore mobile apps from a cloud coding workspace using the full Revyl CLI, with connected Atlas…

Measure and review visual changes with the installed Saccade CLI.

Control the user's existing Safari 26 session with agent-written JavaScript.

Complete Spec-Driven Development flow as portable skills for GitHub Copilot.

The Segmently Modules acceptance-criteria skills: a task's criteria before the code, and a module's acceptance baseline

Local code discovery and change review with Sem; optional branch merge previews with Weave.

Build, test and publish Softr Workflows from local files with the softr-workflows CLI

Specification-driven development workflow skill. Orchestrates a spec-first discipline: frame a one-page Product Spec (problem, falsifiable…

Agent plugin and skill for setting up, configuring, and running Stryker mutation testing in TypeScript and JavaScript repositories. Ships…

Wraps Sunsama's official remote MCP so agents can work with daily tasks and planning after client-managed OAuth.

Coverage, security and code quality for coding agents.

Ternivo Connect for OpenClaw: authenticated social delivery through a remote MCP server with preflight, approval policy, terminal…

QA platform for coding agents. Agents read consolidated coverage signals (scenario, API contract, TrueCoverage from real users,…

TesterArmy runs agents that click through your web and mobile app the way a real user would, on every pull request. Create tests in plain…

TideSurf launches or attaches to Chromium over CDP and compresses the live DOM into token-efficient text for browser agents, exposed via…

Structural code quality metrics, lattice verification, and refactor loops for agent-written code.

通りがかりの、本質的で鋭いギャル。余計なことを考えないから、冴えた頭で本質を突ける。

Continuous quality review and source-anchored findings powered by Jev.

Context-budgeted visual feedback for coding agents: diff-only crops plus a structured text summary of the UI you just changed, within a…

A live-demo UI reviewer: a repeatable smoke-test skill, a focused Copilot agent, and Playwright browser tools.

Connect your AI assistants to your Upsy memory, files, connected accounts, and cloud browser with the access you choose.

General-purpose, project-agnostic workflow skills for planning milestones and maintaining useful software documentation.

Repository-first primary full-stack engineering owner for online repositories: architecture, frontend/backend/data/runtime implementation,…

Search 241 engineering workflows and load the selected working context through a public, read-only MCP server.

Code-aware browser testing and release QA for AI coding agents.

Research a question on the live web and report findings with sources.

Observe and interact with live Android/iOS apps via WebEngine MCP (Appium): snapshot, tap/type/swipe, then generate mobile UI code.

Observe and interact with live web pages via WebEngine MCP (Selenium): snapshot, click/type/select, then generate UI code in any stack.

Weft is the AI task manager for solo founders and small teams. Tell your AI, and it runs your board. Bundles the Weft MCP server and a…

Operator console for an Aeon agent instance: enable, schedule, and edit skills, wire secrets and channels, debug runs, and mine past…

Operator console for an Aeon agent instance: enable, schedule, and edit skills, wire secrets and channels, debug runs, and mine past…

Operator console for an Aeon agent instance: enable, schedule, and edit skills, wire secrets and channels, debug runs, and mine past…

Operator console for an Aeon agent instance: enable, schedule, and edit skills, wire secrets and channels, debug runs, and mine past…

Aevral is an AI security reviewer for GitHub pull requests. Setup skill for the Aevral GitHub App: reviews look for access control,…

Turns an idea or a meeting transcript into a working AI agent you can use right away in ChatGPT, with nothing to install.

Turns an idea or a meeting transcript into a working AI agent you can use right away in ChatGPT, with nothing to install.

Stop manually switching AI models. Send each task to the right model tier and add independent review when the work is risky.

Search about 1,700 free AI agents in the public agent registry and use one right away in ChatGPT.

Search about 1,700 free AI agents in the open agent registry and use one right away in ChatGPT.

Alternate implementation and merge workflows until an active sprint is drained or blocked.

Finds technical debt and anti-patterns in code written with older AI models or vibe coding, and saves a scored report with a prioritized…

Give a cloud-agent Chrome a residential or mobile IP in a chosen country. Country-level geo, not a human VPN and not an MCP.

Serialize Android UI and end-to-end test runs with a device-side adb file lock.

Project-independent adb device locking for Android tests across projects and frameworks.

Display the Zen of Ansible principles and review Ansible code against them.

Evidence-based architecture review, code audits, verification, and authorized improvements.

Bundled Anti-Slop checks after edits, plus pre-edit guardrails, without repository lint setup.

Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.

開発セッションの終わりに、関連Issue・未着手タスク・Issue作成案・追加テストや軽微な整理を確認する。

ast-grep の構造検索・lint・安全な rewrite・ルールテストをプロジェクトで使う。一般的な linter で表現しにくい構文パターンに適用する。

Automatically chooses and coordinates GPT models for project tasks, with the right effort and safeguards for each job.

Community package for the official Atlassian Rovo MCP plugin for Jira, Confluence, and Compass workflows through Atlassian's hosted remote…

Codex engineering with Astra XHIGH planning and advice, Luna MAX Fast workers, Sol MAX design, independent Sol review, and context…

Work with your Basepath goals, weekly plan and reviews in the conversation. Every change is a proposal you approve in Basepath.

Analyze code and architecture for violations of ten system-level software design principles: Separation of Concerns, Single Responsibility…

A real browser beside your chat that your agent drives while you watch. Tabs, persistent logged-in profiles, circle-to-annotate, and an…

Direct browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and…

Browse, inspect, and test websites in CraftStation's isolated in-app browser.

Prepare scoped ChatGPT Pro review packets and reconcile feedback against local repository evidence.

Community package for Chrome DevTools MCP. Inspect pages, automate flows, analyze performance, and debug browser state.

Work with the pages and signed-in sessions already open in Chrome.

Use Claude Code from Codex: delegate coding tasks with independently verified results, get Claude code reviews, pair Claude with Codex, and…

Analyze source code against Robert C. Martin's Clean Code across nine dimensions: Meaningful Names, Functions, Comments, Formatting,…

Findet toten/Legacy-Code und verwaiste Dateien, mit --skills stattdessen repo-lokale Skills. Standard nur analysieren; --fix beweist jede…

Provides structured workflows and checklists for conducting thorough code reviews

Senior-staff-level code review agent. Trained on 140 pull requests; 2 learned procedures, 1 reviewed.

Make the code you choose easier to read and maintain while preserving its behavior.

Evidence-backed, diff-scoped CodeRabbit-style review handoffs for Codex.

git commitのワークフローを自動化するプラグイン。差分の分析、コミットメッセージ生成、pre-commitチェックの実行、コミット作成までを一貫して行う。

Control desktop apps and complete visual workflows.

Guidance for inspecting and controlling Mac apps through Owls Computer Use tools.

One kind of thing, one path. Gives coding agents architectural taste: converge at the source instead of stacking branches, fallbacks, and…

GitHub Copilot CLIを使って観点別に並列コードレビューを実行するプラグイン。差分やPRを複数の専門サブエージェントがcopilot -pで同時にレビューする。

Plan work that fits your time, start a task, and retain decisions in a portable local workspace.

假設驅動除錯法 — 強制 agent 走 Observe → Hypothesize → Experiment → Conclude 四階段科學方法迴圈，所有推理寫進 DEBUG.md，沒有證據前不准寫 fix。專治 AI 一路撞牆寫 150 行錯誤修復的 bulldozer…

Find every edge case of a feature with an exhaustive decision table, get a human ruling on each uncertain cell, then minimize it into a…

Evidence-based debugging for AI agents: map the project, run it, trace what actually executes, then report findings tied to file:line.

Plan and implement code changes in small, reviewable increments, including when executing an existing plan.

Autonomous Dependabot queue management — the one maintainerd plugin that merges. The dependabot skill gates every bot-authored dependency…

Use this plugin for generic UI review, accessibility, and design-quality workflows.

Generate Git or Difftastic code-diff sites for local preview or ngrok sharing.

EARS要件からテスト・トレーサビリティを可視化する。requirements.md(EARS)とpytestを突き合わせ、テストの穴(未検証の要件)を検出し、HTMLレポート・CI判定・pytestスタブ生成を行う。

Let an AI assistant create and update Microsoft Excel workbooks: work with cells, formulas, Power Query, PivotTables, charts, and VBA in…

Jev-based test impact assessment for CI and coding agents.

Control Firefox for browsing, web testing, and debugging. Fill forms, capture network and console activity, take screenshots, run scripts,…

Focused static review for JavaScript, TypeScript, React, Next.js, and browser extension changes.

Debug, instrument, reverse engineer, and patch running programs with Frida, primarily on Windows.

Systematic full-stack web development guidance for architecture, debugging, quality, testing, security, and deployment.

Artifact-driven multi-agent software delivery with approval gates, deterministic verification, and durable evidence.

Parallel AI code review for GitHub pull requests using GitHub Copilot CLI and Agent Plugins.

GitHub Actions の PR チェック失敗を診断し、依頼された範囲で修正・再検証する。外部 CI は URL と制約を報告する。

List, reply to, resolve, and create GitHub PR review comment threads

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser.

Evidence-routed planning, implementation, and review workflows for high-correctness software changes.

Agent plugin for skills for working with GitHub Actions workflows, including setting up and maintaining common actions.

GitHub and git integration driven by the GitHub CLI (gh) and git. Runs a local MCP server for the full pull request review lifecycle from…

Agent plugin for reviewing agent-generated pull requests using a structured, ordered checklist based on GitHub's guide to agent PR review.

GitLab MCP server exposing up to 1088 self-managed GitLab REST/GraphQL MCP tools, or 1094 on GitLab.com Ultimate with Orbit. Includes a…

Glide's official MCP server — build, manage, and operate GlideOS apps, data, and workflows.

Auto-review Go code for 100+ common mistakes from 100go.co. Checks error handling, concurrency, interfaces, performance, testing, and…

Modern Go and Google readability standards, style guidelines, code review checklists, and testing patterns.

A scoped production-engineering workflow for implementing, debugging, reviewing, refactoring, and release-preparing software with explicit…

Golden Path: help people express business intent as reviewable engineering acceptance, then connect it to the controls they already use.…

A local development workflow for exploring, planning, implementing, and shipping changes with shared session state.

Use this plugin for aDHD and CBT planning packs with printable workflow support.

Create app-store screenshots, portfolio mockups and Play banners from local images. Export PNGs and editable Hen projects.

Field notes for a Hermes install: pitfalls with root cause, local core patches checked after every update, and a pinned Telegram dashboard.

GRC compliance review for your pull requests. heyGRC reviews each PR against ISO 27001, SOC 2, GDPR, DORA, NIS 2, the EU AI Act and your…

Implement changes with reproducible verification, visual evidence, and draft pull requests.

Author self-contained implementation plans, multi-plan programs, or compact handoffs that a fresh agent can execute without conversational…

Audit a codebase's motion and produce prioritized, implementation-ready improvement plans.

Guidance for operating Owls's session browser.

Export Instagram Saved post IDs using browser tools or Computer Use, with resumable checkpoints and JSON, CSV, and text output.

GitHub Issueの作成・一覧・処理を自動化するプラグイン。プロンプトインジェクション対策として、自身が作成したIssueまたは承認済みIssueのみを処理する安全機構を備える。

Install, verify, and integrate the lightweight Jet Browser runtime for browser agents.

Plan, verify and learn with an evidence-first Skill and bundled local CLI. Optional Jev; no MCP setup required.

Jev-assisted, evidence-backed merge-queue decisions for rebase and full-test requirements.

Linux kernel development the way experienced kernel engineers work: drivers, devicetree, Kconfig, debugging by symptom, testing, patch…

Analyze code and architecture for unnecessary complexity, over-abstraction, and redundancy. Reports findings with severity ratings and…

HTML is the new markdown. Lavish is the new editor for your HTML artifacts.

Implement and diagnose iOS Liquid Glass with SwiftUI and UIKit using focused guides and public API references.

Creates, executes, and amends graph-based campaign roadmaps.

Version-aware guidance for writing, reviewing, and modernizing Java projects.

Direct Chrome DevTools Protocol access. Skill mode plus MCP mode, zero dependencies.

Present focused evidence and collect typed review decisions from coding agents.

Plan focused tests, execute project-native test commands, and review regressions with specialized Copilot agents.

Community package for the official Notion hosted MCP plugin for user-authorized workspace access. Search pages, read docs, edit content,…

Octo Industries engineering standards: secure-by-default guidance and a pre-merge checklist.

Run one piece of work across several herdr agent sessions, one git worktree per unit.

Connect ChatGPT to an authorized ORDAX device for grant-scoped projects, typed Computer Control, files, Git and specialized adapters.

Run and resume sustained project work with a durable task ledger, bounded attempts, evidence checks, and morning handoffs.

Preview: one orchestrator session runs work across several repositories or parallel streams of one repository - plan, work packages,…

Structured PHP edits for coding agents: named selectors, hash-guarded batches, format preservation and explicit validation results.

How to work: weigh problems in proportion, think before building, fix corrections as classes, failure classes to check, project tooling,…

Delegate Pi code reviews with native sandboxing on macOS and Linux.

Community package for Playwright MCP. Automate browsers and inspect web pages through Playwright.

Browser automation with playwright-cli for web testing, form filling, screenshots, and data extraction

Playwright E2E テストの作成・レビュー・CI 設定を支援する。待機、ネットワーク、認証、ダイアログ、再試行の不安定さを扱う。

Windows-only PowerPoint automation plugin that bootstraps the latest PowerPointMcp MCP runtime on first use.

Generates a consistent pull request (or merge request) title and description from the commits on the current branch, and provides a…

Review pull requests and local changes for bugs, gaps in test coverage, unclear comments, and error-handling and type issues.

Generate submission readiness reports, executable connector tests, policy and publisher records, and post-launch plans for OpenAI and…

Catches AI coding agents gaming their test suites: deleting tests, skipping them, weakening assertions, or hardcoding outputs to fake a…

Read-only, evidence-backed technical project review across applicable architecture, code, security, delivery, operations, and lifecycle…

An engineering prose standard for agent-written text: short active sentences, plain words, comments that explain why, and labelled review…

Proseweaving: house standards and verification for agent-authored human-facing prose.

Record a demo, tutorial, or proof movie of software actually running — and catch the silent defects (frozen picture, narration talking over…

Create focused tests for Python FastAPI applications.

Review one decision document with Quorum's independent model panel.

Evidence-first simplification: prove and remove accidental codebase complexity

Run this workflow from Codex. Analyze Claude Code session logs to identify what went well, what didn't, and how to improve developer-AI…

Concise code review skill. Search and hydrate it instead of preloading.

Review animation code against a strict craft, performance, interaction, and accessibility bar.

Practice code reviews and get focused feedback on missed issues.

Run long repository roadmaps through fresh sequential Codex workers without a model-backed coordinator.

Design, mock, test, document and monitor your APIs from one living OpenAPI spec.

Implement, refactor, and review production Rust code with clear domain models and maintainable module boundaries.

Keep plans and delivered work aligned with user-approved anchors using Jev-backed gates.

Plan broadly, build narrowly, test reality, expand deliberately. A planning interview that produces an Architecture Document, an…

Enforce a search-before-edit workflow: locate relevant files, symbols, call sites, and surrounding context before proposing or making code…

Enforce a search-before-edit workflow: locate relevant files, symbols, call sites, and surrounding context before proposing or making code…

Application-security review skill for codebases and pull requests you are authorized to assess. Maps trust boundaries, keeps issues as…

Threat modeling, secure coding, and severity-classified security review for software and AI-agent changes, grounded in OWASP practice and…

Community package for the official Sentry hosted MCP plugin for human-in-the-loop debugging, issue triage, and incident workflows through…

Diagnose and fix flaky e2e tests and connectivity issues in service mesh environments (Kuma, Istio, Linkerd, Consul). Covers 11 root…

Ship a change or coordinate an approved plan through independent issues, adversarial gates, PRs, CI, repository-required review, and merge.

Delivery workflow where done means an open pull request with proof: branch, check for existing PRs, plan, independent plan review, build…

Write, run and audit skill-lens eval suites for Agent Skills: which cases a skill needs, which check fits each claim, and what a failing…

Spec-driven software delivery with independent model review, layered verification, and Playwright video evidence.

Risk-scaled software-engineering guidance with sparse expert routing

Analyze code for violations of the SOLID principles of object-oriented design (Single Responsibility, Open/Closed, Liskov Substitution,…

Make your AI prove its work before it ships: it plans before it builds, checks its course while it builds, shows every goal working, and…

SwarmForge as an Agent Plugin: tmux-based multi-agent orchestration for git worktrees (two-pack / four-pack / six-pack workflows), with…

Audit a repo for technical debt, research version-specific best practices, and file an umbrella GitHub tracker issue with one rated,…

Write tests that verify behavior (not implementation), use table-driven/parameterized patterns, and minimize mocking. Supports Go, Python,…

Create, position, format, and update native think-cell charts from user-supplied donors with native verification.

Explore, run, and build Tines 3B workflows from your agent.

GitHub workflow skills for enriching PR descriptions, automating code review context, and streamlining collaboration through the gh CLI

Explore web applications and create reliable Playwright UI tests with a focused test engineer agent.

Risk-first PR/branch review: blast radius, agent-authored checks, call-graph pincer, structure.

Turn a hackathon project's repo into a judge-ready demo video: the real app recorded in a browser, animated explainers for the hidden…

Enforce a claim-to-proof workflow: define the evidence, run the right verification, and distinguish verified results from assumptions…

Enforce a claim-to-proof workflow: define the evidence, run the right verification, and distinguish verified results from assumptions…

Give your agent runtime evidence: semantic code search, dead-code detection, and fault localization over real runs — zero code changes…

Consent-first AI visual QA for web features built with GitHub Copilot. Generates and runs Playwright tests only after explicit user…

Vitest skill for AI coding assistants: Vite-native unit and integration testing.

Interactive local workspace for reviewing and iterating on Markdown and agent-generated HTML artifacts

Use the WebEngine CLI and local daemon for persistent browser automation without MCP.

Send one explicitly authorized WeChat message from macOS with local recipient and draft verification.

How to work: weigh problems in proportion, think before building, fix corrections as classes, failure classes to check, project tooling,…

Create a technical architecture design document and a tightly coupled, executable development roadmap.

Blocks narrow fixes: a Hypothesis Ledger with a mandatory zoom-out hypothesis before any bug fix, root-cause diagnosis, or plan is called…

Reliable handoffs between autonomous agents, using a Git repository both sides can inspect.

Named advisor profiles from WATCHDOG.yml, reviewed by a secondary model after each completed agent turn.

數位行銷代理商專用 Agent 集合，涵蓋工程、設計、行銷、銷售、測試等 14 個專業類別，共超過 140 個專業 Agent。

Evidence-first coding agent. Verifies before presenting. Attacks its own output with adversarial multi-model review, IDE diagnostics, and…

Search and quickly navigate Arc's history and open tabs

Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working…

Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working…

Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working…

Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working…

Skills for Azure Architecture Center documentation maintainers: discover needed updates and review multitenant docs for currency, accuracy,…

Native /bug, /fear, /journal, /grasp, and /do commands that append context-rich personal log records.

agent-tools-runtime plugin for ccdd-gate: a stdio MCP client wrapping the ccdd-complexity server (deterministic, AST-based Python…

Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.

Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.

Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.

Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.

Start, supervise and review your AI coding agents from a conversation.

End-to-end code quality: analyze conventions, write conformant code, review quality, and audit cognitive debt.

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Corezoid Actor Engine assistant. Exposes Corezoid operations as an MCP server and provides skills for creating, editing, reviewing, and…

Essential prompts, instructions, and chat modes for C# and .NET development including testing, documentation, and best practices.

Essential prompts, instructions, and chat modes for C# and .NET development including testing, documentation, and best practices.

Essential prompts, instructions, and chat modes for C# and .NET development including testing, documentation, and best practices.

Essential prompts, instructions, and chat modes for C# and .NET development including testing, documentation, and best practices.

Agent plugin for discovery and investigation work before planning or implementation.

Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai

Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai

Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai

Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai

Let your coding agent work with real Microsoft Excel workbooks from the terminal: formulas, Power Query, PivotTables, charts, and VBA. Same…

Ezra skills: automacao, governanca, estudos e agentes

Evidence-backed defect diagnosis, repair, and validation for React and .NET repositories.

Four focused subagents — researcher, planner, code-reviewer, debugger — for deep codebase research, dependency-aware planning, pre-commit…

Codex marketplace bundle for frontend application development, including React, accessibility, UX, testing, and Feature-Sliced Design.

Plan, implement, review, and correct changes with your coding agent. Request each phase separately, follow an agreed plan, and check the…

Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and…

Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and…

Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and…

Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and…

GitHub workflow skills for PR review evaluation, Dependabot PR management, Copilot resource optimization, and AI guidance scaffolding.

Specialized Go development and quality engineering suite with compiler-verified smart editing, automated test analysis, and mutation…

Personal reusable agent skills for safe installation, compact command output, settings curation, and scientific debugging.

Project-neutral, multi-agent workflow core: a fixed backbone of steps that drives an issue from backlog to done, customised per project via…

agent-tools-runtime plugin for kite-lite: a stdio MCP client wrapping the kite-lite browsing/rendering engine, plus a deterministic…

Codex marketplace bundle for language, testing, async, performance, and framework patterns.

Optional full set of NaNLABS agent / subagent personas (reviewers, architect, planner, e2e, …)

Ship software and lead the people who build it — git workflows, architecture decisions, code quality, testing, APIs, and infrastructure.…

Starter template with a lifecycle hook that emits a user-visible plugin message.

Planning, requirements, diagramming, estimation, and release engineering skills.

Windows-only PowerPoint automation plugin that bootstraps the latest powerpointcli runtime on first use.

Modernize PowerShell test suites by migrating Pester v4 tests to Pester v5.

Review GitHub pull requests in a read-only canvas with AI-grouped changes, expandable diffs, and questions scoped to groups, files, or…

Review GitHub pull requests in a read-only canvas with AI-grouped changes, expandable diffs, and questions scoped to groups, files, or…

Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for…

Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for…

Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for…

Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for…

Proving the system works and keeping the repo presentable: LLM evaluation, test strategy, E2E acceptance suites, security review,…

A dedicated Pi refactoring agent with isolated sessions, repository impact tracing, and behavior-preservation checkpoints.

Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.

Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.

Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.

Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable,…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable,…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable,…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable,…

Authentic user insights from autonomous AI agents, backed by evidence.

Model-tiered Claude Code subagents: haiku for mechanical execution, opus for judgment-heavy development, fable for read-only review

An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.

Force-loads the global swamp skill so Kiro always has authoritative swamp CLI guidance — models, workflows, data, CEL, vaults, extensions,…

Local test plugin for validating Codex-compatible hook behavior in Owls.

Run a detected project test suite when a Copilot CLI session ends.

Comprehensive collection for writing tests, test automation, and test-driven development including unit tests, integration tests, and…

Comprehensive collection for writing tests, test automation, and test-driven development including unit tests, integration tests, and…

Comprehensive collection for writing tests, test automation, and test-driven development including unit tests, integration tests, and…

Comprehensive collection for writing tests, test automation, and test-driven development including unit tests, integration tests, and…

Anti-slop engine and profile router for software development workflows.

Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL…

Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL…

Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL…

Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL…