Multi-agent orchestration

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

Skills for writing, sprint work, codebase workflows, and neurodivergent-friendly executive-function support (ink), plus a multi-lens…

pstack の設計・実装・レビューを Codex・Devin などの Agent Skills 対応環境で使う共通ラッパー

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

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

Rigorous engineering skills and principles from the Cursor plugin pstack by Lauren Tan.

Lauren Tan's PStack skills from cursor/plugins (pstack/), with tdd and teach as pstack-tdd and pstack-teach.

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

Agent Skills for rigorous, parallelizable engineering work.

VS Code and GitHub Copilot port of poteto's pstack. Rigorous playbooks, parallel subagents, and verified work.

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

Portable engineering workflows, reusable skills, and principles for coding agents.

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

Routes coding, documentation, and work lifecycle tasks to current MSX standards.

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

Composable agent-workflow skills for planning, communication, knowledge work, and media analysis.

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize…

Rigorous engineering workflows for writing less, higher-quality code and parallelizing with verifiable evidence.

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.

Portable multi-agent harness for .agents-based skills and workflows

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

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

Paved engineering commands for AI coding agents: repository context, governed workflows, explicit Tools, verification and evidence,…

Darkroom Engineering coding standards and reusable engineering workflows for Codex.

A Codex engineering toolkit with orchestration, task ledgers, solve loops, policy-gated effects, async GitHub Stack Merge, catalogs, and…

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

Feedback-based control system for coding agents.

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

Structured AI development: orchestrated fan-out, advisor gate, intent routing, and skill-driven workflow for Claude Code

Morning Star — Agent Plugin for harness engineering workflows: a TS Harness Workflow Engine (@mstar-harness/engine) that enforces…

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.

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

Adaptive office engineering runtime: routed execution, independent review, verification, and closeout through one `office` CLI.

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

Gabriel Operator skills for domain-specific Personas: ontology, Data Feeds, Signals, approved playbooks and evidence-backed ROI, plus…

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

Apptension SDLC processes as skills, each carrying its own portable agent contract for how we work.

Personal agent skills for launching, inspecting, coordinating, and reviewing multi-agent development work.

開発用プラグイン

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.

A skills-first project operating system that inspects, resumes, builds, verifies, and hands off software work.

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。

Hands — extra hands for your repo: an expo/station agent fleet for Claude Code on a per-repo coordination bus. Strict pass discipline…

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

Portable Agent Skills and read-only local tools.

稳态发育多Agent架构 + 软件发育系统（Software Growth Studio）落地插件：包含顶层元架构、软件基因组（唯一真相源）、一致性引擎、质量门禁、生长预算与受约束编码完整体系；L1~L4渐进式技能集与配套稳态治理 MCP…

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…

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

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

Eplayment Android development workflow: Jira intake with the related BE and UI tickets, plan, branch, lint, version, test, code review,…

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

Spec-driven project execution pipeline, from ideation to verified deliverables, orchestrated by AI agents. Works with any project type.…

The Upstash MCP server plus agent skills for every Upstash SDK and CLI — Redis, QStash, Workflow, Box, Blob, Ratelimit, Vector, and Search.

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,…

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…

Portable maestria engineering methodology delivered as Agent Skills for compatible clients.

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,…

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

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

Portable workflow skills for research, planning, implementation, debugging, and review

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

John's consolidated development workflow, engineering standards, worktree, task, review, and agentic-system tooling.

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

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

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

A software development workflow for coding agents.

Blackadder DLC for Cursor: idea → plan → architecture + design system → walking skeleton → verified tracer-bullet slices → release.…

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

Portable Meta-Architect skills for architecture, evidence, review, and bounded autonomous coding workflows.

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

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。

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

Ennoia에서 에이전트 생성, 문서 지식 연결, App 실행, 운영 진단과 제품 피드백을 수행합니다.

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

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

Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting…

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

Spec-driven project execution pipeline backed by Linear. Same skills and agents as spec-plugin, but writes specs, stories and validation to…

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

Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting…

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

Standardizes everyday development work and house conventions.

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

Self-coordinating Codex engineering team for interfaces that expose agent conclusions, supporting evidence, provenance, traces, proposed…

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

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

Focused personal skills for PR authoring, review feedback, readiness, cleanup, commit messages, and release notes.

Saint Tibo agent workflow format: serena-first session boot, GitHub-first issue loop, agent-first handoff.

Kotgent task and structured-plan workflows with browser review, coordinated worker sessions and verified serial merges

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

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

Discover grouped Agent Sessions peers and orchestrate durable Codex, Claude, Grok, and Qwen lanes from Qwen Code.

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

Run Claude Code as a department: roles, a shared protocol, and the skills that drive them.

Evidence-first product and engineering work tracks with capability-gated orchestration.

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

Project-scoped Guardian operations with Cognitive Evolution, verified meta-learning, cross-Guardian knowledge transfer, confidence…

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

Local agent orchestration board with Kanban UI, MCP task handoffs, and semantic knowledge base

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

Build agents and their interfaces: write prompts, skills, and MCP servers, delegate across subagents, enforce output schemas, and use…

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

Personal agent plugins

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

Drive CLI Agent Orchestrator multi-agent sessions from any Agent-Plugins-compatible client. Prerequisites: the `uv` toolchain must be on…

Generic toolkit for driving a local ComfyUI 8188 server: workflow submission, queue monitoring, image download, and reproducible generation…

Agent Plugin that provides Kiro agent orchestration via delegation.

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

Nika — intent-as-code for AI workflows: author a reviewable DAG in YAML, audit cost and permits before running, keep tamper-evident traces…

MCP tools for Pants build system with devcontainer integration

Five skills that scope, draft, review, test and export Talentsia skill packs with bounded subagents, from a shared contract and template.

Reusable skills for agent-asset audits and upgrades, project setup, and reliable agent behavior.

Durable scripted Codex workflows with bounded workers, ordered replay and a local control desk.

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

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.

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

Cross-vendor sub-agent broker with structured envelopes, council, governed deliberation, and authenticated local browser surfaces; optional…

Event-driven After Action Review with scoped improvements, evidence, feedback, journal and rollback.

Team delegation, focused delivery and explicit Codex project setup with an optional model guard.

Shared Compass workflow and project setup for Claude Code and Codex.

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

Session handoff and continuation for Codex. Compact conversations into structured handoff documents for task continuity, then find and…

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

Holdex workflows as agent skills: contributing rules for issues and PRs, bug attribution, and time tracking.

Inter-agent coordination bus: task queues with claim/ack leases, shared result store (SQLite), routing driven by a project-declared roster…

Luna-first orchestration with a local Rust control plane, durable runs, and an MCP Apps workbench.

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

NCP — an agent-to-agent memory bus over MCP. Bounded, trust-weighted context assembly, durable cross-session memory, and directed whispers…

Translate a validated AGER/OKF AgentGraph into Orca ADE orchestration — named worktree agents, parallel fan-out, orca-cli + orchestration…

Context and workload governance for Codex Desktop and ChatGPT Work using Orquestrador Maestro.

Configurable cross-client architect orchestration with lazy setup, exact user-selected native roles, risk-routed Astra and Terra…

Amazon requirements discovery and persistent multi-agent delivery with local code intelligence.

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

Configurable cross-client architect orchestration with lazy setup, exact user-selected native roles, safe adapter installation, and a…

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

Shared project memory and cooperative edit ownership through a local memd daemon.

Put a Capy thread on Agent Relay through Agent Relay Cloud: the thread gets its own relay agent, messages to it are posted into the thread,…

Multi-agent coordination with agent-swarm MCP

Agents and DAG workflows as MCP tools: run agent definitions and multi-step workflows from any MCP client, no native subagent support…

Minimal runtime-neutral engineering policy with proactive execution optimization and objective-level review DAG planning for one,…

Open once, then let Codex and Claude collaborate automatically in the native chat.

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

Use this plugin for atlassian cloud, Jira, and Confluence workflow research and implementation guidance.

The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no…

Delegate coding tasks from MiniMax Code to locally installed coding CLIs (Claude Code, Codex, Kimi Code, ZCode, DSH) through a…

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

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

Fizzy workflows for boards, cards, comments, account setup, self-hosted management, and connector-native MCP access.

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

图谱上下文压缩与任务规划插件（10 个 MCP 工具）。能力：压缩上下文、DAG 规划、增量建图、技能飞轮、诊断与产物导入导出。DeepSeek Harness：dsh plugin --profile web add @roarpeng/graphflow；工具名为…

Run a mission too big for one agent: turns your coding agent into a director that raises a horde — workers in worktrees, one ticket each, a…

Huddo group chat for Hermes: join rooms where people and AI agents talk together by invite link, read and reply, whisper to one member,…

Skill that turns your coding agent into the director of a feature branch: an issue loop (kept out of git by default, committed when you…

Jujutsu (jj) version control for teams of coding agents: one workspace per agent, safe integration, and recovery through the operation log.…

Labflow research workflow plugin for GitHub Copilot & VS Code Agents Window

Plan complex tasks as editable multi-agent workflows. Review the topology before execution, follow live results, and repair failed scripts…

Client delivery workflows and bootstrap

Plan complex Codex work into safe, dependency-aware parallel slices.

ODW for Cursor, Grok Bot (via Cursor CLI), Grok Build, ZCode, Antigravity and Copilot, with safe worktree isolation. Claude and Codex hosts…

Six independent specialists, a Verifier and a Judge assess whether a project is worth building.

Rolecasting: portable model selection and delegation topology for agent work.

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

Token plane: PreToolUse hooks that keep whole-file reads of large files and unbounded repo-wide searches out of the main context, plus…

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

Delegate focused work to other installed agents and coordinate the results.

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,…

See your ChatGPT and Codex work as a small visual team — who is doing what, what needs you, and what is done.

Infinite, editable canvas for plans, architectures, workflows, codebase maps and mind maps, shared live between you and your coding agent:…

Verification-first agent operating system powered by OpenCode Zen and OpenCode Go via ModelHitch.

Orchestrate complex multi-task work by separating advisor reasoning, delegated execution, and independent verification until tasks converge.

Lightweight, evidence-first software delivery for Codex. 中文优先的 AI 软件交付工作流。

Turn multi-step or delegated agent work into a bounded contract with concrete validation and a concise handoff.

Cross-harness dynamic workflows: script-driven multi-agent orchestration for devin, claude, codex, opencode

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional…

Orquestación de modelos por roles: delegación selectiva, continuidad, verificación y registro de uso real.

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

Thin Auto leader: route intent to Fable/Opus/Sol subs, tmp reports, independent review. Use on any non-trivial Cursor Auto or Cloud task.

Framework and tooling for evaluating workflow, skill, and process automation readiness based on the Google DeepMind Intelligent AI…

Prepare bounded mission prompts and coordinate scoped work with Astra, Sol, Luna, and optional GPT-6 Pro Web.

Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. Includes…

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

Plan dependency-linked work, coordinate ready tasks, and track verified progress with Beads.

Translate a validated AGER/OKF AgentGraph into a Claude Code plugin (skills, agents, commands, hooks). Multi-host: Claude Code, Grok Build,…

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

Experimental GPT-6.1 Sol/medium root workflow with Luna/max workers for bounded implementation and exploration.

Coordinated software engineering with one coordinator and delegated specialist agents.

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。

Create, run, monitor, and manage Conductor workflows and tasks

Generates a structured onboarding backlog that takes a team from zero to publishing verified consumer and provider contract tests on…

Turn implementation specs into executable Cortex workflow scripts.

COTAL: the open protocol that lets AI agents from any vendor work as one team. Skills for putting an agent on a Cotal mesh and coordinating…

A multi-agent deliberation hub with 3 core agents and extensible extended agents for structured, multi-perspective decision-making.

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

Explicitly invoked, portable Builder-Critic quality campaigns with dependency-safe parallel work, independent integration review, resumable…

Automatic model and reasoning-effort routing for eligible new local Codex subagents, and for tasks started from the Gearshift composer.

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

Agent plugin for configuring the GitHub Copilot coding agent to use Java 25 (or any JDK version) via a copilot-setup-steps.yml workflow,…

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

Validate handoff manifests and evidence files for AI task交接

IRIS five-step controlled workflow with evidence, error capture, checkpointing, recovery, audit, and verification.

Launch, control and monitor Claude Code, Codex, and Pi workers over tmux.

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

Run authorized local work with durable receipts, recoverable processes, and parallel worker batches.

A teaching bundle for tracked changes: an issue-lifecycle skill, start-tracked-change command, preview-first triage agent, and bounded…

Delegate independent Codex work to parallel OpenCode workers in isolated Git worktrees.

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

Produces evidence-based model routing plans: maps each task unit to the best-suited AI model (Codex, GPT, Gemini, open-weight) using a…

A host-portable, evidence-first workflow for using a separately configured PDF Tools MCP connection.

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

CRAFT+ workflow for turning task descriptions into verified production-ready prompts.

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

A wall of mail slots for parallel coding agents. Each worktree gets a pigeonhole; agents leave each other notes and post what they are…

Twenty-four named engineering principles (prove it works, fix root causes, subtract before you add, build the lever, and more) that steer…

Run the Prism Story and Epic lifecycles as workflows of specialized Callee subagents.

Portable lifecycle orchestration with Case workspaces, legacy Task/Case compatibility, verified migrations, discovery and scoped Git…

Keep durable projects, agents, apps, dashboards, workflows, and reusable skills synchronized to GitHub as the verified canonical record.

PRsquad: Supervised Agentic Workflow for GitHub Copilot. Supervised multi-agent autonomy with deterministic policy enforcement and…

Coordinate RE8CH Teable, LiteLLM, OpenSandbox, KAgent and agent workflows.

Host guidance for bounded Agent delegation and evidence-based acceptance, with tools for explicitly supported executor harnesses.

Hypothesis-driven research orchestration with scored plans, independent discovery review, adaptive workers, resource-aware execution, and…

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

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…

Provides a workflow for creating new projects with the required project structure and technology conventions.

Read-only cost and efficiency audit of sessions that ran agile-skills.

Generic Sessionbus guidance for managed Qwen launches and lanes. Ordinary Qwen discovers the skill without starting a Sessionbus MCP helper.

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

Approach A: link a repository to a shared repo of Squad decisions, routing, wisdom, casting policy, and skills via squad upstream…

Approach B: lay down a pre-built starter Squad team (lead, developer, tester, reviewer, security, docs) in any repository. Each repo gets…

Delegate focused work to other installed agents and coordinate the results.

Composable workflow SDK, local CI runtime, and multi-target compiler for software verification — define checks once, plan locally, run…

Connects Codex to a Swarmail server running on this machine: mail, a session roster and advisory file reservations shared with other…

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

Template plugin showing how Talentsia structures reusable skills: one shared method, self-contained exports, explicit authority and bounded…

How to build, test and analyze thunks with the Thunk.AI Builder MCP. Also install the plugin for your Thunk.AI tenant, for the tools.

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

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…

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

Git worktree management expert for @desplega.ai/wts

Build, extend, port, and test coding-agent plugins: skills, commands, hooks, MCP wiring, subagent orchestration, and cross-harness…

Rewrite instructions with Agent STE, create agent definitions, and orchestrate multi-agent pipelines.

Field notes for building on Gemini Enterprise Agent Platform: ADK vs A2A registration, A2UI rendering, Agent Identity, Agent Gateway, what…

First-party agentic harness skill for Codex marketplace plugin.

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional…

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional…

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional…

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional…

Explicit coding workflows adapted from Lauren Tan's pstack, with independent outcome checks.

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…

19 skills over the cargo-ai CLI, plus the hosted MCP server — build target account and contact lists, enrich and verify them against…

Portable workflow skills for planning, implementation, review, and delivery.

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

Real hands on your own computer for ChatGPT, Claude and any MCP client: project files, shell, Git, editor diagnostics and local coding…

Activate the Edith lead workflow when the user selects or mentions @Edith.

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

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…

Genie's wish, work, review, fix, report and council verbs in Orca's palette and keybindings; genie lifecycle status and review verdicts…

GitHub workflow commands for issues, PRs, and project management using the gh CLI

Activate the Jarvis lead workflow when the user selects or mentions @Jarvis.

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

Deep technical research on Microsoft technologies with multi-agent orchestration and structured documentation output.

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

Multi-agent orchestration system with specialized AI personas, workflow prompts, and skills for VS Code Copilot and GitHub Copilot CLI

The Complete AI Development Toolkit — 110 skills, 36 agents, 162 hooks for full-stack development.

Session-lifecycle skills (status, carry-forward, resume, decision-log), site-design workflows, and Danish property due diligence, with…

Run persistent domain-owning bots through Pi and pi-subagents.

The PowerFlow method as one skill: PRD once, PLAN.md through powerplan (miniplan first, last and per turn), SRS rows before code, close the…

Agent 讲解·演示·协作能力包：概念讲解编排（explain-concept）、D2 结构图、Excalidraw 白板、隔离任务上下文协议，以及论文精读 / 博客共写 / 即时讲解三大工作流命令。

If you want to go fast, go deep first. pstack helps you write less, but higher quality code. Rigorous agent workflows you can parallelize…

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.

Discover local GitHub Copilot CLI sessions and exchange authenticated text messages between them.

Real-time Workshop dashboard with agent signals, honesty calibration, cost-aware desk profiles, and fail-closed Local Delegation.

Real-time Workshop dashboard with agent signals, honesty calibration, cost-aware desk profiles, and fail-closed Local Delegation.

Real-time Workshop dashboard with agent signals, honesty calibration, cost-aware desk profiles, and fail-closed Local Delegation.

Real-time Workshop dashboard with agent signals, honesty calibration, cost-aware desk profiles, and fail-closed Local Delegation.

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

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

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

Per-repo Taskboard coordination skill wrapping atebites-hub/taskboard. Install the Taskboard binary on PATH; this package does not vendor…

Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on…

Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on…

Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on…

Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on…

Activate the Ultron lead workflow when the user selects or mentions @Ultron.