claude-code

Switchable output styles for Codex and Claude Code, enforced by hooks and switched from the chat with ::

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

The definition loop: decide WHAT to build. Competitive industry research -> product spec (SPEC.md) -> plan with the…

Adam's machine-bound skills that need local resources (WSL/Windows homes, local files, a signed-in browser): PDF…

Never reconstruct where you left off. Local-first continuity for you and your coding agents — resume, decisions, and…

The video step for Claude/Codex UGC workflows: skills and a hosted MCP server for captioned vertical videos, narrated…

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

Full lifecycle manager and optimizer for agentic skills — author, densify into micro-kernels, pack, unpack, pin, sym,…

Configure Claude Code Remote Control server mode and choose between the current computer, Claude web, an existing host,…

Skills that audit and fix agent plugins so one DRY repository works in GitHub Copilot CLI, VS Code, Claude Code and…

A dual-path memory system for proactive agents: a typed knowledge graph with evidence, contradictions and supersession,…

Skills for forward-deployed engineering (FDE): discovery, AI solution design, enterprise integration, agent evaluation,…

Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task…

Apply the guidance Anthropic publishes on claude.dev to your Claude Code and Claude API work, with a live check for…

Delegate read-only coding tasks from Codex to supported local external agents and continue them by explicit session ID.

Turn local web projects or hosted web URLs into macOS Dock apps on a local agent host.

Local WhatsApp MCP tools and a graphical UI candidate for Codex on macOS: scoped reads and confirmed replies. Native UI…

Closelly MCP App: skills y connector portable para ChatGPT/Codex, Claude Code y GitHub Copilot CLI.

UX and visual judgment for agent-built UI: a build brief before you build, a scored review after.

A toolkit for working with AI agent harnesses: detect which one is running, query its managed-policy locations, plugin…

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

Harness-agnostic scheduled tasks for AI coding agents: Codex-automations-style recurring runs with any harness and any…

Portable developer-workflow and design skills: canva-studio, codex-review-loop, fable-mode, figma-studio,…

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

Scaffold AI-agent config for a repo: instructions, guard hooks, frontend/backend skills, git-reconciler sub-agent,…

Memory abstraction layer for Claude Code, Codex CLI and Pi: deterministic capture hooks plus model-driven skills over a…

Context-firewall skills and custom agents for Cursor and Claude Code

Run this workflow from Codex. Reverse the built-in Claude Code limitations discovered in the source code leak. Installs…

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。

Isolated project memory, planning, and task context for Codex and Claude Code

Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex / Cursor bundles,…

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

Unofficial Codemagic build operations and iOS/Android signing guidance for coding agents.

Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts

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

Managed Codex and Claude autonomy, local scheduling, CI isolation, and guarded maintenance for Hraness repository work.

Self-evolving second brain with 36 AI agent skills, 10 agents, and people CRM. Closed-loop harness: a V-model…

iEvo — self-evolving plugin for AI coding agents (Claude Code, Codex). Universal via the agentskills.io standard.…

CoDesign gives AI agents like Claude Code, Codex and PI a real design engine for genuine, editable designs, not flat…

impstack, imperfect operator.

Tencent CloudBase — AI models, authentication, NoSQL/PostgreSQL databases, cloud functions, cloud storage, CloudRun…

Cross-cutting agent skills (boost, commit-msg, create-readme, release, …).

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

A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect,…

Turns your coding agent into an architecture diagrammer: describe a system in plain language and it writes, checks and…

Design and edit ERD Designer (.erd) files with an agent. Provides a bundled CLI and a skill so agents can add tables,…

281 Agent Skills for researchers: scientific and research paper writing, journal formats, literature review, citations,…

A collection of portable skills for AI coding agents.

Give the user their RAPP Brainstem and operate setup, verification, repair, updates, and maintenance end to end.

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

The rness workspace in Claude Code: /rness:status, /rness:adr, /rness:spec, /rness:plan.

Human-first skills for writing cleanup and evidence-based work reports. Built by Long.

Delegate bounded work to an explicitly selected local model through an existing Forjal connection.

Evergreen skills for building Roblox games with AI coding agents: connecting to Studio's built-in MCP server the safe…

Publish games with FanZero and connect with content creators through launch visibility and revenue-share pacts.

Official-source Indian legal research, judgment briefs, drafting (including Bombay High Court s.528 BNSS quashing…

Optional, explicitly invoked delegation to Claude Code or its CLI

要件定義→設計→実装→テスト→リリースを一気通貫でオーケストレーションする開発ハーネス（GitHub Copilot / Claude Code 対応。Antigravity はアダプタ同梱・未検証）

Discover and load Agent Skills from configured local directories, plugin marketplaces and Git sources through MCP tools…

Método comum de equipe multiagente: ativação explícita, níveis, rodada em fatias com prova, passagem entre ferramentas…

Evidence-first application-security Agent Skill for repositories and environments you are authorized to test. Maps the…

Portable skills for repository setup, private remote development, code-native design exploration, design-system…

Risk-adaptive software engineering operating skill for reliable AI-assisted vibe coding, architecture, staged…

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

Intent to implementation: ready, then go.

Create, audit, and convert Agent Plugins 1.0.0 packages, then guide reviewed marketplace release. Agent Plugins 1.1.0…

An opinionated workflow for shipping production-ready changes with coding agents.

Initialize standards-based agent configuration across agent harnesses

Legalcode for Claude Code with public Legalcode MCP access and 10 core legal research and drafting skills.

CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.

Portable ESRA skills with a guarded autonomous controller for OpenClaw and Hermes Agent.

Design, build, and equip AI agents — personas, skill authoring and evaluation, plugin packaging, prompt-ready context,…

Coalesce, schedule, and stream cargo so concurrent agent sessions share compiles instead of fighting locks.

Action guardrails that check AI coding changes against explicit project constraints.

A collection of agent skills: brand asset audits, comprehensive docs, READMEs, deep bug hunts, repo CI setup, and…

The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and…

Build public social-data pipelines, competitor trackers, creator research, comment analysis, transcripts, summaries,…

How to author an agent plugin as one pluginfinity source and build it for Claude Code and GitHub Copilot: the config,…

Local-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index…

Tells you whether a change to an agent-consumed document actually worked: paired comparison with a confidence interval…

Cross-agent catalog of reusable Agent Skills with provenance-aware lifecycle management.

Turn your agent into an autonomous Hyperliquid trading desk: seven specialist roles and twenty-four skills, a policy…

Blocks unsafe git subtree invocations: URL fetch, missing --squash, missing -S/--gpg-sign, and subtree push.

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

Create, update, and inspect Charming-hosted interactive web apps via the Charming MCP server.

Techsio UI Kit AI — skills for developing and consuming the @techsio/ui-kit design system (libs/ui): component usage…

Tencent CloudBase — AI models, authentication, NoSQL/PostgreSQL databases, cloud functions, cloud storage, CloudRun…

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

Agent skills for real Figma files: Plugin API gotchas, checks before and after every write, comments to verified fixes,…

Software documentation specialist with arc42 DESIGN_DOC.md, architecture docs, Mermaid-first diagrams, and PlantUML…

Claude API and MCP development workflows paired with the live Claude Code documentation MCP.

Äußerer Loop für Coding: Grok Bot plant, Cursor Cloud Agents schreiben gegen eine GitHub-Organisation, Claude Code…

CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana…

Denglema Agent usage adapter: Codex local snapshots plus a harness-agnostic Skill and schema v2 upload contract.

Reusable agent skills and a public workbench for harness setup.

Plugin for CLI agents — credential leak prevention via PreToolUse + PostToolUse hooks that block secret-leaking…

Hält die Agent-Doku (CLAUDE.md/AGENTS.md + Rules) am Code: Sync als Standard, --audit für den vollen Report, --fix…

Comprehensive sample plugin demonstrating portable Agent Skills and MCP alongside Claude Code extensions.

Agent-driven client POCs: shared skills, MCP tools, and scripts for live demo environments.

The build and verification loops: take one Ready issue at a time from the board to a merged PR, and prove each change…

Keep Claude Code, Codex, and other coding-agent terminals available after disconnects, using the least infrastructure…

Orchestrate complex multi-task work by separating advisor reasoning, delegated execution, and independent verification…

Cloudflare のソース主導セキュリティ監査。通常は関連ガイダンス、明示されたコードベース監査・包括的レビュー・報告成果物の依頼では六段階の検証と報告を実行する。

Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring

CloudBase Sites — create, save, deploy, and inspect React/Vite web apps hosted on Tencent CloudBase. Inspired by Codex…

Design skills: brand, design, design-system, ui-styling, ui-ux-pro-max.

TradingView Pine Script v6 for coding agents, backed by a real validator rather than prose. A language skill plus an…

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

Evergreen skills for driving Unity with AI coding agents: the official Unity CLI and Pipeline package, headless…

Discover FanZero for indie game distribution, assess fit from supplied context and draft a listing and creator launch…

Changesets skills for AI agents — set up releases and write changeset files.

Legalcode Pro for Claude Code with Pro MCP access and 10 core legal research and drafting skills.

Run Quick Gate CLI 0.4.0 as one deterministic JavaScript/TypeScript gate and read its gate-result/v1 verdict

Author and maintain Agent Skills — scaffolding, spec compliance, evaluation, and cataloging. Keep a skill library…

Architect agent: plan, delegate to code agents, grade implementations, iterate to a quality bar. Agent Skill Standard +…

Lints every agent edit with oxlint (PostToolUse) and blocks edits that weaken the oxlint config (PreToolUse).

CloudBase Sites — create, save, deploy, and inspect React/Vite web apps hosted on Tencent CloudBase. Inspired by Codex…

Erklärt die letzte Antwort in einfacher Sprache neu — gleiche Aussage, keine neuen Informationen.

Native Notes, Calendar, Reminders, Mail, Safari and screenshots with intent-oriented MCP tools.

Always-on control plane: what the Plenipo platform already gives you (so you never rebuild it), how any Plenipo product…

Read-only repository audit for choosing between a rebuildable remote-agent task and a persistent development workspace.

Create Conventional Commits safely, including logical commit stacks over mixed working trees and plan-traceable commit…

Claude Code の settings.json または Codex の config.toml を対象別に構文・スキーマ検証する。ホスト固有の設定と hook 仕様を区別。

Python quality gate CLI for Ruff, Pyright, and pytest with bounded auto-repair and escalation artifacts

Python archetype skills (python-coding, runic-ogm, docker-multi-stage, …).

A communication layer for your AI coding agent: plain language, no jargon, no invented timelines, and one clear yes…

Automate macOS apps via Apple Events using AppleScript (discovery) and JXA (production).

Richtet CLIProxyAPI und eine claudex-Funktion für Claude Code mit GPT auf macOS ein — installieren, aktualisieren,…

NYCU portal, E3 coursework, public timetable and part-time attendance through MCP.

The front door. Eight loop verbs that drive every other plugin so you never have to remember the rest: setup (make a…

Improve performance, resource use, determinism, or simplicity through measurement, profiling, benchmarks, and proven…

Bounded public search evidence with source-explicit supersearch.search.v1 receipts (pinned hermes-supersearch 0.11.0);…

reflex.dev / AppKit web skills (appkit-*, reflex-*).

Autonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps…

Translate a validated AGER/OKF AgentGraph into a Claude Agent SDK lead + subagents project (max_turns, tools).

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

Proxmox and gateway operations through MCP: guests, port forwards, internal DNS, and Caddy.

The discovery loop: inventory every product already built on Plenipo, map industry coverage, and rank unclaimed…

Author self-contained implementation plans, multi-plan programs, or compact handoffs that a fresh agent can execute…

Terraform / infra skills (terraform-*).

Skill that makes your coding agent stop and ask instead of silently resolving spec ambiguity, picking up workarounds,…

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

Destilliert die laufende Session in ein Übergabe-Dokument, mit dem ein anderer Agent direkt weiterarbeiten kann. Die…

Personal web tools and research demos with fixed zyx corners and a focused workspace.

The design loop: decide the SHAPE once, against the platform rather than from scratch. Which modules and manifests,…

Survey a codebase as a senior advisor, report prioritized improvements, and implement selected fixes or produce handoff…

Translate a validated AGER/OKF AgentGraph into a Claude Managed Agents YAML manifest (entry, loop, agents).

Baut aus einer MSI/EXE ein in sich geschlossenes Intune-Win32-Paket (App\ + Output\ + IntuneWinAppUtil.exe + Pack.cmd +…

Uber Eats order history, receipts and group-order ledgers through MCP.

The platform side of the request protocol, enabled in the Plenipo repo only: triage the incoming platform-request queue…

Write, edit, or audit READMEs, docs, landing pages, and other prose so it reads like a person wrote it, without…

Wizard-style codebase exploration, documentation, and Q&A with auto-captured sessions.

Windows-Dev-Umgebung: /windev vermisst read-only, --fix behebt die Befunde mit Backups, --setup richtet…

zyx skills for slides, docs, academic writing, Next.js and the dev workflow.

Turn a product idea, loose PRD, or inconsistent pre-implementation repository into an implementation-ready…

Translate a validated AGER/OKF AgentGraph into a Codex plugin. Multi-host: Claude Code, Grok Build, Codex, Cursor,…

Produce a strict evidence-based release verdict with severity-ranked findings, blockers, a pre-release work batch, and…

Build static sites with Zola (Rust SSG): Tera templates, taxonomies, deploy.

Analyze local Codex, Pi, and Claude Code session logs for cost, token waste, cache misses, retries, and duplicate…

Translate a validated AGER/OKF AgentGraph into a CrewAI hierarchical Crew (manager_agent, max_iter, tasks).

Search local Codex, Pi, and Claude Code session history to recover prior decisions, feedback, prompts, and conversation…

Data Engineering Knowledge Capture: schemas, lineage, medallion, semantic models, and glossary into a durable OKF…

Fetch a URL or convert a local file (PDF, DOCX, HTML, and more) into Markdown with markitdown, optionally summarizing…

Debugging-first guidance for professional Docker development (CLI, Compose, Desktop, Rancher).

Write and review X/Twitter posts and threads using the reach mechanics of X's open-source recommendation stack.

Software documentation specialist with arc42 DESIGN_DOC.md, architecture docs, Mermaid-first diagrams, and PlantUML…

Translate a validated AGER/OKF AgentGraph into Google ADK (Python, TypeScript, Go, Java, Kotlin) — LlmAgent (non-graph)…

Universal agent plugin for Google developer documentation style. Skills, a custom output formatter, and hooks for…

Translate a validated AGER/OKF AgentGraph into a Grok Build plugin. Multi-host: Claude Code, Grok Build, Codex, Cursor,…

Generate cover images and in-article illustrations. Imagen direct adapter plus explicit Grok and Codex agent-engine…

Convert Mermaid and PlantUML into slide and article figures. Themes as YAML. Layout-hints prompt. Fidelity judge.…

Translate a validated AGER/OKF AgentGraph into a LangChain Deep Agents project (skills from AgentNodes,…

Translate a validated AGER/OKF AgentGraph into a LangGraph StateGraph (Send fan-out, LoopPolicy breaks, ScratchPad…

AWS CDK v2 TypeScript guidance: stacks, troubleshooting, CI/CD, service patterns.

Modern Python coaching: types, async, packaging, testing, Pydantic, FastAPI.

OKF Agent Graph Engineering Runtime (AGER): author multi-agent loop graphs as OKF and reverse-engineer existing agent…

OKF graph engine: validate, walk, pack, and impact-analyze Git-native knowledge graphs. Owns Catalog and ContextPack.…

Git-native join table linking any OKF noun to any other, including temporal nodes. Not a search index.

Replication of an OKF bundle across machines, plus read-only MCP access. No write verbs.

Chronological spine for agent memory: Session → Hour → Day → Week → Month → Year. Git-native OKF plugin.

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

Pack a module into one markdown or YAML file. Unpack YAML to a directory. Harvest or generate examples from a book,…

Project Knowledge Capture: meetings, experiments, decisions, TicketLink/WikiTicket work, and project-memory nouns into…

Layer 1 projector: OKF research → Agent Brain (Chroma + BM25 + Kuzu). Owns no nouns.

Research Knowledge Capture (RKC): ingest deep-research dumps and articles into an OKF ContentPack of areas, subjects,…

Shared foundation for Spillwave ContentPack plugins: OKF schemas, typed edges, deterministic write helpers,…

Unified multi-platform marketplace plugin bundling document-specialist, Mermaid, PlantUML, imagen-diagrams, Google Docs…

Spillwave skills catalog: Docker, LocalStack, Zola, macOS, Python, AWS CDK, Codebase Wizard, Google Docs style, UI…

ASD-STE100 Simplified Technical English gate: Claude Code skill + output style, local orchestrator/editor/adversary…

System Architecture Capture: reverse-engineer services, packages, IaC, CI/CD, IAM, and runtime topology into a durable…

Build, test, and debug AWS-native systems locally with LocalStack (Community/Pro).

WikiTicket SDD (worklog): git-native plans, tickets, roadmaps, and wiki publishing. Multi-host bindings. Knowledge-tree…