Каталог навыков агентов

Implement hooks for permission control and security in custom agents. Use when adding security controls, blocking danger...

Agent Governance Skill entrypoint. Points to the canonical Codex governance override and included governance skills with...

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment v...

Generate comprehensive handoff documentation optimized for AI agent takeover by analyzing project structure, design docs...

Package agent context and state for handoff between agents or sessions. Use when transferring work between agents, savin...

Agent parameter passing, memory files, and data handoffs between agents

Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency...

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks...

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Bootstrap or upgrade a software repository for agent-first engineering. Use when a user wants to improve project-wide de...

Expert en génération musicale HeartMuLa (lyrics + tags → Suno-like songs)

Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator

Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing ev...

Hire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview...

HR & Recruiter IA — Expert en recrutement RH (job descriptions, screening, ATS, onboarding, culture fit)

HR Tech Specialist IA — Expert en technologies RH (ATS, payroll, benefits administration, employee self-service, DZ labo...

Define human approval points for irreversible, externally visible, costly, or privilege-changing actions in agent workfl...

Give your agent a persistent cross-platform identity. Generate an agent card, emit OADP discovery signals, and register...

TS/JS 程式碼智能重構工具。執行以下操作時自動選用：- 重命名符號 → /rename（取代逐一 Edit）- 移動/重組檔案 → /move（取代 Write+Delete）- 理解專案架構 → /snapshot（取代逐檔 Read...

This skill should be used when the user asks to 'create an agent', 'add an agent', 'write a subagent', 'agent frontmatte...

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatte...

Apply per-archetype Git identity and visible posting identity conventions for delivery agents. Use when agents make comm...

Authenticate an AI agent with an auth server using the Agent Identity (AID) protocol, with Ed25519 identity documents, p...

Without identity infrastructure, every Claude Code session starts from zero. The agent has no name, no remembered prefer...

Register and manage on-chain AI agent identity via ERC-8004.

Keep a running impl-notes file next to the phase meeting log while a subagent executes a task, recording design decision...

Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and in...

Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder

Self-improvement loop for multi-agent workflows. Diagnose failures, improve tool descriptions, and learn from success/fa...

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automaticall...

Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when che...

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, r...

Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or repla...

Analyze a workspace and generate or maintain a modular project documentation setup with a lean, concise agents.md entryp...

Interactive project setup wizard — creates agent.yaml, .workflow/ scaffold, and .gitignore entries for the Claude Agent...

Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any dir...

Use whenever creating OR editing CLAUDE.md, AGENTS.md, GEMINI.md, a SKILL.md, or any other file whose job is to instruct...

Use when the user requests integration testing, feature validation, or test plan execution

Use this skill to create or update the root AGENTS.md file to register SynthesisFlow skills for AI agent discovery. Trig...

9 advanced agent and AI meta-skills for Claude Code: adversarial code review, agent design, workflow orchestration, cont...

에이전트 간 상호작용 구조와 워크플로우 정의

Expose an existing route to AI agents as an MCP tool via route `.agent()` metadata. Use when the user asks to "expose th...

Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose...

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection...

Creates PhD-grade expert agents when no suitable agent exists. Produces highly specialized agents with deep domain exper...

Agent invocation syntax and boundary rules

Run an owner's ad-hoc request for delegated work as a properly configured background subagent — picks the model from doc...

Specialist subagent:

Agent skill for issue-tracker - invoke with $agent-issue-tracker

Use the agent_journal tool to report blockers, failures, missing capabilities, or environment issues, and to manually tr...

Build Claude judges that grade what your prompt, skill, or agent produces against its own rules, then test the judges be...

Interact with KakaoTalk - send messages, read chats, manage conversations

Prepare, before you need it, the runbook for stopping a proactive agent that is misbehaving: how to pause it in seconds,...

Prepare the kill switch runbook to stop one agent identity fast: ordered steps to disable it, end sessions, remove crede...

The portable rules layer of the agent — laws, rules, hooks and checks shipped by the package and adjusted by the tree th...

Ready-made examples of how a tree adds its own on top of the rules package. Load when the package text says something th...

Specialist subagent: Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use wh...

Launches specialized Claude agents for targeted tasks. Analyzes requirements, selects appropriate agent, and executes wi...

Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude...

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account —...

Expert legal advisor specializing in technology law, compliance, and risk mitigation. Masters contract drafting, intelle...

Legal tech — contrats, conformité, DPI, INAPI, marques, propriété intellectuelle DZ

Framework-agnostic repository review from the perspective of a future AI coding agent. Use when Codex needs to evaluate...

Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deletin...

Manage full OpenClaw agent lifecycle operations on a node: create/register agents, configure channel bindings, optionall...

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting u...

Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarli...

Expert en inference llama.cpp avancé (GGUF, quantization, local models, HTTP server, hardware)

Expert LLM architect specializing in large language model architecture, deployment, and optimization. Masters LLM system...

Agent skill for load-balancer - invoke with $agent-load-balancer

Expert en SEO local avancé (Google Business Profile, citations, reviews, NAP, DZ local search)

Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger w...

Expert en logging v2 (ELK, Loki, Fluentd, structured logging, correlation IDs, alerting)

Download or stream agent logs from GKE. Accepts issue number, session ID, or --all. Default mode downloads JSONL to tmp/...

Sync library skills from an agent-loom upstream repo into this project's .agents/skills while preserving project-local a...

Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and publ...

Continuous autonomous agent execution loop for open-ended, complex, or emergent multi-step tasks. Iterates through asses...

Use this skill when you need evidence-bounded loop state, plan/action/observation cycles, stop conditions, budgets, repe...

Complete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tests. Drives...

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or...

Control agent-lx-music (alx) CLI to search, play, download music, fetch lyrics/covers, and manage playlists.

Use when coordinating agents with Agent Mail locks, inboxes, threads, and conflict-prevention handoffs.

MCP Agent Mail for multi-agent coordination. Use when agents need file locks, messaging, inboxes, or conflict prevention...

多编排者/长期 agent 身份之间的异步信箱总线——发信、收信、回信、归档、名册注册。每个身份一个 inbox，一封信只有一个去处（收件人 inbox），收信只查自己信箱。触发：给另一个编排者/CTO/agent 写信或提议、查我的信箱、...

Multi-agent coordination with Agent Mail MCP. Use when registering agents, reserving files, sending messages, coordinati...

AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list age...

Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with...

Orchestrate multi-agent workflows with task decomposition, role assignment, handoff protocols, and per-session context b...

Automatically manage agent lifecycle, proposals, and registry.

Creates, lists, and removes custom project-specific agents. Custom agents are stored in .claude/crew-agents/ and registe...

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Expert en animations mathématiques Manim (3Blue1Brown, équations, algorithmes, vidéos éducatives)

A curated collection of 2903+ best agent skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps a...

Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer

Manage and health-check the machine's MCP servers (mcp_agents.py CLI) - inventory the declared servers from user and rep...