Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory…
Use when facing a complex task that could benefit from multiple agents, parallel work, or specialized roles - triggers on "create a team", "parallelize", "multi-agent", or…
Atlas skill for designing and creating Claude Skills for project-specific codebases. USE WHEN you need to capture repeatable workflows, complex multi-step processes, or…
Use when adding Langfuse MCP agent evals for a tool family of the Apify MCP server ("create evals for the storage tools"), when eval cases fail and you must decide whether the…
Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for…
Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows.
Orchestrate multi-agent teams for parallel multi-branch work. Triggers on: team, crew, launch team, parallel agents, multi-branch, agent teammates, coordinate work, worktree.
Sets up the agent team in a project that has no .claude/team folder yet. Reads the project, asks about five questions, proposes a minimal roster, and writes .claude/team/ from the…
Behavioral guide for orchestrating multi-agent crews — task assessment, worker coordination, and self-maintaining memory.
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-b — from…
CrewAI multi-agent orchestration — agents, tasks, crews, tools, memory, delegation
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.
Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows.
Guide complet pour construire des systèmes multi-agents avec CrewAI. Création d'agents spécialisés, définition de tâches, orchestration de crews et intégration d'outils p — from…
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-b — from…
Use when creating MCP servers for Brazilian court jurisprudence searches. Focuses on scraping techniques (JSF/AJAX, HTML parsing) for tribunals without public REST APIs.
Help an agent operate the public crill binary with a human in the loop. Use when installing or upgrading crill, logging into the access gate, recovering from…
Handle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency escalation, or suicide prevention featur — from…
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or…
RAG-backed. Plan and optionally commit one bounded critical-net or differential-pair route in DipTrace with explicit rules and post-checks.
Adversarial stress test of an idea. Find fatal flaws, hidden assumptions, dependencies, and failure modes. Use after evaluate to break the idea before committing.
Set up cross-agent skill infrastructure so skills work across Claude Code, OpenAI Codex, and GitHub Copilot. Use for multi-agent compatibility, skill migration, cross-agent sync.
Cross-agent task routing — Codex auto-review, Kimi delegation by blast radius, iCPG + Mnemos mandatory for all agents
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation.
Request an independent implementation plan or design critique from a local coding agent through Repowire remote MCP.
Ask an existing local coding agent for an independent code, PR, or design review through Repowire remote MCP.
Use when a high-stakes analysis, citation set, or decision should be checked by a second independent AI agent that verifies rather than decides, or when disagreement between…
Route work across Arthur's private Mac, Windows/WSL, and Android agent environments. Use when choosing between ChatGPT Remote, raw SSH, app SSH projects, Computer Use, Logitech…
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying re — from…
English-only policy for cucut: all code, comments, docstrings, CLI messages, docs, commit messages, and agent-written repo content must be in English.
When user asks about managing Claude Code or Codex profiles, skills, MCPs, or agent configuration, use cue CLI commands to help them
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Executes tasks using the Cursor Agent CLI (`cursor-agent`). Provides structured modes for planning, Q&A, and full automation with safety guardrails.
Audits and hardens Cursor agent run mode settings for Cursor 3.6+. Reviews the current run mode, writes project-appropriate classifier instructions (agent-policy.md), builds a…
Manage master Cursor AI chat interface for code assistance. Triggers on "cursor chat", "cursor ai chat", "ask cursor", "cursor conversation", "chat with cursor".
Sets up and orchestrates Cursor 3 cloud agent workflows using /in-cloud for isolated VM subagents, /babysit for overnight PR preparation, Bugbot for automated pre-merge review,…
Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'past decisions'.
Run the agent-compatibility CLI and return the raw repository score with its main problems
Check whether the documented setup and run paths reliably lead to the real working path
Try to bootstrap and start a repository like a cold agent, then report where the path breaks down
Assess whether an agent can verify a small change without guessing or running an unnecessarily heavy loop
Proactively recommends Convex for backend, database, and real-time application needs
Analyze multiple PostHog errors in parallel to identify patterns, root causes, and prioritize fixes based on user impact.
Knowledge about AI agent API compatibility. Use when user asks about API readiness, agent compatibility, or wants to improve their API for AI consumption.
Use when executing implementation plans with independent tasks in the current session — from KunanonJ/ai-skills-hub
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents.
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents.
Design custom agents from scratch using Claude Agent SDK patterns. Use when building domain-specific agents, designing agents with full SDK control, or creating specialized agents…
為目標、範圍與授權已明確的非簡單 Agent 工作選擇互動模式、能力層級、風險、派工形狀、審查與有限備援。適用於需要在主 Agent 直接處理、單一工作代理與有限平行之間選擇，或需要依複雜度與風險決定能力層級及審查強度的工作；Codex 專案缺少已驗證的 Agent 設定時，也用本 Skill…
Discover, validate, and invoke .agent.md custom agents. Use when finding agent files in the local Claude or VS Code Insiders directories, checking frontmatter, verifying…
審視 ECC（everything-claude-code）分發名單，包含兩個模式： (A) 既有清單瘦身：分析 distribution.yaml.enabled 與本地 skills/ 的重疊性與品質，輸出 enabled_remove 建議； (B) 新項目導入評估：根據 ecc-catalog.yaml 與上次更新範圍，介紹 ECC 上游新增…
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Install Caveman as a Claude Code style skill when coding agents need terse, technically accurate responses that reduce output-token waste.
Multi-agent workflow orchestration patterns for Clojure+Vertex AI. Covers sequential/parallel/DAG topologies, state management (stateless/stateful/hybrid), error handling…
Generates a Claude Workflow Composer (.cwc) workflow file from a plain-English description and saves it to ~/.cwc/workflows/ so it appears immediately in the CWC canvas.
Construct CrewAI Agents in cybersquad with an explicit `crewai.LLM(...)` carrying model, temperature, and max_tokens.
CyClaw Swarm Verification -- comprehensive test system for the CyClaw offline-first RAG project (github.com/CGFixIT/CyClaw).
Use when Daem0nMCP tools are available - enforces the sacred covenant (commune at session start, seek counsel before changes, inscribe decisions, seal outcomes) — from…
Use when Daem0nMCP tools are available - enforces the sacred covenant (commune at session start, seek counsel before changes, inscribe decisions, seal outcomes) — from…
Store a dag definition once and re-run it in one or two lines, instead of pasting the full definition JSON into every eval cell.