Write a clear, empathetic EOL announcement with rationale, customer impact, and next steps. Use when retiring a product, feature, or plan without creating avoidable confusion.

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

Create detailed phase plan (PLAN.md) with verification loop

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

>-

Post project updates to team chat, gather feedback, triage responses, and plan next steps. Adapts to available tools (chat, git, issues, tasks). First run discovers tools and saves a playbook; subsequent runs execute from the playbook. Trigger with 'team update', 'post update', 'sync with team', 'standup', 'check team chat', 'feedback loop', 'project update', 'what did the team say'.

Git worktree management for safe, isolated feature development. Creates, manages, and cleans up worktrees with branch naming and dependency setup.

Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking

ASC 606 five-step model implementation skill for revenue recognition analysis and documentation

Deep integration with finite element analysis tools for structural simulation across static, dynamic, and nonlinear domains

Navigation mesh generation and pathfinding skill for game AI. Enables creation and configuration of navigation meshes, pathfinding queries, dynamic obstacles, and navigation agent setup across Unity, Unreal, and Godot engines.

Unity Physics skill for collision detection, rigidbody dynamics, raycasting, and physics configuration.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Use this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the claim-verification rule into a systematic action protocol that prevents false assertions from grep-only results.

Friendly onboarding tour of Claude Code capabilities for users asking what it can do.

>

The lead orchestrates, Codex agents execute. Each agent gets one focused task. The team lead prevents file conflicts before spawning — the orchestrator IS the lock manager.

Turn a mature `.agents` corpus into operator-ready knowledge surfaces.

> **Purpose:** Keep a compounding markdown wiki of **external knowledge** (articles, papers, transcripts, clipped web content) maintained by an LLM so the bookkeeping is free and the knowledge accumul

Strategic planning for open source contributions.

Systematic exploration of upstream repositories before contributing.

Plugins can store user-configurable settings and state in `.claude/plugin-name.local.md` files within the project directory. This pattern uses YAML frontmatter for structured configuration and markdow

Autonomous task execution via the codex CLI. Runs non-interactively. Progress streams to stderr; final result on stdout.

Analyze the current codebase and produce a structured threat model at `.turbo/threat-model.md`.

Analyze task complexity and route to an execution mode.

Run health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues.

Enable communication between AI coding agents using AI Maestro's dual-channel messaging system. Agents are identified by their agent ID or alias, with tmux session names as a fallback. Supports both S

Intelligent routing layer that analyzes requests and directs them to the most appropriate Skills, Agents, or Commands

Discover, install, and manage AI agent skills from agentskill.sh. Search for capabilities, install mid-session, scan for security issues, and provide feedback. Use when asked to find skills, install extensions, or check skill safety.

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

>

>

verification-before-completion

How to properly create Claude Code skills - teaches global vs project-local, naming conventions, and proper file structure

恢复之前保存的会话上下文。列出所有待处理的 session，读取选定 session 的任务信息，更新进度，任务全部完成后删除文件。

Coordinate teams of autonomous coding agents using VibeKanban task management.

The MapReduce skill enables parallel task execution across multiple AI providers or agent instances, followed by intelligent consolidation of results. This produces higher-quality outputs by levera...

Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.

Chat Shared Conversation To File - Convert ChatGPT, Gemini, Grok, and Claude share links to clean Markdown + HTML transcripts. Preserves code fences with language detection, deterministic filenames, GitHub Pages publishing. Bun-native CLI.

Advanced swarm patterns with dynamic topology switching and self-organizing behaviors for complex multi-agent coordination

Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash

Understand what context is, why it matters, and the anatomy of context in agent systems

Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures

用户收到了一个 GitHub Issue（bug 报告、疑问、feature request），需要 AI 协助分析问题、判断是否要做、起草回复。AI 全程主导推进，用户只在关键节点做判断。

>-

Manage Claude Code sessions with naming, checkpointing, and resume strategies.

Faithful implementation of the Outline Agent from PaperOrchestra

Faithful implementation of the Section Writing Agent from PaperOrchestra

Create professional, print-ready HTML documents that export to PDF with customizable branding.

Respond terse like smart caveman. All technical substance stay. Only fluff die.