creating-skills
How to create new Agent Skills following the open standard. Use when authoring new skills, extending agent capabilities, or packaging specialized knowledge into reusable formats.
prompt-engineer
MUST use when editing CLAUDE.md, SKILL.md, or slash commands. Applies prompt engineering best practices regardless of task size.
context-restore
Use when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.
gemini-embed
Generate text embeddings using Google Gemini API for RAG, semantic similarity, classification, and clustering tasks. Invoke when user wants to embed text, create embeddings, or convert text to vectors with Gemini.
memory-integration
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
skill-builder
Create and validate Agent Skills with proper structure and effective descriptions. Use when building custom skills, testing skill discovery, or designing new skill workflows.
pedro-pathing
Helps write autonomous and teleop code using Pedro Pathing library. Use when creating paths, building autonomous routines, setting up path following, working with Follower, PathChain, BezierLine, or heading interpolation.
map-reduce
When it would yield better results to explore mulitple approaches to a problem, load this skill to orchestrate multiple agents using a diverge and converge strategy.
goose-introspection
Goose session introspection and self-discovery via DuckDB reafference database. Query past sessions, find self, and enable cross-session awareness.
rl-optimization
Apply reinforcement learning principles when working on spec-kit-extensions. Auto-activates when: (1) editing command prompts in commands/*.md, (2) modifying workflow templates in extensions/workflows/, (3) discussing user feedback about workflow friction, (4) reviewing issues or PRs mentioning prompt clarity or template problems, (5) analyzing chat logs or workflow usage from other repositories. Helps ensure changes improve prompt effectiveness and template utility.
deepsearch-service
基于 LLM 的深度迭代搜索与推理服务。擅长处理复杂问题，通过自动分解查询、多轮迭代检索、信息评估与验证，最终生成全面且结构化的深度分析报告。
security-gate
Classifies inbound Telegram messages for telclaude as ALLOW/WARN/BLOCK with brief rationale.
winjin-dev
WinJin AIGC 项目开发规范和最佳实践。在开发 WinJin AIGC 项目时使用，包含 Sora2 API 集成、React Flow 节点开发、文档更新流程。每次功能开发或 Bug 修复后必须更新文档。
gemini
Shell out to Gemini CLI from Claude for any task. Use when asked to "pipe content to Gemini", "get Gemini perspective", "use gemini CLI", "run headless AI task", "parallel analysis with Gemini", or "get second opinion from Gemini". Useful for alternative perspectives, batch processing, or leveraging Gemini 2.5 Pro capabilities alongside Claude.
nlp-pipeline-builder
Build natural language processing pipelines for text analysis and understanding
claude-code-docs
Local Claude Code documentation reference. Use when asked about Claude Code features, configuration, skills, hooks, MCP, sub-agents, plugins, or troubleshooting Claude Code issues.
polyglot-spi
Cross-Language Strong Parallelism Invariance Verification for 15+ languages
claude-sdk-expert
Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices for Anthropic models
