AI Skills Registry

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search

Agent tracing CLI for inspecting agent execution snapshots. Use when user mentions 'agent-tracing', 'trace', 'snapshot', wants to debug agen

HeroUI v2 to v3 migration guide for agents. Use when migrating HeroUI v2 apps to v3, upgrading components, or accessing migration documentat

Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), exte

Smoke test Mastra projects locally or deploy to staging/production. Tests Studio UI, agents, tools, workflows, traces, memory, and more. Sup

Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requ

Write and improve agent skills (SKILL.md files). Use when creating new skills, refactoring existing ones, debugging why an agent ignores ins

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or ot

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent se

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code model

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to

Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill",

Build and run evaluators for AI/LLM applications using Phoenix.

Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10

Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyz

INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain,

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。 触发方式：/story-review、/审查、「

Spawns multiple AI coding agents to work on related GitHub issues concurrently using git worktrees. Use when breaking down a large feature i

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText,

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl c

Slack automation CLI for AI agents. Use when: - Reading a Slack message or thread (given a URL or channel+ts) - Browsing recent channel mess

Type-safe Hono APIs with routing, middleware, RPC. Use for request validation, Zod/Valibot validators, or encountering middleware type infer