AI Skills Registry

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, a

Load automatically when user asks to learn Medusa development (e.g., "teach me how to build with medusa", "guide me through medusa", "I want

Discord-backed OpenClaw agent/session relay; not archive search.

【大型代码库分析专用】当需要分析整个项目架构、识别代码模式、追踪功能实现、梳理模块关系时必须使用本技能。触发关键词：分析整个项目/代码库、架构梳理、模块划分、代码模式识别、功能追踪、全局扫描。本技能通过 Gemini CLI 快速扫描完整代码库，提供 AI 驱动的架构洞察和代码分

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPo

Prepare for Anthropic-specific technical interviews covering Constitutional AI, RLHF, interpretability, scaling laws, MCP, agentic systems,

Finds and recovers content from Claude Code session history files. This skill should be used when searching for deleted files, tracking chan

Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.

Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.

Build a new builtin tool package under `packages/builtin-tool-<name>/`. Use when adding a new agent-callable toolset, designing its API surf

Use when writing async/await code, enabling strict concurrency, fixing Sendable errors, migrating from completion handlers, managing shared

Context management engine for AI coding agents. Handles context window optimization, persistent memory across sessions, context retrieval st

Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diariz

Shared audit integrity framework for all AppSec agents — enforces output quality, intellectual honesty, and continuous improvement through a

Alibaba Cloud Tablestore Agent Storage Skill. Use for building and managing Tablestore-based knowledge bases with the `tablestore-agent-stor

Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when a

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers

Bootstrap evaluators from production traces — emit SDK code, a framework-agnostic JSON spec, or publish online LLM-judge evaluators directly

Build NLP applications using transformers library, BERT, GPT, text classification, named entity recognition, and sentiment analysis

Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest

Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit,