AI Skills Registry

Provides configuration patterns for LangChain4J vector stores in RAG applications. Use when building semantic search, integrating vector dat

Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG ins

{what this skill teaches agents}

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference

Deep EVM smart contract security audit system. Use when asked to audit a contract, find vulnerabilities, review code for security issues, or

JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate 250+ models. Package: @inferencesh/sdk (npm install). Full

When the user wants to track AI search traffic in GA4 or GSC. Also use when the user mentions "AI traffic," "ChatGPT referral," "Perplexity

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining,

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecr

Step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating, or de

AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal ste

Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then impleme

Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Im

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

项目初始化工具。读取全局协议 ~/.claude/CLAUDE.md，分析项目实际情况，生成项目特定的 CLAUDE.md 和 docs/ 上下文。本技能应在用户说"初始化项目"、"项目设置"、"配置 Claude Code"、"新建项目配置"时使用，或在进入一个新项目需要快速配

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained

Zoom Meeting SDK for Windows - Native C++ SDK for embedding Zoom meetings into Windows desktop applications. Supports custom UI architecture

Google Model Armor: Sanitize a user prompt through a Model Armor template.

自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。

Authoring playbook for building agents that search, read, and synthesize information into a report. Use this when the user wants an agent to

[BETA] Dogfood the active branch end-to-end as a QA engineer. Diffs the branch against main, builds an exhaustive browser test matrix of eve

Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilitie