AI Skills Registry

Best practices for building on-device AI features in React Native using React Native ExecuTorch. Use when the user wants to add AI to a mobi

Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adapta

Instrument a Java application with the Elastic Distribution of OpenTelemetry (EDOT) Java agent for automatic tracing, metrics, and logs. Use

Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want t

Marketing and promotion specialist for Claude ecosystem technology - MCP servers, skills, plugins, and agents. Expert in community engagemen

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (GPT-5/o3) o

抖音爆款脚本创作工作流。从竞品视频拆解到脚本生成的完整流程：下载抖音视频→Gemini视频分析→爆款公式提炼→脚本+分镜生成→AI味审校。 当用户提到"抖音脚本"、"爆款拆解"、"竞品分析"、"带货脚本"、"千川素材"、"种草脚本"、"视频拆解"、"抖音视频分析"时使用此技能。

Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch and validated by SkillLens (arXiv 2605.23899). Eval

批量数据采集技能，负责分批并发调度 researcher agent 抓取所有数据源。

ローカルのコスト追跡データベースからClaude Codeのトークン使用量、支出、予算を追跡・レポートします。コスト、支出、使用量、トークン、予算、またはプロジェクト、ツール、セッション、日付によるコスト内訳について質問する場合に使用します。

Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling,

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspec

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video.

Applies Anthropic brand colors (dark #141413, orange #d97757, blue #6a9bcc, green #788c5d), Poppins headings, and Lora body text to artifact

Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a r

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, cu

Use when defining or implementing Go interfaces, designing abstractions, creating mockable boundaries for testing, or composing types throug

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality

Hacker News from your terminal — with a local SQLite store, snapshot history, and agent-native output no other HN tool has. Trigger phrases:

Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and sema

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub

Imports memories from an exported Markdown file or MEMORY.md into the current project. Use when migrating from another project, restoring fr