全部能力

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional…

Large Language Model development, training, fine-tuning, and deployment best practices.

Master React version upgrades, class to hooks migration, concurrent features adoption, and codemods for automated transformation.

Performance profiling principles. Measurement, analysis, and optimization techniques.

React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure,…

用于 code-goal-planner 的 Agent 技能 - 使用 $agent-code-goal-planner 调用

当用户想要规划、设计或实施 A/B 测试或实验时。当用户提到 "A/B test"、"split test"、"experiment"、"test this…" 时也使用。

Agentica 多智能体基础设施 API 参考指南

Expert guidance for Spring Boot application development with best practices for RESTful APIs, testing, security, and deployment

Design and implement database indexing strategies. Use when creating indexes, choosing index types, or optimizing index performance in PostgreSQL and MySQL.

Expert guidelines for building performant animations with Motion (formerly Motion One) vanilla JavaScript animation library

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios,…

Execute tasks from a track's implementation plan following TDD workflow

Implement form validation using React Hook Form, Formik, Vee-Validate, and custom validators. Use when building robust form handling with real-time validation.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks,…

Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT earnings results", "did NVDA beat earnings", "post-earnings analysis", "earnings surprise", "what happened with GOOGL earnings", "earnings reaction", "stock moved after earnings", "EPS beat or miss", "revenue beat or miss", "quarterly results for", "how were earnings", "AMZN reported last night", "earnings call recap", or any request about a company's recent earnings outcome. Use this skill when the user references a past earnings event, even if they just say "AAPL reported" or "how did they do".

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand…

Build and deploy Streamlit apps natively in Snowflake. Covers snowflake.yml scaffolding, Snowpark sessions, multi-page structure, Marketplace publishing as Native Apps, and caller's rights connections (v1.53.0+). Use when building data apps on Snowflake, deploying SiS, fixing package channel errors, authentication issues, cache key bugs, or path resolution errors.

精通现代 Angular（v20+），深入掌握 Signals、Standalone Components、无 Zone 应用、SSR/Hydration 及响应式模式。