菜单
Expert on Anthropic Codex API, models, prompt engineering, function calling, vision, and best practices. Triggers on anthropic, Codex, api, prompt, function calling, vision, messages api, embeddings
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run all 8 cleanup skills in sequence: unused → cycles → dedupe → types → weak-types → defensive → legacy → slop. Each step verifies before the next runs; halts on first failure. Produces one consolidated report. Use when the user asks to clean up the whole codebase, run all cleanup skills, do a full code-quality pass, or sweep the repo. Example queries — "clean up the whole codebase", "run a full code-quality pass", "sweep this repo", "do all the cleanups in order".
Find and remove deprecated, legacy, and fallback code paths with zero callers. Verifies callers via repo grep + LSP before deletion. Removes unreachable fallback branches. Use when the user asks to remove deprecated code, clean up legacy paths, drop fallbacks, or simplify code branches. Example queries — "remove the deprecated API", "drop the v1 fallback", "this code is marked legacy, kill it", "simplify these branches".
Comprehensive Expo expert with access to complete official documentation covering React Native development, EAS Build, EAS Submit, EAS Update, Expo Router, Expo Modules API, configuration, deployment, and all platform features. Invoke when user mentions Expo, React Native, EAS, Expo Router, mobile app development, iOS/Android development, or cross-platform development.
Expert guidance for Plaid banking API integration including Link, Auth, Transactions, Identity, and webhook handling. Invoke when user mentions Plaid, bank connections, financial data, ACH, or banking APIs.
Token-Oriented Object Notation (TOON) format expert for 30-60% token savings on structured data. Auto-applies to arrays with 5+ items, tables, logs, API responses, database results. Supports tabular, inline, and expanded formats with comma/tab/pipe delimiters. Triggers on large JSON, data optimization, token reduction, structured data, arrays, tables, logs, metrics, TOON.
Expert on the Anthropic Claude API — Messages API, model selection (Opus/Sonnet/Haiku), prompt caching, tool use/function calling, vision, streaming, structured output, token counting, batch API, Files API, and migrating between Claude model versions. Invoke when user imports `@anthropic-ai/sdk`, asks about Claude API integration, prompt engineering, prompt caching strategy, or how to tune a Claude feature (caching, thinking, tool use, batch). Example queries — "set up prompt caching for a long system prompt", "switch this Sonnet call to Opus with the 1M context window", "stream a response with tool calling", "migrate from claude-3-5-sonnet to claude-sonnet-4-6".
| name | anthropic-expert |
| description | Expert on Anthropic Codex API, models, prompt engineering, function calling, vision, and best practices. Triggers on anthropic, Codex, api, prompt, function calling, vision, messages api, embeddings |
| allowed-tools | Read, Grep, Glob |
| model | sonnet |
Provide expert guidance on Anthropic's Codex API, including prompt engineering, function calling, vision capabilities, and best practices based on official Anthropic documentation.
Auto-invoke when users mention:
Full access to official Anthropic documentation (when available):
docs/.md filesNote: Documentation must be pulled separately:
pipx install docpull
docpull https://docs.anthropic.com -o .Codex/skills/anthropic/docs
When a user asks about Anthropic/Codex:
Common topics:
- Getting started / API keys
- Model selection (Opus, Sonnet, Haiku)
- Messages API / streaming
- Prompt engineering techniques
- Function/tool calling
- Vision and image analysis
- Extended context (200K tokens)
- Prompt caching
- Rate limits and pricing
- Error handling
Use Grep to find relevant docs:
# Search for specific topics
Grep "function calling|tool" docs/ --output-mode files_with_matches -i
Grep "vision|image" docs/ --output-mode content -C 3
Check the INDEX.md for navigation:
Read docs/INDEX.md
Read the most relevant documentation files:
Read docs/path/to/relevant-doc.md
Structure your response:
User: "How do I implement function calling with Codex?"
1. Search: Grep "function calling|tool" docs/
2. Read: Function calling documentation
3. Answer:
- Explain tool use format
- Show request/response example
- Discuss tool choice vs any
- Best practices for tool definitions
User: "Can Codex analyze images?"
1. Search: Grep "vision|image" docs/ -i
2. Read: Vision API documentation
3. Answer:
- Supported image formats
- Image encoding (base64, URLs)
- Show example API call
- Limitations and best practices
User: "How do I write better prompts for Codex?"
1. Search: Grep "prompt|engineering" docs/
2. Read: Prompt engineering guide
3. Answer:
- Clear instructions principle
- Examples and context
- XML tags for structure
- Chain of thought prompting
Models:
API Features:
Best Practices:
SDKs:
anthropic)@anthropic-ai/sdk)After answering, suggest: