Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Claude API
Use this skill when the user wants to build with the Claude API or Anthropic SDKs.
## Reading Guide
Pick the language-specific docs that match the user's stack, then use the shared references for models, caching, errors, and tool use concepts.
## When to Use WebFetch
Use WebFetch when the user needs the latest official documentation or behavior that may have changed recently.
The line at the top of this page pins the label git:20260331.4178dd7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_sgiru4biuy54kvdk
GET https://markdownregistry.com/api/v1/resolve?ref=esonhugh/claude-code/claude-api
GET https://markdownregistry.com/api/v1/blob/06d480a0e137751ab60c587f7441506257353e16c2157f183973b606f2e9e172
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
esonhugh/claude-code · .claude/skills/claude-agent-workflow-validation/SKILL.md · This skill should be used automatically when the user asks for strict binary-side validation of Agent, Workflow…
esonhugh/claude-code · .claude/skills/claude-code-feature-validation/SKILL.md · Use this skill automatically whenever validating a Claude Code repository change: a new feature, modified feature, bug…
esonhugh/claude-code · .claude/skills/claude-network-debug/SKILL.md · This skill should be used when the user asks about Claude Code “代理不生效”, “OAuth 网络失败”, “抓流”, “CONNECT”, “SSE/WebSocket”…
esonhugh/claude-code · .claude/skills/claude-runtime-debug/SKILL.md · This skill should be used when the user asks to diagnose Claude Code CLI/runtime behavior, including “运行时调试”…
esonhugh/claude-code · .claude/skills/claude-source-binary-analysis/SKILL.md · This skill should be used when the user asks to statically analyze authorized Claude Code source or…
esonhugh/claude-code · .claude/skills/release-validation/SKILL.md · Validates release readiness with related bun tests, make release-check, current-binary scripted tmux interactions, and…
anthropics/skills · skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/claude-api/SKILL.md · Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended…
nikships/droidproxy · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
rudycity/superagent · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
skateddu/claude-code-python-setup · .claude/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
lichangzheng10086/doyin_ai_video · .agents/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…
archubbuck/workspace-architect · assets/skills/claude-api/SKILL.md · Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching…