oc-claude-api

原文涵盖的主题

• Claude API
• How This Skill Fits the Build Pipeline
• /oc-claude-api — Command Reference
• Model-Routing Decision Tree
• Prompt Caching Is the Default
• /oc-claude-api cache-audit — target ≥ 60% hit rate
• Tool-Use Patterns
• Migration Playbooks — /oc-claude-api migrate

On first invocation, read references/orchestrator.md and follow its welcome protocol. First-party harness for building, debugging, and optimizing applications on the Claude API / Anthropic SDK. Owns model routing, prompt caching (on by default), tool-use design, batch/streaming patterns, and version-migration playbooks. Apps built or touched through this skill ship prompt caching from the first commit and carry token-ceiling guardrails per phase. This is the Claude-in-the-loop counterpart to the rest of the pipeline. If you're building an LLM feature — a chatbot, an extraction pipeline, an agent, an LLM judge — this skill owns the request layer: which model, how it's cached, how tools are wired, and how the code moves when a model version bumps. It does not own agent topology or harness loops (that's oc-agent-forge), retrieval (oc-rag-forge), or prompt versioning + eval datasets (oc-prompt-ops). It owns the Claude API surface those skills build on. Accuracy contract. Model IDs, prices, parameters, and breaking changes in this skill and its reference docs are sourced from the Claude Code built-in claude-api skill (when present), not from memory. It is not bundled with opchain. When

这里只展示节选，请以完整原文和当前要求为准。