Skills 导航

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景，自动识别项目语言并给出对应示例与默认配置，快速搭建 LLM 应用。

✎ 想把Claude能力接进应用或智能体，用claude-api上手快、兼容Anthropic与Agent SDK，集成路径清晰又省心

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

Operate long-running AI tasks safely across GPT-5.4 and Claude by using model selection rules, phased execution, checkpoints, resumable workflows, API throttling discipline, and subagent isolation. Use when a task may run for a while, touch multiple files/systems, involve external APIs, browser automation, Azure, Orgo, or multiple subagents, or when the user asks about long autonomous runs, rate limits, reliability, or safe operating mode.

Review, validate, and generate code with AI-powered linting. Use when fixing bugs, generating boilerplate, formatting, or running analysis.

Full project audit — launches 5 parallel AI agents (security, bugs, dead code, architecture, performance) to scan your codebase read-only, then compiles a unified report with health grade (A+ to F) and offers surgical fixes. Language-agnostic. Zero config.

Use when building, auditing, or simplifying an AI coding-agent harness, especially when the current runtime has unclear config precedence, weak tool permissions, hidden product-only behavior, or poor transcriptability.

专门整理臃肿的 CLAUDE.md，用渐进式披露把高频规则留在主文档、细节移到 references，建立多入口索引和校验流程，适合给 Claude Code 的项目记忆做降噪和长期维护。

✎ 把复杂提示词、文档和工作流按步骤渐进展开，能显著缓解上下文拥挤，让 AI 协作更稳，也更适合长期维护。

扫描Claude Code在~/.claude/projects的会话历史，按关键词定位旧会话、恢复被删代码或文件，并追踪跨会话修改记录与工具操作轨迹。

✎ 误删代码或想追溯改动时，它能直接从 Claude Code 会话历史里捞回文件内容，跨会话恢复尤其省心。

排查 Claude Code 插件和 Skill 安装后不显示、未激活、enabledPlugins 配置异常等问题，按步骤诊断 settings.json、缓存与 marketplace 状态，快速定位并修复。

✎ 专门排查 Claude Code 插件装了不显示、技能不触发等问题，连 enabledPlugins 配置异常也能快速定位，排障更省心

扫描项目中的 CLAUDE.md，按统一标准做质量评分、审查与报告，给出可执行改进建议并在确认后定向更新，适合检查文档质量、维护项目上下文或从零创建 CLAUDE.md。