harness-code

深度功能分析，以问题驱动的方式深入挖掘某个功能/机制的实现原理，生成单篇深度解析文档。参考 skill-creation-mechanism.md 的分析风格：从核心问题出发，层层深入，多维度对比，最后给出总结。适用于"深入分析 X 的原理"、"深度解析 Y 机制的实现"、"理解 Z 功能的设计决策"等场景。

在评审技术设计文档、实现计划、迁移方案、架构规格、发布与上线计划、插件或 hook 设计、以及需要工程师或代理按文档可靠执行的安全敏感自动化方案时使用；也适用于用户说评审技术方案、审设计文档、看实现计划、方案可不可行等场景。

Build and maintain a personal knowledge base where an LLM incrementally builds and maintains a structured, interlinked collection of markdown files. Based on Andrej Karpathy's LLM Wiki pattern.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when building TypeScript SDKs, extracting shared code into packages, creating developer tooling libraries, designing clean API surfaces, or publishing to npm (public or private). Covers typed clients, error handling, multi-target bundling (ESM/CJS/browser).

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs, splitting PDFs, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, presentations; reading, parsing, or extracting text from .pptx files; editing, modifying presentations; combining or splitting slide files.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet; or convert between tabular file formats.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.

Comprehensive quality analysis tool for Claude Skills. Evaluates skills from GitHub URLs, marketplace links, ZIP files, or local directories across five dimensions (structure, security, UX, code quality, integration) using balanced scoring and three output modes (comprehensive report, interactive review, pass/fail certification). Triggers on "analyze skill quality", "review this skill", "evaluate skill", or "skill quality check".

Comprehensive security analysis for Claude Code skills with P0-P3 enhancements. Detects malicious code, obfuscation, YAML injection, typosquatting, time bombs, sandbox escapes, and 40+ attack patterns. Use for analyzing skills before installation or auditing existing skills. Trigger this skill when: "Analyze this skill for security", "Check if skill-name is safe", "Audit security of installed skills", "Scan file.zip before installing", "Review skill vulnerabilities"

Design and build AI agents for any domain. Use when users want to create agents, understand agent architecture, or build assistants. Keywords - agent, assistant, autonomous, workflow, tool use, orchestration.