Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

luochang212

@luochang212 source repo

22 published skills

  1. ▌
    Tech Book Writing · luochang212
    技术书籍章节写作风格指南。融合反模板化叙事结构与段落级流畅性控制技法。 当用户要求写新的书籍章节、重写现有章节、优化文章可读性、或讨论技术写作风格时使用。 触发场景：写章节、重写、改写、优化文章、写作风格、叙事结构、可读性、 “换个切入方式”“这段太干了”“读者会流失”。 即使用户没有明确提到写作风格，只要任务涉及产出或修改技术书籍的正文内容，就应该参考本 skill。
    0
    installs
  2. ▌
    Worth Fix · luochang212
    分析和判断任何论断、报告、想法或需求的真实性、价值与做法。当用户说"这个 bug 是真的吗"、"分析一下这个问题/这个报告/这个说法"、"这个修复值得做吗"、"帮我看下这个建议靠不靠谱"，或用户给出一个待评估的 bug 报告、文章摘录、设计提案时使用。先核验、复现、定级、讲清原理、判断是否值得做，而不是直接相信或直接动手改代码。也适用于评估"要不要重构"。
    0
    installs
  3. ▌
    App Release · luochang212
    Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.
    0
    installs
  4. ▌
    NPM Release · luochang212
    Use when publishing or preparing to publish an npm package from this repository, especially the Skill Zoo CLI package under packages/cli. Also use when npm publish fails because of duplicate versions, npm authentication, browser authentication, dist-tag propagation, tarball contents, bin entry issues, or workspace/lockfile version mismatches.
    0
    installs
  5. ▌
    Tauri Updater · luochang212
    Use when adding software auto-update to a Tauri 2 desktop app, or when users ask about tauri-plugin-updater integration, app update checking, distinguishing installer vs portable builds for updates, or generating update manifests for GitHub Releases.
    0
    installs
  6. ▌
    Adrkit Init · luochang212
    Use when initializing ADR Kit in a repository or when the agent cannot find an adr/ directory.
    0
    installs
  7. ▌
    Adrkit Accept · luochang212
    Use when a proposal draft is complete, and the team has decided to accept it.
    0
    installs
  8. ▌
    Adrkit Decide · luochang212
    Use when recording a decision that is already accepted and does not need a proposal phase.
    0
    installs
  9. ▌
    Adrkit Reject · luochang212
    Use when a proposal draft should be declined and discarded.
    0
    installs
  10. ▌
    Adrkit Propose · luochang212
    Use when starting a new architecture decision that still needs review before it is accepted.
    0
    installs
  11. ▌
    Adrkit Validate · luochang212
    Use when checking whether ADR files follow the ADR Kit format, especially before accepting a proposal or committing.
    0
    installs
  12. ▌
    Adrkit Supersede · luochang212
    Use when an accepted decision is replaced by a newer accepted decision and must be retired without deleting history.
    0
    installs
  13. ▌
    Web Fetch Cce · luochang212 bundle
    网页内容提取策略。当需要读取网页内容、爬取页面、提取文章正文、处理JS渲染页面、或绕过反爬限制时，必须使用此技能。三层工具选择：WebFetch（内置）→ Crawl4AI（JS渲染/反爬）→ 原生 Playwright（兜底降级）。
    0
    installs
  14. ▌
    Web Search Cce · luochang212 bundle
    网络搜索策略。当需要搜索网络信息、查询最新资料、查找技术文档、或选择搜索工具时，必须使用此技能。定义了多层搜索工具优先级链，同层并发、失败即降级。
    0
    installs
  15. ▌
    Agent Skills Cce · luochang212 bundle
    Skill 管理与市场导航。当需要安装、搜索、删除、备份 skills，查找新技能，管理上下文预算，或用户询问「有什么好用的skill」「怎么装skill」「skill太多了怎么办」时，必须使用此技能。核心纪律：工具箱不是仓库。
    0
    installs
  16. ▌
    Tool Registry Cce · luochang212 bundle
    工具可用性追踪系统。当需要调用任何外部工具、查询工具状态、记录工具调用结果、或判断工具是否可用时，必须使用此技能。跨会话记住工具状态，避免每次盲试。
    0
    installs
  17. ▌
    Coding Philosophy Cce · luochang212 bundle
    编程哲学与决策框架。当需要写新功能、改bug、重构代码、审查代码、或做架构决策时，使用此技能。包含开发（熵增）和审查（熵减）两套思维。从第一性原理推理，核心问题永远是「收益是否大于副作用」。
    0
    installs
  18. ▌
    Md To PDF · luochang212 bundle
    Markdown to PDF Converter
    0
    installs
  19. ▌
    Code Audit · luochang212 bundle
    Security audit and code scanning. Use when the user asks to scan code for bugs/vulnerabilities, audit security, run SAST, find code patterns, or review code for security issues. Supports two modes — fast pattern scanning (Semgrep) for quick results and CI gating, and deep AI-powered investigation (deepsec) for thorough reasoning-based analysis. Also use when the user mentions "semgrep", "deepsec", "static analysis", "security scan", "code scanning", "find vulnerabilities", "scan my code", or "security audit".
    0
    installs
  20. ▌
    HTML Report · luochang212 bundle
    Create beautiful, self-contained single-file HTML reports, landing pages, and documents that are visual, interactive, and spatial. Use when the user wants to present information that would benefit from layout, color, diagrams, or interaction — such as project reports, product pages, architecture overviews, design documents, dashboards, slide decks, code review summaries, incident post-mortems, status reports, or any document where plain text would be too flat. Triggers include "create an HTML page", "make a report", "write a landing page", "build a dashboard", "present this information visually", or any request to communicate technical or business information in a polished, readable format.
    0
    installs
  21. ▌
    Code Quality · luochang212
    Use when the user asks to review code quality, find redundant code, audit duplication, or "clean up" a codebase. Also use when the user says "find issues" or "anything worth fixing" after a feature is built. This skill provides a systematic framework for identifying code quality issues, evaluating whether each fix is worth making, and safely applying changes without over-engineering.
    0
    installs
  22. ▌
    Github Research Assistant · luochang212 bundle
    Use whenever the user wants to understand, evaluate, or analyze a GitHub repository, even without the word "analyze", or when they simply paste a github.com link and ask about it. When the question is asked inside a local repo directory, analyze that directory's own repository by default (no link required). Covers basics, purpose, tech stack, usage examples, and architecture.
    0
    installs