Coding & Development

Sets up or audits a repository's baseline files, including license, security policy, contributing guide, README, editor and Git hygiene, PR and issue templates, Dependabot, CI, and for Node.js/TypeScript projects the lint, format, test, hook, and publish tooling. Includes starter PR and issue templates. Use when bootstrapping a new repository, adding missing community or GitHub files to an existing one, or checking a repository against a new-repo checklist.

Code review rules for pull requests. Use when reviewing a PR or a diff, or re-reviewing a PR after new commits: what to flag, the severity bar, the comment format, and how to converge over review rounds instead of raising new minor issues every time.

改写中文或英文论文、学术文本和技术文档，减少模板化、机械化表达，保留事实、术语、引文与结构。用户要求降 AIGC、去 AI 味、人性化改写或继续已有改写轮次时使用，支持文本、TXT、DOCX、分块高亮 HTML 对照，以及可用环境中的子代理分工；不用于查重检测或承诺检测分数。

在任意 Markdown 文件/文件夹上构建并迭代文件式个人知识库与知识图谱：给文档起草 frontmatter 元数据（日期/领域/状态/一句话结论），用 supersedes 演进、related 语义相关、[[双链]] 引用三类关系建图，脚本生成决策登记簿与图谱邻接表。当用户要求搭建个人知识库、建知识图谱、整理笔记或文档入库、更新已有知识库，或说"帮我回忆/复盘/找找之前关于某主题的分析和结论"、决策前想参考历史思路时使用。适用于任何支持 SKILL.md 的 Agent（ZCode、Claude Code 等）。

Verify the enclosure in Fusion 360 with clash checks, clearance gaps, section views and screenshots. Use after every build, when checking fit or clearance, or when asked to show or screenshot the model.

Build or rebuild the enclosure in Fusion 360 from the repo's Python scripts via the Fusion MCP. Use when changing enclosure geometry or parameters, adding a feature, or when Fusion's model is missing or stale.

Upgrades, or migrates, an Android project to use Android Gradle Plugin (AGP) version 9. Do not use this skill for migrating Kotlin Multiplatform (KMP) projects.

Runs a mock AI/ML engineer interview round and scores the answer against the 4-category rubric (0-5 each, total out of 20) with one improvement. Use when the user asks to "practise", "practice", "run a mock round", "mock interview", or "quiz me" on AI/ML interview prep.

글로만 설명하기 어려운 것을 실제로 띄워 찍은 화면과 저장된 값을 증거로 삼아, 하나의 질문에 답하는 HTML 보고서 한 장을 만든다. 휴대폰에서도 읽히고 브라우저 인쇄로 A4 PDF 가 그대로 나오며, 정할 것이 있으면 받는 사람이 문서 안에서 고르고 복사해 회신한다. 답할 질문에 따라 구조를 그때그때 짠다 - 무엇이 바뀌었나(개선 전후), 기획서대로 되었나(명세 대조), 우리 원칙대로 되어 있나(점검, 감사), 조건이 바뀌면 무엇이 달라지나(상태 대조), 지금 어떤 상태인가(현황), 무엇을 정해야 하나(의사결정). 화면에 드러나는 큰 기능을 구현하거나 고친 작업을 마쳤으면, 사용자가 따로 말하지 않아도 완료 보고를 이 보고서로 할지 먼저 떠올린다. "html 로 보여줘", "시각화해서 보여줘", "캡처해서 설명", "스크린샷 찍어서 설명", "실제 화면 찍어줘", "구현한 거 보여줘", "작업 끝났으면 정리해줘", "전후 비교", "before after", "뭐가 바뀌었는지 정리해줘", "기획서대로 됐는지 확인", "남은 게 뭔지", "점검 결과 정리", "결과보고서", "고객에게 보낼 자료", "기획자에게 보고", "의사결정문", "결정할 것 골라서 붙여넣게", "작업 내역 정리해서 공유"류 요청과, 점검, 코드 리뷰, 버그 조사의 결과가 화면에서 어떻게 보이는지가 논점일 때 발동합니다. 발견을 글머리표로 길게 늘어놓거나 코드 diff 를 붙여 설명하려 하기 전에 이것을 먼저 떠올린다 - 받는 사람은 코드를 읽지 않는다. (화면이 없는 순수 문서와 화면 사이 이동 흐름 지도는 이 스킬의 대상이 아니다.)

Discover under-the-radar GitHub repositories using deep, multi-strategy topic graph searches. Use when the user asks to find hidden gems, underrated projects, missed opportunities, or non-obvious repos in a domain, technology, or topic. Sweeps topic clusters, star bands, recency windows, and low-star ranges, then ranks by gem signals (velocity, activity, README quality) rather than raw stars. Not for finding the most popular repo in a category, and not for code search.

Stops Claude Code from deleting your session history after 30 days by setting cleanupPeriodDays to 365 in ~/.claude/settings.json. Backs the file up first, keeps every other setting, and shows the result.

Picks one repeated job from section D of your Already Told You report and sets up its automation with you - a skill, a skill plus an app connection (MCP), or a scheduled run - always ending with one human approval step before anything is sent, published, paid or deleted.

>- Structural code search via ast-grep — use when code shape and element relationships matter, not just text. E.g., "find async functions without error handling", "refactor foo(a, b) to foo({ a, b })". Use Grep for simple name lookups.

Maintainer-only. Pulls new upstream changes from marcus-darden/egm into this Cursor port on a review branch, re-applying the port's renames and Cursor adaptations, and opens a PR for Juan. Run only when typed as /egm-sync-upstream.

装 skill 之前先查一句：这个值不值得装。它扫 skill 的目录，看声称的功能有没有对应的东西撑着——有能跑的代码，或者步骤清单写全的文档，算过；说要做某件事却一行实现都没有，标『别装』。也能盘点已装的 skill，指出哪些可以删。触发：值不值得装、这个skill能装吗、skill体检、装完有没有用、哪些skill可以删、skill是不是空的、skill review。

Turn a skill idea into a finished, tested, reviewed and released agent skill in one run - spec, tests first, an independent review against a release checklist, and a release that waits for the user's yes. Use for "skill factory", "/skill-factory", "build and ship a skill for X", "make this a skill and release it", or when loot hands over a drop whose form is a skill.

Builds or checks a simple skill with the user, for use in Claude, ChatGPT or Copilot.

根据业务需求生成或修订中文 MRD 需求内容，重点输出单界面的核心逻辑、明细列表和筛选项；适用于仲裁、理赔、工单、网点配置等业务系统需求。用户只要求讨论内容时不处理 Word 排版或界面图。

Purpose: full scientometrics review of a manuscript **before submission to

>- Checks that D source files and markdown documentation adhere to the project's 80-column line length rule. Run via rdmd.

根据流程描述生成或核对OA流程编码与中英文完整名称，沿用ME-HR-001 Offer审批 | Employment Offer Approval格式；适用于流程命名，不处理角色命名、流程配置或审批发起。

Work with the user on their Margin drawing board (an iPad pen canvas). Use when the user mentions Margin, their board, drawing, sketch, page or whiteboard, says "check my board" or "look at my drawing", or asks you to answer, explain, plot or diagram something they drew.

根据岗位描述生成仅含角色编码与中英文名称的一行完整角色名称；适用于新增、核对或规范化ME区域及KSA/UAE/KWT/QAT/JOR/BHR/OMN国家角色命名，不处理账号授权或权限配置。

指导 AI 正确使用 PowPop MCP 连接器的 9 个工具：附近发现（数字人/用户/帖子）、话题搜索、数字人与帖子详情、景点商圈、活动与会员方案、身份检查。