agentleFS
Sign inStart free
JurnLoryuJurnLoryu/claude-code-starter-kit/coding/SKILL.md

coding

Skill0 starsChanged 5 months agoMITView on GitHub

Integrated software-engineering skill that fuses the user's configured engineering skills into one. Two scales: a SOLO/daily coding loop (source-driven → incremental → TDD → simplify → debug) for fast-but-solid work, and a LARGE-PROJECT lifecycle (plan → spec → docs/ADR → context → git → security → performance → CI/CD → ship → deprecate) for work that must scale, ship, and be maintained — plus a quality bar (five-axis review, adversarial verification, interface contracts, production UI) and the user's own coding rules. Use whenever writing, modifying, debugging, refactoring, or reviewing code, or picking up a codebase. Triggers: write code, implement, build feature, fix bug, debug, refactor, review, ship, large project, 写代码, 改代码, 修bug, 重构, 代码审查, 上线, 大项目, 接手代码.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use general, paper-writing and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jcsaaddupuySkill

    general

    Universal coding principles and best practices

    Also in 3 projects that use this

  • MLNLP-WorldSkill

    paper-writing

    学术论文写作检查与优化助手。基于 MLNLP-World 社区整理的论文写作技巧，帮助检查和优化学术论文。Use when: (1) 检查论文 LaTeX 格式和排版, (2) 优化公式符号使用, (3) 改进图表设计, (4) 润色英文学术表达, (5) 检查参考文献格式, (6) 投稿前终稿检查, (7) 用户询问论文写作技巧或规范。

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 7 projects that use this

  • GoogleSkill

    domain-modeling

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

    Also in 4 projects that use this

  • MicrosoftSkill

    writing-for-agents

    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

    Also in 3 projects that use this

  • GoogleSkill

    grilling

    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

    Also in 4 projects that use this

  • +2 more from google

The file

Create a free account to mount
Files
SKILL.md

Coding

写、改、修、重构、审查代码的统一操作手册——单人日常闭环 ⇄ 大项目全生命周期，外加质量审查与你的编码守则。

写/改/修/重构/审查代码的统一手册——把你已配置的工程 skills 的精华整合在一处。按尺度取用：单人/日常（快而稳）与 大项目（可规划、可上线、可维护）。

基线（每次改动，always-on）

先读后改 · 贴合既有风格 · 最小手术式改动（标 file:line）· 用专用工具且独立调用并行 · 验证后如实报告（失败贴输出，不报未验证的"完成"）· 删除/覆盖/force-push/发数据先确认。

单人 / 日常编码闭环 → references/implement/

源码驱动source-driven.md → 增量实现incremental.md（≤100 行/步、改完即测） → TDDtdd.md（先写失败测试、红-绿-重构） → 简化simplify.md（降认知复杂度） → 调试debug.md（STOP→复现→缩小→根因→回归）。

大项目生命周期 → references/project/

规划planning.md · 规格spec.md · 文档/ADRdocs-adr.md · 上下文context.md · Gitgit.md · 安全security.md · 性能performance.md · CI/CDci-cd.md · 上线shipping.md · 弃用/迁移deprecation.md。

质量与正确性 → references/quality/

审查流程review.md（五维+严重度，0→7 按序） · 对抗性复核adversarial-review.md · 接口契约api-design.md · 生产 UIui.md。

编码守则（你平时的要求）→ references/rules.md

批评直给 · 速度并行但关键决策先问 · 质量零 AI 味 · 详细不啰嗦 · 复用优先 · 验证如实报告 · 暴露坑 · commit/安装/部署不擅自做。

沉淀 → 配套 memory 技能

非显然的修复根因、确立的标准、踩过的坑、用户偏好 → 按 memory 技能写进记忆，并把当天工作记进日记。

清单 → references/checklists.md

实现前 / 实现中 / 提交前 / 上线前 四道关。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free