agentleFS
lvdaxianerlvdaxianer/skills/CLAUDE.md

skills

CLAUDE.md1 starsChanged 5 months agoMITView on GitHub

The workflow is mandatory. Do not treat it as optional guidance. Any deviation from the workflow is noncompliant. 本仓库的开发任务默认遵循 development-workflow/SKILL.md。 归档、解压与备份任务同时遵循 package-backup/SKILL.md。 每个 Claude 会话开始后,只要任务涉及代码、测试、配置、重构、持久项目文档、 OpenSpec change 或提交,都必须先加载并遵守 development-workflow/SKILL.md。 如果任务涉及打包、备份、还原、解压或提取,还必须先加载并遵守 package-backup/SKILL.md。 对于归档与解压工作,还要额外遵守:

The file

Show its rules and text

We split this CLAUDE.md into the rules it gives an agent

36 rules. About 0 are common, 26 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈26

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    commit-per-task:继续下个任务前执行 commit --style=full,创建一个带 body 和 footer 的原子中文 Conventional Commit。

    line 23
  2. Distinctive:

    After all planned tasks finish, emit a final audit report that lists completed tasks and lists unfinished tasks before the workflow is …

    line 36
  3. Very specific:

    Use superpowers:brainstorming before writing the plan so the plan captures the intended behavior, constraints, trade-offs, and acceptance …

    line 46
  4. Very specific:

    Use openspec to create or update the written change asset under openspec/changes/<change-name>/.

    line 47
  5. Very specific:

    Before creating or updating the written change asset, verify that the project root contains a non-hidden openspec/ directory.

    line 48
  6. Very specific:

    Use the local OpenSpec spec-driven layout:

    line 50
  7. Distinctive:

    Every planned task must have one durable checkbox or equivalent status marker.

    line 59
  8. Distinctive:

    If a session resumes mid-change, read the OpenSpec task list first, continue from the first unchecked task, and preserve already completed …

    line 60
  9. Distinctive:

    After every OpenSpec change is fully executed and verified, archive the completed OpenSpec change according to the repository's OpenSpec …

    line 61
  10. Distinctive:

    After the final audit and archive flow completes, produce a final audit report that lists completed tasks and lists unfinished tasks for …

    line 62
  11. Distinctive:

    Every workflow-created commit MUST be a Chinese Conventional Commit with a mapped emoji subject, a non-empty body, and a non-empty footer.

    line 67
  12. Very specific:

    Use superpowers:brainstorming to clarify the requirement and approve the design.

    line 83
  13. Very specific:

    Use OpenSpec to create or update the written change, including the OpenSpec plan and task checklist.

    line 84
  14. Very specific:

    Use superpowers:test-driven-development and write the smallest useful TDD test for the selected task.

    line 87
  15. Distinctive:

    Run the focused test and confirm the RED failure is caused by missing behavior.

    line 88
  16. Distinctive:

    Run the focused test again and confirm it passes.

    line 90
  17. Distinctive:

    Run the relevant broader test, lint, build, or documentation check for the touched area.

    line 91
  18. Distinctive:

    Run a plan-implementation consistency audit using Superpowers audit capability.

    line 92
  19. Very specific:

    Create one atomic Chinese Conventional Commit for this task by applying commit --style=full.

    line 97
  20. Distinctive:

    Only after the commit succeeds, move to the next task.

    line 98
  21. Distinctive:

    After all tasks are complete, run a final audit to ensure all planned tasks are complete, all acceptance criteria are satisfied, and no …

    line 99
  22. Distinctive:

    Do not ask for confirmation when the next action is mandated by this workflow.

    line 104
  23. Distinctive:

    Do not skip validation, even for small or documentation-only changes.

    line 105
  24. Distinctive:

    Do not implement production code before the OpenSpec plan has been written and validated.

    line 106
  25. Distinctive:

    Do not create standalone planning commits by default.

    line 107
  26. Distinctive:

    Do not create a standalone OpenSpec or documentation commit unless the change is documentation-only or no business implementation remains …

    line 108
  27. Distinctive:

    Do not keep implementation code that was written before a failing test unless the user explicitly exempted the task from TDD.

    line 109
  28. Very specific:

    Do not mark a task complete before RED, GREEN, broader verification, plan-implementation consistency audit, code-review-spec, fixes, …

    line 110
  29. Distinctive:

    Do not batch-complete tasks at the end.

    line 111
  30. Distinctive:

    Do not combine unrelated plan tasks into one commit.

    line 112
  31. Distinctive:

    Do not commit unrelated user changes.

    line 113
  32. Distinctive:

    If a gate fails, fix the failure and re-run the same gate before continuing.

    line 114
  33. Distinctive:

    If a clear fix is available during review, make it immediately and verify again.

    line 115
  34. Distinctive:

    If the same blocker prevents progress after repeated attempts, report the blocker with exact command output and the affected file path.

    line 116
  35. Distinctive:

    When reporting progress, include the current task and gate:

    line 122
  36. Distinctive:

    Keep reports concise. Problems or risks come before summaries.

    line 130

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Claude 默认开发上下文

The workflow is mandatory. Do not treat it as optional guidance. Any deviation from the workflow is noncompliant.

本仓库的开发任务默认遵循 development-workflow/SKILL.md。 归档、解压与备份任务同时遵循 package-backup/SKILL.md。

会话启动规则

每个 Claude 会话开始后,只要任务涉及代码、测试、配置、重构、持久项目文档、 OpenSpec change 或提交,都必须先加载并遵守 development-workflow/SKILL.md。 如果任务涉及打包、备份、还原、解压或提取,还必须先加载并遵守 package-backup/SKILL.md。

该默认流程要求:

  • brainstorming-first:需求讨论先用 superpowers:brainstorming。
  • OpenSpec-plan-first:落地到文件时每次变更都是一个 OpenSpec change,使用 openspec/changes/<change-name>/ 的 spec-driven 结构,并通过 openspec validate <change-name> --strict。
  • planning-validated-first:OpenSpec 规划必须先于实现完成并通过验证,但默认随首个完整业务任务提交一起提交。
  • TDD-first:每个任务先写失败测试,确认 RED,再实现 GREEN,并保持可重构。
  • review-gated:每个小任务后严格执行 code-review-spec,按 canonical 规范修复所有应修复的问题。
  • commit-per-task:继续下个任务前执行 commit --style=full,创建一个带 body 和 footer 的原子中文 Conventional Commit。
  • final-audit-and-report:所有 planned tasks 完成后先做 final audit,再输出 final audit report,列出 completed tasks 和 unfinished tasks,然后再归档 OpenSpec change。

对于归档与解压工作,还要额外遵守:

  • package-backup-first:先用 package-backup/SKILL.md 和 package-backup/references/package_backup.md 确认命名、校验与还原安全约定,再执行任何压缩或解压动作。

Stage Boundaries

  • Requirement discussion uses superpowers:brainstorming.
  • Requirement persistence uses OpenSpec.
  • Implementation uses superpowers:test-driven-development after the OpenSpec planning asset has been created and validated.
  • Archive and extraction work uses package-backup/SKILL.md as the domain skill.
  • After all planned tasks finish, emit a final audit report that lists completed tasks and lists unfinished tasks before the workflow is considered fully closed.

Lightweight Discussion And Architecture Design

  • 需求讨论、方案比较、架构设计、调研总结、快速架构设计文档草稿,如果不进入代码、测试、配置、重构、持久项目文档、OpenSpec change 或 git commit,不触发完整 development-workflow。
  • 这类轻量工作可以快速输出 Markdown 草稿、架构说明、对比表、决策建议或讨论结论,不要求 OpenSpec planning、TDD、code-review-spec 或 commit-per-task gates。
  • 如果轻量讨论或架构设计后续进入代码、测试、配置、重构、持久项目文档、OpenSpec change 或 git commit,必须先切换回完整 development-workflow,再执行对应文件修改、验证和提交。

OpenSpec Planning Requirements

  • Use superpowers:brainstorming before writing the plan so the plan captures the intended behavior, constraints, trade-offs, and acceptance criteria.
  • Use openspec to create or update the written change asset under openspec/changes/<change-name>/.
  • Before creating or updating the written change asset, verify that the project root contains a non-hidden openspec/ directory. If it is missing, initialize the OpenSpec scaffold first and select Codex and Claude instruction targets. Hidden .openspec paths do not satisfy the project OpenSpec root requirement.
  • Future persisted changes and approved specs must be based on the project OpenSpec workflow. Keep changes under openspec/changes/ and approved specs under openspec/specs/. Non-OpenSpec documents do not replace OpenSpec change/spec assets as the authoritative source.
  • Use the local OpenSpec spec-driven layout:
    • openspec/changes/<change-name>/.openspec.yaml
    • openspec/changes/<change-name>/proposal.md
    • openspec/changes/<change-name>/design.md
    • openspec/changes/<change-name>/tasks.md
    • openspec/changes/<change-name>/specs/<capability>/spec.md
  • Validate the OpenSpec change with openspec validate <change-name> --strict.
  • The OpenSpec plan is a required project asset. Validate it before implementing production code, but do not require a standalone planning commit by default. OpenSpec planning files are committed with the first atomic task commit that carries a complete business module.
  • A standalone OpenSpec or documentation commit is allowed only when the change is documentation-only or when no business implementation remains to carry the document update.
  • Every planned task must have one durable checkbox or equivalent status marker. Mark exactly one completed task immediately after its gate passes. Do not batch-complete tasks at the end.
  • If a session resumes mid-change, read the OpenSpec task list first, continue from the first unchecked task, and preserve already completed task markers.
  • After every OpenSpec change is fully executed and verified, archive the completed OpenSpec change according to the repository's OpenSpec archive process.
  • After the final audit and archive flow completes, produce a final audit report that lists completed tasks and lists unfinished tasks for the completed change.

Commit Message Requirements

  • Apply commit --style=full for every workflow-created task, archive, or documentation commit unless the user explicitly requests --style=simple.
  • Every workflow-created commit MUST be a Chinese Conventional Commit with a mapped emoji subject, a non-empty body, and a non-empty footer.
  • The commit body MUST explain what changed and why, including relevant verification evidence when useful.
  • The commit footer MUST include traceability metadata. Use Refs: when no breaking change, issue, co-author, or review reference applies.
  • For OpenSpec-driven task commits, prefer footer values such as Refs: OpenSpec <change-name> task <task-id>.

code-review-spec 执行要求

  • 当任务涉及代码审查、格式化或代码修改时,必须严格执行 code-review-spec,不得用“差不多”“大致符合”或选择性覆盖代替。
  • 执行 code-review-spec 时,必须逐项对照 canonical 的 SKILL.md、spec.md 以及相关 references/* 检查;未覆盖的项必须明确说明原因,不能默认合格。
  • 如果 canonical code-review-spec 的任一要求不满足,必须视为未通过,直到修复并重新验证通过为止。
  • 任何 code-review-spec 结论都必须基于实际对照结果,而不是摘要、印象判断或部分规则检查。

Mandatory Task Loop

For each development task, execute this exact order:

  1. Use superpowers:brainstorming to clarify the requirement and approve the design.
  2. Use OpenSpec to create or update the written change, including the OpenSpec plan and task checklist.
  3. Validate the OpenSpec change and keep those planning files available for the first related task commit.
  4. Select the next unchecked task from the OpenSpec plan. Do not start later tasks early.
  5. Use superpowers:test-driven-development and write the smallest useful TDD test for the selected task.
  6. Run the focused test and confirm the RED failure is caused by missing behavior.
  7. Implement the minimal GREEN change required by the failing test.
  8. Run the focused test again and confirm it passes.
  9. Run the relevant broader test, lint, build, or documentation check for the touched area.
  10. Run a plan-implementation consistency audit using Superpowers audit capability. Confirm the implementation matches the OpenSpec plan, acceptance criteria, and current task scope.
  11. Apply code-review-spec to the full diff for this task, strictly and item-by-item against the canonical sources.
  12. Fix every issue that should be fixed under code-review-spec. Do not ask for confirmation before making clear quality, correctness, maintainability, performance, or security fixes.
  13. Re-run the focused and broader verification commands after fixes.
  14. Mark exactly one completed task immediately after its gate passes in the OpenSpec checklist.
  15. Create one atomic Chinese Conventional Commit for this task by applying commit --style=full; the message must include a non-empty body and non-empty footer. Include uncommitted related OpenSpec planning files in this commit when the task carries a complete business module.
  16. Only after the commit succeeds, move to the next task.
  17. After all tasks are complete, run a final audit to ensure all planned tasks are complete, all acceptance criteria are satisfied, and no implementation drift remains.
  18. Archive the completed OpenSpec change, then commit the archive/update if the archive modifies repository files.

Gate Rules

  • Do not ask for confirmation when the next action is mandated by this workflow.
  • Do not skip validation, even for small or documentation-only changes.
  • Do not implement production code before the OpenSpec plan has been written and validated.
  • Do not create standalone planning commits by default; carry OpenSpec planning files with the first atomic task commit for a complete business module.
  • Do not create a standalone OpenSpec or documentation commit unless the change is documentation-only or no business implementation remains to carry it.
  • Do not keep implementation code that was written before a failing test unless the user explicitly exempted the task from TDD.
  • Do not mark a task complete before RED, GREEN, broader verification, plan-implementation consistency audit, code-review-spec, fixes, re-verification, and commit gates all pass.
  • Do not batch-complete tasks at the end. Progress must be durable after every finished task.
  • Do not combine unrelated plan tasks into one commit.
  • Do not commit unrelated user changes. Preserve existing dirty work that is outside the task.
  • If a gate fails, fix the failure and re-run the same gate before continuing.
  • If a clear fix is available during review, make it immediately and verify again.
  • If the same blocker prevents progress after repeated attempts, report the blocker with exact command output and the affected file path.
  • For code-review-spec, a gate only passes after every applicable rule has been checked and any uncovered rule has been explicitly accounted for.
  • The final audit gate only passes when the OpenSpec checklist, implementation diff, tests, and review evidence agree that the planned change is complete.

Required Status Format

When reporting progress, include the current task and gate:

Current task: <task name>
Gate: <brainstorming | OpenSpec plan | OpenSpec validation | RED | GREEN | broader verification | plan-implementation consistency audit | code-review-spec | task mark-complete | commit | final audit | OpenSpec archive | next task>
Evidence: <command or file checked>

Keep reports concise. Problems or risks come before summaries.

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.

Reviews can't be read right now.

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.