comment-hygiene
について
このスキルは、コードコメントを特定の付箋箇所(Surface、Data、Rule、External)に分類することで、開発者がコメントの記述、レビュー、最適化を支援します。コメントのベストプラクティスについて尋ねられた場合や、既存のコード内のコメントを改善する際にご利用ください。改善されたコメントの配置とテキストを含む更新済みコードを直接返します。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/comment-hygieneこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Comment Hygiene
Response Contract
- Deliverable: return the updated code with the final comment text and placement.
- Chat output: no additional output beyond the deliverable.
Skill Model
This model classifies what can be commented. It does not imply quality.
Comment Attachment Sites
-
Surface Public entry points and externally visible surfaces.
-
Data Data shapes and schemas.
-
Rule Rule-bearing logic and decision points.
-
External External coupling and external constraints.
Standards
Each standard is defined once here and referenced elsewhere by its ID.
-
site.assign — Assign a site Every comment must be assignable to exactly one attachment site: Surface, Data, Rule, or External.
-
site.focus.surface — Surface focus Surface comments cover externally visible meaning and caller-facing constraints.
-
site.focus.data — Data focus Data comments cover representation meaning and structural constraints.
-
site.focus.rule — Rule focus Rule comments cover rule intent and rule boundaries.
-
site.focus.external — External focus External comments cover external assumptions and external constraints.
-
site.closest — Place at the closest site Place the comment at the closest location where a reader needs it for the assigned site and focus.
-
comment.no_narration — No narration Remove comments that restate adjacent code or narrate straightforward steps.
-
comment.nonoverlap — No overlap Avoid multiple comments that cover the same point. If one note spans multiple sites, split it so each comment has one site and one focus.
-
comment.precise — Precise and scoped Use specific terms and explicit conditions. Keep scope bounded to what the assigned site and focus need.
-
comment.stable — Prefer stable content Prefer describing intent, constraints, and externally relevant meaning over volatile implementation detail.
-
conflicts.priority — Priority rule When standards conflict, apply this priority order:
comment.no_narrationsite.assignandsite.focus.*comment.nonoverlapsite.closestcomment.precisecomment.stable
Workflow
- Enumerate existing comments and planned comments.
- Assign each comment to exactly one attachment site and confirm it matches the site focus. Apply
site.assignandsite.focus.*. - Delete narration and restatement. Apply
comment.no_narration. - De-duplicate overlapping points. Apply
comment.nonoverlap. - Relocate comments to the closest location where readers need them. Apply
site.closest. - Rewrite remaining comments to be specific and bounded. Apply
comment.precise. - Prefer stable content over volatile detail. Apply
comment.stable. - Run acceptance checks.
Acceptance Criteria
A revision is complete only if all checks pass.
- Response: Output satisfies the Response Contract.
- Standards satisfied:
site.assign,site.focus.*,site.closest,comment.no_narration,comment.nonoverlap,comment.precise,comment.stable,conflicts.priority.
GitHub リポジトリ
関連スキル
algorithmic-art
メタThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
開発This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
デザインUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
その他This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
