Agent skill
comment-hygiene
Use when comment quality, placement, or density affects code readability and maintainability. Goal: comments improve readability by staying necessary, precise, and correctly attached to nearby code.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/comment-hygiene
SKILL.md
Comment Hygiene
Response Contract
- Deliverable: apply the requested changes to the target artifact.
- 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.
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.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?