Agent skill
documentation-review
Review and correct documentation for consistency, correctness, and drift. Documentation edits only (txt, md, mdx, rst) - no functional code changes. Triggers: "review docs", "check documentation", "doc review", "fix docs".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/documentation-review-keminghe-common-devx
Metadata
Additional technical details for this skill
- author
- KemingHe
- version
- 2.0.0
SKILL.md
Documentation Review
Review and correct documentation files for consistency, correctness, and drift. Documentation edits only - no functional code changes.
Temporary persona: Technical editor with expertise in documentation standards and version control.
When to Use This Skill
- Before committing documentation changes
- Auditing docs for staleness or drift
- Reviewing PRs (GitHub) / MRs (GitLab) with documentation updates
- Checking consistency across related files
Process
Step 1: Identify Scope
Determine files to review:
- Single file, directory, or pattern
- Related files (e.g., SKILL.md + README + assets)
Step 2: Apply Checklist
| Dimension | Check For |
|---|---|
| Consistency | Version sync (frontmatter/footer), naming patterns, terminology |
| Correctness | Valid YAML/markdown, working links, accurate paths |
| Completeness | Required sections present, no unfilled placeholders |
| Freshness | Last Updated date, version numbers, changelog entries |
| Characters | QWERTY-only everywhere; no smart quotes, emojis, or special Unicode; no em-dashes or em-dash substitutes (--, --) in prose; use - for clause separation (exception: ↑) |
| Inline formatting | _underscore_ italics only; colon outside bold label markers (**Topic**:) |
| Linter | Check IDE/editor linter errors when available |
| Output quality | Soft-wrapped bullets or prose; sentences broken across hard newlines; orphaned (optional) labels in populated sections; unfilled [placeholder] text; terminology inconsistency; KISS/DRY violations |
Step 3: Check Linter Errors
When linter tooling is available (IDE, markdownlint, etc.):
- Run linter on files in scope
- Include linter errors in findings table
- Distinguish between new errors (introduced by changes) and pre-existing
Common markdown linter catches:
- Missing language specifier on fenced code blocks
- Inconsistent list indentation
- Trailing whitespace or missing final newline
- Invalid link references
Step 4: Report Findings
Present issues in structured table:
| Issue | Location | Current | Fix Needed |
| :--- | :--- | :--- | :--- |
| [issue type] | Line X | `[current]` | [action] |
Summarize with:
- Total issues found
- Critical vs minor classification
- Recommended action order
Common Misses
- Last Updated: Forgetting to update date after changes
- Version drift: Frontmatter version differs from footer
- Stale links: Renamed files but not references
- Placeholder remnants:
[TODO]or[TBD]left in final docs - Linter errors: Ignoring IDE warnings on markdown files
General Doc Constraints
Apply to all generated output. If a discovered template deviates from any rule (e.g., uses emojis semantically, uses a different bullet convention), note the deviation explicitly and confirm with the user before treating it as a permitted exception.
- Characters: QWERTY keyboard typeable only - no smart quotes, emojis, or special Unicode anywhere. In prose, do not use em-dashes or em-dash substitutes (
--,--); use-(space-dash-space) for clause separation instead. Exception:↑for ToC navigation. - Inline formatting: Use
_underscore_for italics, not*single-star*. Place colons after bold inline labels outside the markers:**Topic**:not**Topic:**. - Bullets: Use
-for all unordered lists; one bullet per complete thought; never wrap a bullet's content mid-sentence onto a continuation line - split into separate bullets if too long or multi-thought. Nested sub-bullets for component grouping are permitted. End with a period only when the item is a full sentence; omit the period for concise fragment items (preferred). - Prose: Never break a sentence across lines with a hard newline; multi-sentence paragraphs belong on one continuous line since editors and viewers handle visual wrapping. Exception: commit message bodies use one sentence per line for
git logreadability. - Template hygiene: Delete
(optional)and any parenthetical conditional label (e.g.,(if operational)) from a section header the moment the section is populated - treat it as a.gitkeep-style placeholder that exists only until first use, then is removed. Omit the entire section (header and body) when unused. Populate all bracketed placeholders with actual content; never leave[TODO],[TBD], or any[placeholder]in generated output. - Consistency: Use the same term for the same concept throughout; match the voice and tense of the template; do not mix header levels for parallel sections.
- KISS and DRY: Each section and bullet conveys unique information - no redundancy or overlap.
General Doc Constraints v1.1.0 - KemingHe/common-devx
Skill Constraints
- Documentation only: Edit txt, md, mdx, rst files - no functional code changes
- Structured output: Always use table format for findings
- Prioritized: Critical issues (broken links, wrong versions) before style issues
- Linter-aware: Check and report linter errors when tooling is available
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?