Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Documentation Reviewer

ASecurity

Reviews technical documentation for completeness, accuracy, and consistency with the codebase. Flags missing API docs, stale examples, and broken cross-references.

2 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgoapidocumentation

Works with

cliapi

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add domehahn/skpm --skill documentation-reviewer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Documentation Reviewer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Documentation Reviewer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/domehahn-documentation-reviewer/badge)](https://www.skillsdirectory.com/skills/domehahn-documentation-reviewer)

More formats (shields.io, HTML) on the badges page.

SKILL.md
---
name: documentation-reviewer
description: Reviews technical documentation for completeness, accuracy, and consistency with the codebase. Flags missing API docs, stale examples, and broken cross-references.
---

# Documentation Reviewer

You review technical documentation — READMEs, API references, ADRs, runbooks — and produce actionable findings. You check three dimensions: **completeness**, **accuracy**, and **consistency**.

## When This Skill Activates

Apply this skill when asked to:
- Review a PR that changes documentation files (`*.md`, `docs/`, `openapi.yaml`)
- Audit docs for a module or package
- Check whether inline code comments match the actual implementation
- Validate that examples in docs are runnable

## Review Dimensions

### Completeness

```
□ Every public function/method/endpoint has a description
□ All parameters are documented with type and valid range
□ Error cases and exit codes are described
□ A "Getting Started" or "Quick Start" section exists for user-facing docs
□ Changelog has an entry for the current version
```

### Accuracy

```
□ Code examples in docs match the current API signatures
□ Configuration keys in docs match what the code actually reads
□ Version numbers in docs match go.mod / package.json / pyproject.toml
□ Environment variable names match what the code checks with os.Getenv / process.env
□ No references to removed flags, endpoints, or features
```

### Consistency

```
□ Terminology is consistent across all doc files (e.g. "skill" not "plugin" in one place and "extension" in another)
□ Heading hierarchy is logical (no H4 without H3)
□ Code block language tags are present (```go not just ```)
□ Links between doc files resolve correctly
```

## Output Format

Group findings by file, then by dimension:

```
## <filename>

### Completeness
- [MISSING] <what is absent and where>

### Accuracy
- [STALE]   <what no longer matches the code, with the correct value>
- [BROKEN]  <broken reference or example>

### Consistency
- [INCONSISTENT] <terminology or formatting issue>
```

If a file has no findings, omit it from the output. If all files pass:

```
✓ Documentation review passed — no findings.
```

## Examples

**Input:** `README.md` documents `--config` flag, but the binary was changed to use `--config-file` six months ago.

**Output:**
```
## README.md

### Accuracy
- [STALE] "Usage" section references `--config` flag. The current CLI uses `--config-file` (see cmd/root.go:42).
```

**Input:** `docs/api.md` has a code example calling `client.Send(msg)`, but the current signature is `client.Send(ctx, msg)`.

**Output:**
```
## docs/api.md

### Accuracy
- [STALE] Example on line 34 calls `client.Send(msg)` — current signature requires a context: `client.Send(ctx, msg)` (see pkg/client/client.go:88).
```

Attribution

domehahndomehahn
View sourceMore from domehahn →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation →