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

Review Clarity

ASecurity

Review documentation for clarity, conciseness, and technical precision using cognitive load theory and decision-focused writing

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgodatabasedocumentation

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill review-clarity --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review Clarity?

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

Security grade badge for Review Clarity
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-review-clarity/badge)](https://www.skillsdirectory.com/skills/tstapler-review-clarity)

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

Download Zip
Files
SKILL.md
---
description: Review documentation for clarity, conciseness, and technical precision using cognitive load theory and decision-focused writing
---

# Documentation Clarity Review

Review the specified documentation file(s) using research-backed technical writing principles to ensure they are tight, terse, and technically precise for efficient human consumption.

**Target**: {{args}}

## Review Framework

Apply the **Three Questions Framework** (from [[Technical Writing - What Actually Counts]]):
1. **Decision Focus**: What specific decision does the reader need to make?
2. **Obstacle Identification**: What prevents them from making that decision confidently?
3. **Minimum Viable Information**: What is the least information needed to overcome those obstacles?

## Review Criteria

### 1. Cognitive Load Optimization (Based on [[Cognitive Load Theory in Technical Documentation]])

**Working Memory Limit**: Humans process 7±2 chunks. Reduce extraneous cognitive load.

- **Spatial Contiguity**: Related information appears physically close together
- **Coherence Principle**: Remove interesting but irrelevant information
- **Chunking**: Group information into 5-7 item clusters maximum
- **Progressive Disclosure**: Layer from overview to implementation details
- **Given-New Structure**: Progress from familiar to new information

### 2. Conciseness (Cut the Fluff)

- Remove filler words: "very", "really", "basically", "actually", "just", "simply", "in fact"
- Eliminate redundant phrases: "in order to" → "to", "at this point in time" → "now", "due to the fact that" → "because"
- Delete obvious statements and unnecessary context ("Context Dumping" anti-pattern)
- Avoid "Show My Work Problem": Include conclusions and actions, not reasoning process
- **Active Voice Preference**: "Configure the database" vs "The database should be configured"
- One idea per sentence, one topic per paragraph

### 3. Technical Precision

- Use specific, concrete terms over vague descriptions
- Include exact values, not approximations ("30 seconds" not "about half a minute")
- Define acronyms on first use, then use consistently
- Ensure code examples are correct and runnable
- Verify technical claims are accurate
- Name components explicitly rather than using pronouns

### 4. Information Architecture (Inverted Pyramid)

- **Front-Load Impact**: Critical information and risk factors appear first
- **Tier 1/2/3 Hierarchy**: Essential (decision-making) → Important (implementation) → Optional (context)
- Use descriptive headings that convey meaning (not just "Overview")
- Prefer bullet lists and tables over prose for comparisons
- Keep paragraphs short (3-5 sentences max)
- Use code blocks for commands, configs, and examples

### 5. Actionable Content

- **Problem → Solution → Action** pattern: Lead with problem, present solution, specify actions
- Lead with "what" and "how", not "why" (unless context is critical)
- Provide concrete examples, not abstract descriptions
- Include copy-pasteable commands and code
- Make next steps obvious with explicit action items
- Use **Priority Indicators**: CRITICAL (blocks progress), REQUIRED (necessary), CONSIDER (optimization)

### 6. Diátaxis Alignment (if applicable)

Check document type matches content:
- **Tutorial**: Learning-oriented, step-by-step for beginners
- **How-to Guide**: Task-oriented instructions for specific goals
- **Explanation**: Understanding-oriented discussions of concepts
- **Reference**: Information-oriented technical descriptions

Don't mix types—each document should have one primary purpose.

## Anti-Patterns to Flag

From [[Technical Writing - What Actually Counts]]:
- **Comprehensive Coverage Trap**: Documenting everything instead of what matters for decisions
- **Show My Work Problem**: Including reasoning process instead of conclusions and actions
- **Feature Documentation**: Describing what systems do rather than what users accomplish
- **Academic Writing Style**: Passive voice, abstract language, buried action items
- **Context Dumping**: Extensive background without clear relevance to current decisions
- **Split Attention**: Related information separated by irrelevant content

## The 30-Second Test

Can a knowledgeable reader understand the core message and required action within 30 seconds? If not, restructure for clarity.

## Output Format

For each file reviewed, provide:

1. **Summary**: One-line assessment + 30-second test result (pass/fail)
2. **Cognitive Load Issues**: Information processing overhead problems with line references
3. **Conciseness Issues**: Words/phrases to cut with before/after examples
4. **Structure Issues**: Organization and hierarchy problems
5. **Anti-Patterns Found**: Which patterns from the list above are present
6. **Suggested Edits**: Specific before/after improvements prioritized by impact
7. **Recommended Actions**: Prioritized list (CRITICAL/REQUIRED/CONSIDER)

After identifying issues, ask if I should apply the fixes automatically.

## Review Process

1. Read the target file(s)
2. Apply the Three Questions Framework to assess purpose
3. Run the 30-Second Test
4. Identify violations using criteria above
5. Categorize by cognitive load impact (high/medium/low)
6. Provide specific, actionable feedback with line references
7. Offer to apply fixes if requested

Attribution

tstaplertstapler
View sourceMore from tstapler →
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?".

942310 votes
View all in documentation →