docs-verify — community docs-verify, claude-pilot, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Technical Writing Agents requiring precise documentation validation and compliance checks 🎯 Claude Code workflow engine - SPEC-first planning, TDD automation, GPT delegation, and context engineering. From idea to production, discipline included.

changoo89 changoo89
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The docs-verify skill by changoo89 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for Technical Writing Agents requiring precise documentation validation and compliance checks

Core Value

Empowers agents to validate 3-Tier documentation systems, ensuring adherence to line limits, cross-references, and file counts, leveraging bash scripting and grep for efficient link checking

Capabilities Granted for docs-verify

Validating documentation compliance before committing changes
Automating cross-reference checks in markdown files
Enforcing line limits and file count standards in documentation

! Prerequisites & Limits

  • Requires bash environment
  • Limited to markdown file analysis
  • Dependent on grep for link checking
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

docs-verify

Install docs-verify, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

SKILL: Documentation Verification

Purpose: Validate 3-Tier documentation system compliance - line limits, cross-references, file counts


Quick Start

When to Use

  • After closing plan (/03_close)
  • After running /document
  • Before committing documentation changes

Quick Reference

bash
1# Pure bash link check (no external deps) 2for file in CLAUDE.md docs/ai-context/*.md; do 3 [ -f "$file" ] || continue 4 grep -oE '@[^][:space:]]+' "$file" | while read ref; do 5 ref_path="${ref#@}" 6 [ ! -e "$ref_path" ] && echo "Broken: $ref in $file" 7 done 8done

Change Detection (MANDATORY FIRST STEP)

Before running verification, check if docs changed:

bash
1# Get changed markdown files (with fallback) 2CHANGED_MD=$(git diff --name-only HEAD~1 -- "*.md" 2>/dev/null || git diff --name-only -- "*.md" 2>/dev/null || echo "FALLBACK_FULL_VERIFY") 3 4# Fallback: If git diff fails, run full verification 5if [ "$CHANGED_MD" = "FALLBACK_FULL_VERIFY" ]; then 6 echo "Cannot detect changes, running full verification" 7 CHANGED_MD=$(find . -name "*.md" -type f ! -path "*/.git/*" ! -path "*/.trash/*") 8fi 9 10if [ -z "$CHANGED_MD" ]; then 11 echo "No markdown files changed" 12 echo "Skipping documentation verification" 13 exit 0 14fi 15 16echo "Changed markdown files:" 17echo "$CHANGED_MD"

Core Concepts

3-Tier System

Tier 1 (3 files, ≤200 lines each):

  • CLAUDE.md - Project architecture, features, Quick Start
  • docs/ai-context/project-structure.md - Tech stack, file tree
  • docs/ai-context/docs-overview.md - Documentation navigation

Tier 2: Component CONTEXT.md files (unlimited)

Tier 3: Feature-specific CONTEXT.md files


Verification Checks

1. Tier 1 Line Limits (Changed Files Only)

Limit: ≤200 lines per file

bash
1TIER1_FILES=( 2 "CLAUDE.md" 3 "docs/ai-context/project-structure.md" 4 "docs/ai-context/docs-overview.md" 5) 6 7for file in "${TIER1_FILES[@]}"; do 8 # Only check if file was changed 9 if echo "$CHANGED_MD" | grep -q "$file"; then 10 LINES=$(wc -l < "$file" | tr -d ' ') 11 if [ "$LINES" -gt 200 ]; then 12 echo "FAIL: $file has $LINES lines (limit: 200)" 13 exit 1 14 fi 15 echo "$file: $LINES lines" 16 fi 17done

On violation: Extract content to Tier 2 CONTEXT.md files

2. Tier 1 File Count (CRITICAL)

Limit: Exactly 2 files in docs/ai-context/

bash
1COUNT=$(find docs/ai-context -maxdepth 1 -name "*.md" -type f | wc -l | tr -d ' ') 2if [ "$COUNT" -ne 2 ]; then 3 echo "FAIL: docs/ai-context/ has $COUNT files (expected: 2)" 4 exit 1 5fi

3. Cross-Reference Validation (Changed Files Only)

bash
1# Only validate changed files 2for file in $CHANGED_MD; do 3 [ -f "$file" ] || continue 4 grep -oE '@\.(claude|docs)/[^][:space:]]+' "$file" 2>/dev/null | while read ref; do 5 ref_path="${ref#@}" 6 ref_path="${ref_path%[\`\*\]\"]}" 7 if [ ! -e "$ref_path" ]; then 8 echo "Broken reference: $ref in $file" 9 fi 10 done 11done

4. Circular Reference Detection

bash
1# Check for self-references (A → A) 2find . -name "*.md" ! -path "*/REFERENCE.md" ! -path "*/.git/*" | while read file; do 3 refs=$(grep -oE '@\.(claude|docs)/[^)[:space:]+' "$file" || true) 4 for ref in $refs; do 5 if [ "${ref#@}" = "$file" ]; then 6 echo "Self-reference: $file" 7 fi 8 done 9done

5. Skill Count Validation

bash
1ACTUAL=$(find .claude/skills -name "SKILL.md" | wc -l | tr -d ' ') 2STATED=$(grep -oE '\*\*[0-9]+ Skills\*\*' README.md | grep -oE '[0-9]+' || echo "0") 3 4if [ "$ACTUAL" -ne "$STATED" ]; then 5 echo "WARNING: Skill count mismatch - README: $STATED, actual: $ACTUAL" 6fi

Integration Pattern

In Commands

markdown
1## Step 3: Documentation Verification 2 3Invoke the `docs-verify` skill to validate documentation compliance. 4 5The skill checks: 6- Tier 1 line limits (≤200 lines) 7- Tier 1 file count (exactly 2 in ai-context/) 8- Cross-reference validity 9- Circular references

Claude reads this skill file and executes the bash commands inline.


three-tier-docs: Full 3-Tier documentation system | vibe-coding: File size standards


Version: claude-pilot 4.4.14

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is docs-verify?

Ideal for Technical Writing Agents requiring precise documentation validation and compliance checks 🎯 Claude Code workflow engine - SPEC-first planning, TDD automation, GPT delegation, and context engineering. From idea to production, discipline included.

How do I install docs-verify?

Run the command: npx killer-skills add changoo89/claude-pilot/docs-verify. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for docs-verify?

Key use cases include: Validating documentation compliance before committing changes, Automating cross-reference checks in markdown files, Enforcing line limits and file count standards in documentation.

Which IDEs are compatible with docs-verify?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for docs-verify?

Requires bash environment. Limited to markdown file analysis. Dependent on grep for link checking.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add changoo89/claude-pilot/docs-verify. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use docs-verify immediately in the current project.

Related Skills

Looking for an alternative to docs-verify or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI