Agent SkillsAgent Skills
jeremylongshore

000-jeremy-content-consistency-validator

@jeremylongshore/000-jeremy-content-consistency-validator
jeremylongshore
1,761
231 forks
Updated 3/31/2026
View on GitHub

Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy reports. Use when checking content alignment or finding mixed messaging. Trigger with phrases like "check consistency", "validate documentation", or "audit messaging".

Installation

$npx agent-skills-cli install @jeremylongshore/000-jeremy-content-consistency-validator
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Pathplugins/productivity/000-jeremy-content-consistency-validator/skills/000-jeremy-content-consistency-validator/SKILL.md
Branchmain
Scoped Name@jeremylongshore/000-jeremy-content-consistency-validator

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

npx agent-skills-cli list

Skill Instructions


name: 000-jeremy-content-consistency-validator description: | Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy reports. Use when checking content alignment or finding mixed messaging. Trigger with phrases like "check consistency", "validate documentation", or "audit messaging". allowed-tools: Read, WebFetch, WebSearch, Grep, Bash(diff:), Bash(grep:) version: 1.0.0 author: Jeremy Longshore jeremy@intentsolutions.io license: MIT compatible-with: claude-code, codex, openclaw tags: [productivity, audit, 000-jeremy]


Content Consistency Validator

Overview

Checks content for tone, terminology, formatting, and structural consistency across multiple documentation sources (websites, GitHub repos, local docs). Generates read-only discrepancy reports with severity-classified findings and actionable fix suggestions including file paths and line numbers.

Examples

  • Pre-release audit: Before tagging a new version, run the validator to catch version mismatches between your README, docs site, and changelog β€” e.g., the website says v2.1.0 but the GitHub README still references v2.0.0.
  • Post-rebrand check: After renaming a product or updating terminology (e.g., "plugin" to "extension"), validate that all docs, landing pages, and contributing guides use the new term consistently.
  • Onboarding review: When a new contributor flags confusing docs, run a consistency check to surface contradictory feature claims, outdated contact info, or missing sections across your documentation sources.

Prerequisites

  • Access to at least two content sources (website, GitHub repo, or local docs directory)
  • WebFetch permissions configured for remote URLs (deployed sites, GitHub raw content)
  • Local documentation stored in recognizable paths (docs/, claudes-docs/, internal/)

Instructions

  1. Discover sources β€” scan for build directories (dist/, build/, public/, out/, _site/), GitHub README/CONTRIBUTING files, and local doc folders:
    find . -maxdepth 3 -name "README*" -o -name "CONTRIBUTING*" | head -20
    ls -d docs/ claudes-docs/ internal/ 2>/dev/null
    
  2. Extract structured data from each source: version numbers, feature claims, product names, taglines, contact info, URLs, and technical requirements:
    grep -rn 'v[0-9]\+\.[0-9]\+' docs/ README.md
    grep -rn -i 'features\|capabilities' docs/ README.md
    
  3. Verify extraction β€” confirm at least 3 data points per source. If a source returns empty, check the Error Handling table before continuing.
  4. Build comparison matrix pairing each source against every other (website vs GitHub, website vs local docs, GitHub vs local docs):
    diff <(grep -i 'version' README.md) <(grep -i 'version' docs/overview.md)
    
  5. Classify discrepancies by severity:
    • Critical: conflicting version numbers, contradictory feature lists, mismatched contact info, broken cross-references
    • Warning: inconsistent terminology (e.g., "plugin" vs "extension"), missing information in one source, outdated dates
    • Informational: stylistic differences, platform-specific wording, differing detail levels
  6. Apply trust priority: website (most authoritative) > GitHub (developer-facing) > local docs (internal use).
  7. Generate report as Markdown with: executive summary, per-pair comparison tables, terminology consistency matrix, and prioritized action items with file paths and line numbers.
  8. Save to consistency-reports/YYYY-MM-DD-HH-MM-SS.md.

Report Format

# Consistency Report β€” YYYY-MM-DD

## Executive Summary
| Severity | Count |
|----------|-------|
| Critical | 2     |
| Warning  | 5     |
| Info     | 3     |

## Website vs GitHub
| Field        | Website       | GitHub        | Severity |
|-------------|---------------|---------------|----------|
| Version     | v2.1.0        | v2.0.0        | Critical |
| Feature X   | listed        | missing       | Warning  |

## Action Items
1. **Critical** β€” Update `README.md:14` version from v2.0.0 β†’ v2.1.0
2. **Warning** β€” Add "Feature X" to `README.md` feature list

Output

The skill produces a timestamped Markdown report saved to consistency-reports/YYYY-MM-DD-HH-MM-SS.md containing:

  • Executive summary: Severity counts (Critical/Warning/Info) at a glance
  • Pair comparison tables: Field-by-field comparison between each source pair with severity classification
  • Terminology matrix: Cross-source consistency check for product names, versions, and key terms
  • Prioritized action items: Specific fixes with file paths and line numbers, ordered by severity

Error Handling

ErrorCauseSolution
Website content unreachableURL returns 4xx/5xx or build dir missingVerify site is deployed or run local build; check WebFetch permissions
GitHub API rate limitToo many fetches in short windowPause and retry after reset window; use authenticated requests
No documentation directoryExpected paths don't existConfirm working directory; specify doc path explicitly
Empty content extractionClient-side rendering not visible to fetchUse local build output directory instead of live URL
Diff command failureFile paths contain special charactersQuote all file paths passed to diff and grep

Resources

  • Content source discovery logic: ${CLAUDE_SKILL_DIR}/references/how-it-works.md
  • Trust priority and validation timing: ${CLAUDE_SKILL_DIR}/references/best-practices.md
  • Use-case walkthroughs: ${CLAUDE_SKILL_DIR}/references/example-use-cases.md

More by jeremylongshore

View all
vertex-agent-builder
1,768

Build and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

gcp-examples-expert
1,768

Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns. Use when asked to "show ADK example" or "provide GCP starter kit". Trigger with relevant phrases based on skill purpose.

genkit-production-expert
1,768

Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.

validator-expert
1,768

Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices. Generates weighted scores (0-100%) with actionable remediation plans. Use when asked to validate a deployment, run a production readiness check, audit security posture, or verify compliance for Vertex AI agents. Trigger with "validate deployment", "production readiness", "security audit", "compliance check", "is this agent ready for prod", "check my ADK agent", "review before deploy", or "production readiness check". Make sure to use this skill whenever validating ADK agents for Agent Engine.