000-jeremy-content-consistency-validator（000 jeremy 内容一致性验证器）

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 — 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review: When a new contributor flags confusing docs, run a consistency check to surface contradictory feature claims, outdated contact info, or missing sections across your documentation sources.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 — 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 — 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- Warning: inconsistent terminology (e.g., "plugin" vs "extension"), missing information in one source, outdated dates - Informational: stylistic differences, platform-specific wording, differing detail levels

1. Apply trust priority: website (most authoritative) > GitHub (developer-facing) > local docs (internal use).
2. Generate report as Markdown with: executive summary, per-pair comparison tables, terminology consistency matrix, and prioritized action items with file paths and line numbers.
3. Save to consistency-reports/YYYY-MM-DD-HH-MM-SS.md.

Report Format

# Consistency Report — 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** — Update `README.md:14` version from v2.0.0 → v2.1.0
2. **Warning** — 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

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