PluginBench
Skill
Pass
Audit score 90

blog-locale-audit

agricidaniel/claude-blog

Audit multilingual blog content for translation completeness, SEO parity, hreflang correctness, and freshness.

What is blog-locale-audit?

Scans a directory of multilingual blog posts to verify every language version is complete, consistent, correctly tagged, and SEO-optimized. Builds a translation coverage matrix, flags stale translations, validates hreflang and schema, and emits a prioritized report with runnable fix commands. Use when checking international content quality before publication.

  • Builds a translation coverage matrix showing which posts exist in which languages
  • Audits content parity across versions (section count, FAQ count, image count, word count ratios, link counts)
  • Validates SEO elements across languages (title tags, meta descriptions, lang attributes, canonical URLs, schema markup)
  • Checks hreflang tags for self-reference, bidirectionality, canonical consistency, and x-default fallback
  • Detects stale translations by comparing source modification dates against translation dates
  • Emits prioritized fixes with runnable commands for missing and outdated translations

How to install blog-locale-audit

npx skills add https://github.com/agricidaniel/claude-blog --skill blog-locale-audit
Claude Code
Cursor
Windsurf
Cline

How to use blog-locale-audit

  1. 1.Run the skill with the target blog directory: `npx skills add https://github.com/agricidaniel/claude-blog --skill blog-locale-audit`
  2. 2.Invoke with `locale audit <directory>` or equivalent trigger phrase
  3. 3.Review the markdown report showing translation coverage matrix, content parity issues, SEO gaps, and hreflang validation results
  4. 4.Run suggested fix commands (e.g., `/blog translate <file> --to <language>`) to address missing or stale translations
  5. 5.Optionally pass `--html` flag to generate an HTML report file for sharing with stakeholders

Use cases

Good for
  • Before publishing a multilingual blog redesign, audit all language versions to ensure no translations are missing or out of sync
  • Verify that German and French translations of a product blog have the same number of sections and images as the English source
  • Check that hreflang tags are correctly configured across all language versions to prevent duplicate-content penalties
  • Identify which translations are older than 90 days and need refresh after the source content was updated
  • Generate an HTML report for stakeholders showing translation coverage gaps and SEO compliance across all locales
Who it's for
  • Multilingual content managers and editors
  • International SEO specialists
  • Blog platform maintainers supporting multiple languages
  • Content teams managing translations across language pairs

blog-locale-audit FAQ

What language codes does this skill recognize?

ISO 639-1 language codes in lowercase (e.g., en, de, fr), optionally with ISO 15924 script in title case (e.g., zh-Hans) or ISO 3166-1 Alpha-2 region in uppercase (e.g., en-US). Ambiguous codes like es, pt, and zh are flagged unless explicitly declared as neutral.

How does it detect which post is the source and which are translations?

It uses translationGroupId, sourceSlug, schema translationOfWork.url, or hreflang-map.json entries to group related posts. It identifies the source language as the most common translatedFrom target or the sourceLanguage field in hreflang-map.json.

What happens if hreflang files don't exist?

The skill flags this as a critical gap and offers to regenerate hreflang assets via `/blog multilingual` or suggests creating hreflang-tags.html manually. If seo-hreflang from claude-seo is installed, it recommends running that for deeper validation.

How does it determine if a translation is stale?

It compares translatedDate in frontmatter against the source's dateModified or Git mtime. Translations older than 90 days are flagged as needing refresh. It also detects when the source was updated after the translation date.

Can it generate an HTML report for stakeholders?

Yes, pass the `--html` flag to write locale-audit-report.html inside the audited project root. All dynamic content is HTML-escaped for security.

Full instructions (SKILL.md)

Source of truth, from agricidaniel/claude-blog.


name: blog-locale-audit description: > Audit a directory of multilingual blog content for completeness, consistency, hreflang correctness, meta-tag parity, and freshness. Builds a translation coverage matrix, flags stale translations, validates hreflang and schema, and emits a prioritized report with runnable fix commands. Use when user says "locale audit", "blog locale-audit", "check translations", "multilingual audit", "translation check", "hreflang check", "Uebersetzungen pruefen". user-invokable: true argument-hint: "<directory>" license: MIT compatibility: Standalone within claude-blog. Optional richer hreflang validation via claude-seo seo-hreflang. metadata: author: AgriciDaniel version: "2.2.0" category: blog

Blog Locale Audit, Multilingual Quality Control

Audits a directory of multilingual blog content to ensure every language version is complete, consistent, correctly tagged, and SEO-optimized. Catches international content issues before they hurt rankings.

Adapted from claude-blog-multilingual by Chris Mueller (Pro Hub Challenge, March 2026). Original: https://github.com/Chriss54/multilingual-int

Workflow

Phase 1: Discovery

  1. Resolve the target directory inside the project root/current working directory. Reject symlinked directories and traversal outside the root, then scan blog content and group posts by language using:
    • Subdirectory names (en/, de/, fr/).
    • Frontmatter lang and translatedFrom fields.
    • hreflang-map.json if present.
  2. Normalize detected language codes with the shared multilingual locale rules used by blog-translate, blog-localize, and blog-multilingual: ISO 639-1 language in lowercase, optional ISO 15924 script in title case, optional ISO 3166-1 Alpha-2 region in uppercase. Flag ambiguous language-only codes such as es, pt, and zh unless the content declares an explicit neutral mode.
  3. Build a content matrix mapping which post exists in which languages. Use a stable translation-group key before comparing slugs: translationGroupId, sourceSlug, schema translationOfWork.url, or the IDs and URLs in hreflang-map.json. Fall back to normalized source slug only when no stable key exists.
  4. Detect the source language (most common translatedFrom target, or the sourceLanguage field in hreflang-map.json if present).

Phase 2: Completeness Audit

Show which translations are missing:

### Translation coverage matrix

| Post (EN) | DE | FR | ES | JA |
|-----------|----|----|----|----|
| how-to-avoid-ai-slop | ok | ok | missing | missing |
| content-marketing-2026 | ok | missing | ok | missing |

Coverage: 60% (6 of 10 expected translations present)
Missing: 4 translations needed

Phase 3: Content Parity Audit

For every post that exists in multiple languages:

CheckWhatSeverity
Section countSame number of H2 and H3 sectionsCritical
FAQ countSame number of FAQ itemsHigh
Image countSame number of imagesHigh
Chart countSame number of charts (SVG figures)High
Word count ratioWithin expected band for language pair (DE +20% to +30%, JA -20%, ES +10%)Medium
Link countSimilar internal and external link countsMedium
Evidence-backed claimsSame supported claims and citations across versionsMedium
Frontmatter parityAll required fields present per versionHigh

Flag every significant deviation as an issue.

Phase 4: SEO Parity Audit

For every language version verify:

ElementCheckSeverity
Title tagPresent, localized, clear, and appropriate for the pageCritical
Meta descriptionPresent, localized, accurate, and consistent with visible contentCritical
lang attribute or frontmatter langPresent, valid Google-compatible hreflang or BCP 47 language tagCritical
Canonical URLPoints to the same-language page, not the source-language page or x-defaultCritical
Schema inLanguageMatches langHigh
Schema translationOfWorkPoints to the source URLHigh
Alt textTranslated (no English alt in non-EN posts)High
SlugLocalized (no English slug in non-EN posts)Medium
TagsLocalizedMedium
KeywordsLocalizedMedium

Phase 5: Hreflang Audit

If hreflang-tags.html, hreflang-sitemap.xml, or hreflang-map.json exists in the directory:

CheckWhatSeverity
Self-referencingEach page references itselfCritical
Return tagsEvery relationship is bidirectionalCritical
Canonical consistencyEvery hreflang page canonicalizes to its same-language URLCritical
x-defaultPresent, points to the unmatched-language fallback such as a language selector or default market pageCritical
Language codesValid Google-compatible hreflang tags: ISO 639-1 language plus optional ISO 15924 script or ISO 3166-1 Alpha-2 regionHigh
URL consistencySame protocol, same trailing-slash conventionMedium
CompletenessEvery language version representedHigh

If no hreflang files exist, report it as a critical gap and offer: "Run /blog multilingual <topic> --languages ... to regenerate, or create hreflang-tags.html manually."

If seo-hreflang from claude-seo is installed, suggest running it for deeper validation.

Phase 6: Freshness Audit

For posts with translatedDate in frontmatter:

CheckWhatSeverity
Source updated after translationSource modified after translatedDateCritical
Source content driftStored source hash or source dateModified differs from current sourceCritical
Translation driftStored translation hash differs from current localized fileMedium
Translation older than 90 daysMay need refreshMedium
lastUpdated mismatch across versionsVersions out of syncMedium
Git or file mtime newer than translatedDateContent changed without frontmatter updateWarning

When available, store and compare sourceHash, source dateModified, translationHash, and Git mtime before relying only on translatedDate.

Emit actionable commands per stale file:

3 translations are stale:
- de/ki-trends-2026.md (source updated 2 days ago)
  -> Run: /blog translate en/ai-trends-2026.md --to de
- fr/ki-trends-2026.md (source updated 2 days ago)
  -> Run: /blog translate en/ai-trends-2026.md --to fr
- es/tendencias-ia-2026.md (translation > 90 days old)
  -> Run: /blog translate en/ai-trends-2026.md --to es

Phase 7: Report

Output as markdown by default. If the user passes --html, also write the report to locale-audit-report.html only inside the audited project root. Escape all dynamic filenames, titles, URLs, and issue text with html.escape(value, quote=True) before rendering HTML, and reject symlinked or outside-root report paths.

## Multilingual content audit report

### Summary
- Posts audited: [N] across [N] languages
- Overall health: [score] / 100
- Critical issues: [N]
- Warnings: [N]

### Translation coverage
[Matrix from Phase 2]

### Issues found
#### Critical
- [Issue with file references]

#### Warnings
- [Issue with file references]

#### Passed
- [Checks that passed]

### Prioritized fixes
1. [Highest-impact action]
2. [...]

### Stale-translation alerts
[Runnable commands from Phase 6]

### Quick fixes
- Run `/blog translate <file> --to <missing-langs>` for [N] missing translations.
- Run `/blog multilingual` to regenerate hreflang assets.
- Run `/blog localize <file> --locale <code>` for weak cultural adaptations.

Error Handling

ScenarioAction
Empty directory"No blog posts found in [path]"
Only one language presentReport coverage, suggest target languages
No hreflang filesFlag as critical gap, offer regeneration
Unrecognized file formatSkip with a warning

Cross-References

  • Fill missing translations: /blog translate <file> --to <missing-codes>
  • Deepen weak adaptations: /blog localize <file> --locale <code>
  • Regenerate hreflang assets: /blog multilingual <topic> --languages <codes>