New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Audit a directory of multilingual blog content

Blog Locale Audit, Multilingual Quality Control

by AgriciDaniel · MIT license · ★ 2,219 on GitHub · updated Sep 18

Blog Locale Audit, Multilingual Quality Control cover

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…

---
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

Overview

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.

Manual install (npx, ZIP)
Claude Codenpx skills add AgriciDaniel/claude-blog --skill blog-locale-audit -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/AgriciDaniel/claude-blog/tar.gz/2500d4c76503 \ | tar -xz -C ~/.claude/skills --strip-components=2 claude-blog-2500d4c76503/skills/blog-locale-audit
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/1cd6ab250c2c6da531b5/blog-locale-audit.zip" -OutFile "$env:TEMP\blog-locale-audit.zip"; Expand-Archive "$env:TEMP\blog-locale-audit.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md8.1 KB
Read the files here
AgriciDaniel/2500d4c1 file
SKILL.md
Show the full text211 lines

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:

Check What Severity
Section count Same number of H2 and H3 sections Critical
FAQ count Same number of FAQ items High
Image count Same number of images High
Chart count Same number of charts (SVG figures) High
Word count ratio Within expected band for language pair (DE +20% to +30%, JA -20%, ES +10%) Medium
Link count Similar internal and external link counts Medium
Evidence-backed claims Same supported claims and citations across versions Medium
Frontmatter parity All required fields present per version High

Flag every significant deviation as an issue.

Phase 4: SEO Parity Audit

For every language version verify:

Element Check Severity
Title tag Present, localized, clear, and appropriate for the page Critical
Meta description Present, localized, accurate, and consistent with visible content Critical
lang attribute or frontmatter lang Present, valid Google-compatible hreflang or BCP 47 language tag Critical
Canonical URL Points to the same-language page, not the source-language page or x-default Critical
Schema inLanguage Matches lang High
Schema translationOfWork Points to the source URL High
Alt text Translated (no English alt in non-EN posts) High
Slug Localized (no English slug in non-EN posts) Medium
Tags Localized Medium
Keywords Localized Medium
Phase 5: Hreflang Audit

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

Check What Severity
Self-referencing Each page references itself Critical
Return tags Every relationship is bidirectional Critical
Canonical consistency Every hreflang page canonicalizes to its same-language URL Critical
x-default Present, points to the unmatched-language fallback such as a language selector or default market page Critical
Language codes Valid Google-compatible hreflang tags: ISO 639-1 language plus optional ISO 15924 script or ISO 3166-1 Alpha-2 region High
URL consistency Same protocol, same trailing-slash convention Medium
Completeness Every language version represented High

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:

Check What Severity
Source updated after translation Source modified after translatedDate Critical
Source content drift Stored source hash or source dateModified differs from current source Critical
Translation drift Stored translation hash differs from current localized file Medium
Translation older than 90 days May need refresh Medium
lastUpdated mismatch across versions Versions out of sync Medium
Git or file mtime newer than translatedDate Content changed without frontmatter update Warning

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

Scenario Action
Empty directory "No blog posts found in [path]"
Only one language present Report coverage, suggest target languages
No hreflang files Flag as critical gap, offer regeneration
Unrecognized file format Skip 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>
1---
2name: blog-locale-audit
3description: >
4 Audit a directory of multilingual blog content for completeness, consistency,
5 hreflang correctness, meta-tag parity, and freshness. Builds a translation
6 coverage matrix, flags stale translations, validates hreflang and schema,
7 and emits a prioritized report with runnable fix commands.
8 Use when user says "locale audit", "blog locale-audit", "check translations",
9 "multilingual audit", "translation check", "hreflang check",
10 "Uebersetzungen pruefen".
11user-invokable: true
12argument-hint: "<directory>"
13license: MIT
14compatibility: Standalone within claude-blog. Optional richer hreflang validation via claude-seo seo-hreflang.
15metadata:
16 author: AgriciDaniel
17 version: "2.2.0"
18 category: blog
19---
20 
21# Blog Locale Audit, Multilingual Quality Control
22 
23Audits a directory of multilingual blog content to ensure every language
24version is complete, consistent, correctly tagged, and SEO-optimized.
25Catches international content issues before they hurt rankings.
26 
27> Adapted from `claude-blog-multilingual` by Chris Mueller (Pro Hub Challenge,
28> March 2026). Original: https://github.com/Chriss54/multilingual-int
29 
30## Workflow
31 
32### Phase 1: Discovery
33 
341. Resolve the target directory inside the project root/current working
35 directory. Reject symlinked directories and traversal outside the root,
36 then scan blog content and group posts by language using:
37 - Subdirectory names (`en/`, `de/`, `fr/`).
38 - Frontmatter `lang` and `translatedFrom` fields.
39 - `hreflang-map.json` if present.
402. Normalize detected language codes with the shared multilingual locale rules
41 used by `blog-translate`, `blog-localize`, and `blog-multilingual`: ISO
42 639-1 language in lowercase, optional ISO 15924 script in title case,
43 optional ISO 3166-1 Alpha-2 region in uppercase. Flag ambiguous
44 language-only codes such as `es`, `pt`, and `zh` unless the content
45 declares an explicit neutral mode.
463. Build a content matrix mapping which post exists in which languages. Use a
47 stable translation-group key before comparing slugs: `translationGroupId`,
48 `sourceSlug`, schema `translationOfWork.url`, or the IDs and URLs in
49 `hreflang-map.json`. Fall back to normalized source slug only when no
50 stable key exists.
514. Detect the source language (most common `translatedFrom` target, or the
52 `sourceLanguage` field in `hreflang-map.json` if present).
53 
54### Phase 2: Completeness Audit
55 
56Show which translations are missing:
57 
58```
59### Translation coverage matrix
60 
61| Post (EN) | DE | FR | ES | JA |
62|-----------|----|----|----|----|
63| how-to-avoid-ai-slop | ok | ok | missing | missing |
64| content-marketing-2026 | ok | missing | ok | missing |
65 
66Coverage: 60% (6 of 10 expected translations present)
67Missing: 4 translations needed
68```
69 
70### Phase 3: Content Parity Audit
71 
72For every post that exists in multiple languages:
73 
74| Check | What | Severity |
75|-------|------|----------|
76| Section count | Same number of H2 and H3 sections | Critical |
77| FAQ count | Same number of FAQ items | High |
78| Image count | Same number of images | High |
79| Chart count | Same number of charts (SVG figures) | High |
80| Word count ratio | Within expected band for language pair (DE +20% to +30%, JA -20%, ES +10%) | Medium |
81| Link count | Similar internal and external link counts | Medium |
82| Evidence-backed claims | Same supported claims and citations across versions | Medium |
83| Frontmatter parity | All required fields present per version | High |
84 
85Flag every significant deviation as an issue.
86 
87### Phase 4: SEO Parity Audit
88 
89For every language version verify:
90 
91| Element | Check | Severity |
92|---------|-------|----------|
93| Title tag | Present, localized, clear, and appropriate for the page | Critical |
94| Meta description | Present, localized, accurate, and consistent with visible content | Critical |
95| `lang` attribute or frontmatter `lang` | Present, valid Google-compatible hreflang or BCP 47 language tag | Critical |
96| Canonical URL | Points to the same-language page, not the source-language page or x-default | Critical |
97| Schema `inLanguage` | Matches `lang` | High |
98| Schema `translationOfWork` | Points to the source URL | High |
99| Alt text | Translated (no English alt in non-EN posts) | High |
100| Slug | Localized (no English slug in non-EN posts) | Medium |
101| Tags | Localized | Medium |
102| Keywords | Localized | Medium |
103 
104### Phase 5: Hreflang Audit
105 
106If `hreflang-tags.html`, `hreflang-sitemap.xml`, or `hreflang-map.json`
107exists in the directory:
108 
109| Check | What | Severity |
110|-------|------|----------|
111| Self-referencing | Each page references itself | Critical |
112| Return tags | Every relationship is bidirectional | Critical |
113| Canonical consistency | Every hreflang page canonicalizes to its same-language URL | Critical |
114| `x-default` | Present, points to the unmatched-language fallback such as a language selector or default market page | Critical |
115| Language codes | Valid Google-compatible hreflang tags: ISO 639-1 language plus optional ISO 15924 script or ISO 3166-1 Alpha-2 region | High |
116| URL consistency | Same protocol, same trailing-slash convention | Medium |
117| Completeness | Every language version represented | High |
118 
119If no hreflang files exist, report it as a critical gap and offer:
120"Run `/blog multilingual <topic> --languages ...` to regenerate, or create
121hreflang-tags.html manually."
122 
123If `seo-hreflang` from claude-seo is installed, suggest running it for
124deeper validation.
125 
126### Phase 6: Freshness Audit
127 
128For posts with `translatedDate` in frontmatter:
129 
130| Check | What | Severity |
131|-------|------|----------|
132| Source updated after translation | Source modified after `translatedDate` | Critical |
133| Source content drift | Stored source hash or source `dateModified` differs from current source | Critical |
134| Translation drift | Stored translation hash differs from current localized file | Medium |
135| Translation older than 90 days | May need refresh | Medium |
136| `lastUpdated` mismatch across versions | Versions out of sync | Medium |
137| Git or file mtime newer than `translatedDate` | Content changed without frontmatter update | Warning |
138 
139When available, store and compare `sourceHash`, source `dateModified`,
140`translationHash`, and Git mtime before relying only on `translatedDate`.
141 
142Emit actionable commands per stale file:
143 
144```
1453 translations are stale:
146- de/ki-trends-2026.md (source updated 2 days ago)
147 -> Run: /blog translate en/ai-trends-2026.md --to de
148- fr/ki-trends-2026.md (source updated 2 days ago)
149 -> Run: /blog translate en/ai-trends-2026.md --to fr
150- es/tendencias-ia-2026.md (translation > 90 days old)
151 -> Run: /blog translate en/ai-trends-2026.md --to es
152```
153 
154### Phase 7: Report
155 
156Output as markdown by default. If the user passes `--html`, also write the
157report to `locale-audit-report.html` only inside the audited project root.
158Escape all dynamic filenames, titles, URLs, and issue text with
159`html.escape(value, quote=True)` before rendering HTML, and reject symlinked
160or outside-root report paths.
161 
162```
163## Multilingual content audit report
164 
165### Summary
166- Posts audited: [N] across [N] languages
167- Overall health: [score] / 100
168- Critical issues: [N]
169- Warnings: [N]
170 
171### Translation coverage
172[Matrix from Phase 2]
173 
174### Issues found
175#### Critical
176- [Issue with file references]
177 
178#### Warnings
179- [Issue with file references]
180 
181#### Passed
182- [Checks that passed]
183 
184### Prioritized fixes
1851. [Highest-impact action]
1862. [...]
187 
188### Stale-translation alerts
189[Runnable commands from Phase 6]
190 
191### Quick fixes
192- Run `/blog translate <file> --to <missing-langs>` for [N] missing translations.
193- Run `/blog multilingual` to regenerate hreflang assets.
194- Run `/blog localize <file> --locale <code>` for weak cultural adaptations.
195```
196 
197## Error Handling
198 
199| Scenario | Action |
200|----------|--------|
201| Empty directory | "No blog posts found in [path]" |
202| Only one language present | Report coverage, suggest target languages |
203| No hreflang files | Flag as critical gap, offer regeneration |
204| Unrecognized file format | Skip with a warning |
205 
206## Cross-References
207 
208- Fill missing translations: `/blog translate <file> --to <missing-codes>`
209- Deepen weak adaptations: `/blog localize <file> --locale <code>`
210- Regenerate hreflang assets: `/blog multilingual <topic> --languages <codes>`
211 
View all files on GitHub →

Details

Updated
Sep 18, 2026
License
MIT
Stars on the repo
★ 2,219
Checked
Source
AgriciDaniel/claude-blog ↗
Creator
AgriciDaniel · 130 listings
View creator

Made with blog-locale-audit

Blog Locale Audit, Multilingual Quality Control — claude-blog /blog write demo: end-to-end article generation with the 5-gate Delivery Contract (from the AgriciDaniel/claude-blog README)
Blog Locale Audit, Multilingual Quality Control — claude-blog /blog write demo: end-to-end article generation with the 5-gate Delivery Contract (from the AgriciDaniel/claude-blog README)

by AgriciDaniel

Similar skills

See all →
SkillTranslate books into any language using parallel sub-agentsBook Translation Skilldeusyu/translate-book · by deusyuTranslate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.★ 2.1k GitHub starsSkillMarketing copy localization skill that converts EnglishArabic Copy Localizer — Claude Skillgrowthack88/growth-marketing-os · by growthack88Marketing copy localization skill that converts English marketing copy (ads, landing pages, emails, CTAs) into native Egyptian Arabic عامية — or GCC dialect on request — with natural English code-switching for business terms. Use whenever marketing copy needs an Arabic version, an Arabic draft "sounds translated", or a bilingual campaign is being built. Rebuilds meaning per line instead of translating words; never outputs فصحى for performance marketing contexts.★ 117 GitHub starsPromptTranslate text from Chinese to EnglishChinese to english translation assistantf/prompts.chat · by BruceTranslate text from Chinese to English, ensuring accurate and contextually appropriate translations.New listingSkillTranslate, 翻译, 精翻, translate article, translate to ChineseTranslatorJimLiu/baoyu-skills · by JimLiuThis skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", localize", "本地化", "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", 这篇文章翻译一下", or provides a URL/file with translation intent. Supports three modes (quick/normal/refined) with custom glossary support.★ 26.6k GitHub starsMCPYou need to translate a DESIGN.mdDesign bridgeVoltAgent/awesome-claude-code-subagents · by VoltAgentUse this agent when you need to translate a DESIGN.md from the VoltAgent/awesome-design-md repository into polished Claude Code instructions for building user interfaces that faithfully match the chosen brand. Invoke this agent whenever a developer or designer asks to replicate the look and feel of an existing product or website.★ 25.2k GitHub starsSkillDeep cultural adaptation of translated blog postsBlog Localize, Cultural Deep-AdaptationAgriciDaniel/claude-blog · by AgriciDanielDeep cultural adaptation of translated blog posts. Run after blog-translate completes. Goes beyond translation to swap brand examples, adapt CTAs, substitute legal references, localize statistic sources where possible, and adjust formality (Sie/du, tu/vous, formal/informal). Built-in profiles for DACH, Francophone, Hispanic, and Japanese markets. Use when user says "localize blog", "blog localize", "cultural adaptation", adapt for Germany", "lokalisieren", "localiser", "adaptar".★ 2.2k GitHub stars

More from AgriciDaniel

SkillThe Lighthouse Agentic Browsing fractionAgentic Browsing ReadinessAgriciDaniel/claude-seo · by AgriciDanielAudit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).★ 17.4k GitHub starsSkillOptimize content for AI Overviews , ChatGPT web searchAI Search / GEO Optimization (May 2026)AgriciDaniel/claude-seo · by AgriciDanielOptimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", ChatGPT search", or "AI visibility".★ 17.4k GitHub starsSkillReferring domains, anchor text distributionBacklink Profile AnalysisAgriciDaniel/claude-seo · by AgriciDanielBacklink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and DataForSEO extension. Use when user says backlinks, link profile, referring domains, anchor text, toxic links, link gap, link building, disavow, or backlink audit.★ 17.4k GitHub starsSkillYou share your Amazon advertising numbers and goals; you getAmazon Ads AuditAgriciDaniel/claude-ads · by AgriciDanielYou share your Amazon advertising numbers and goals; you get back a plain-language review of what's draining your budget and what to change first.★ 9.5k GitHub starsSkillPaste what you're spending on Apple Search AdsApple Ads AuditAgriciDaniel/claude-ads · by AgriciDanielPaste what you're spending on Apple Search Ads and your recent numbers; get back a plain review of what's wasting money and what to fix first.★ 9.5k GitHub starsSkillPaste the sales and spend numbers each ad platform claimsAttribution AuditAgriciDaniel/claude-ads · by AgriciDanielPaste the sales and spend numbers each ad platform claims, and get back a plain explanation of why they disagree and which figure to trust.★ 9.5k GitHub stars