What does this skill do, and when should you use it?
Blog Locale Audit is the multilingual quality-control skill in the claude-blog suite. It scans a content directory, builds a language coverage matrix, and checks translation completeness, structural parity, metadata, schema, hreflang, and freshness. The skill produces prioritized findings and runnable fix commands. It is a good fit for teams or individuals maintaining multilingual blog files before publication.
Reads language subdirectories, article frontmatter, and optional hreflang-map.json, hreflang-tags.html, or hreflang-sitemap.xml files; identifies the source language and builds a post-by-language coverage matrix; compares headings, FAQs, images, charts, word counts, links, citation capsules, and frontmatter across language versions; checks titles, meta descriptions, lang values, schema fields, translation references, alt text, slugs, tags, and keywords; validates hreflang self-references, return tags, x-default, language codes, URL consistency, and language coverage; detects stale translations using translatedDate, lastUpdated, and file modification times; emits a Markdown report by default and additionally writes locale-audit-report.html when --html is supplied.
- A multilingual editorial team wants to find missing DE, FR, ES, or JA versions before publishing a content batch.
- An international SEO editor needs to verify lang values, schema, and hreflang relationships across localized pages.
- A marketing team wants to identify translations that predate recent source updates or have passed the 90-day freshness threshold.
- A static-blog maintainer wants a directory-level report when hreflang assets are missing or incomplete.
How do you install this skill?
- The advertised runnable fix commands invoke other blog skills, but confirmation, change scope, and rollback are unspecified.
- Hreflang, schema, file-mtime, and language-pair word-ratio rules lack implementation or test evidence and may produce false positives.
- Chinese language codes, Simplified/Traditional Chinese variation, regional variants, and mainland-China offline degradation are undefined.
- Do not treat the example translation ratios or SEO length thresholds as empirically validated standards.
- Local filesystem
Install the public claude-blog plugin collection:
/plugin marketplace add AgriciDaniel/claude-blog/plugin install claude-blog@agricidaniel-claude-blog- Restart Claude Code.
The skill is bundled at skills/blog-locale-audit/SKILL.md. The source does not document a standalone installation procedure for this sub-skill.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/AgriciDaniel/claude-blog.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/blog-locale-audit" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Invoke it in Claude Code with a request such as “locale audit,” or use /blog locale-audit <directory>, where <directory> is the multilingual blog content directory. Example: /blog locale-audit content/blog. Pass --html if an HTML report is wanted; the source does not provide a complete command example for that option.
What are this skill's strengths and limitations?
- Covers translation completeness, content parity, SEO metadata, schema, hreflang, and freshness in one audit.
- Produces a coverage matrix, severity-ranked issues, prioritized fixes, and commands for stale files.
- Clearly reports a critical gap when hreflang assets are absent and offers regeneration guidance.
- Runs standalone within claude-blog, with optional deeper hreflang validation through claude-seo seo-hreflang.
- Depends on recognizable directory layouts, frontmatter, and date fields; unrecognized formats are skipped with a warning.
- The source provides no independent test count or platform-specific validation for this sub-skill.
- Some recommended remediation relies on sibling claude-blog commands such as translate, localize, or multilingual, which are outside this skill’s own scope.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Blog Locale Audit this page | 50 · Use with care | ★ 2.4k | 14d ago | MIT |
| Multilingual Blog Publisher | 55 · Use with care | ★ 2.4k | 14d ago | MIT |
| SEO Audit (Basic) Skill | 57 · Use with care | ★ 765 | 4mo ago | MIT |
| llms.txt Analysis & Generation Skill | 46 · Use with care | ★ 11k | 22d ago | MIT |
| International SEO Hreflang Auditor | 51 · Use with care | ★ 19k | 23d ago | MIT |
How did FollowSkills review this skill?
The skill limits itself to scanning a target directory and producing an audit report, with no declared credential access or publishing action, and it identifies the optional SEO dependency. However, least-privilege boundaries, user confirmation, sensitive-data handling, write scope, rollback, and data-flow disclosure are incomplete, so points are deducted.
The workflow covers discovery, completeness, content, SEO, hreflang, freshness, and several error cases, with some textual failure feedback. However, there is no skill-specific script, input contract, edge-case test coverage, or detailed diagnosable exception behavior; the static ceiling therefore applies.
The audience, directory input, and trigger phrases are reasonably clear for multilingual blog QA. However, non-fit boundaries, language-detection limits, locale-specific variation, Chinese-language support, and mainland-China reachability of any external dependency are not defined, so points are deducted.
The skill has structured frontmatter, an MIT license, version and author metadata, an argument hint, staged documentation, examples, error handling, and cross-references. It lacks skill-specific changelog details, explicit maintenance ownership, and a direct update path; installation and dependency guidance mainly comes from repository context, so it is not full marks.
The skill specifies useful outputs: a coverage matrix, prioritized findings, stale-translation alerts, and runnable remediation commands, making the core task plausible. However, language-pair thresholds and other rules are unverified assumptions, and skill-specific evidence does not prove report correctness or direct usability; the static ceiling limits this to7.
The file supplies detailed checks, examples, and auditable rules, while repository context claims CI and tests. The supplied tests mainly cover unrelated scripts and the delivery contract, not the blog-locale-audit key paths, and static review cannot confirm the examples or external commands, so points are deducted.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →