blog-locale-audit

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".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable audit playbook with clear phased sequencing, severity-rated checks, runnable fix commands, and explicit error handling. It is concise and free of over-explanation; the main gap is the absence of an explicit validate-retry feedback loop for batch fix operations and no bundle files to externalize the long criteria tables.

Suggestions

Add an explicit validate->fix->retry feedback loop for batch fix commands so Claude re-checks coverage/hreflang after applying '/blog translate' fixes.

Move the detailed parity and hreflang criteria tables into a references/ file (e.g. CHECKS.md) and summarize the key checks inline to reduce body length and improve progressive disclosure.

Make the Phase 7 report section a concrete, copy-pasteable template with literal placeholders rather than bracketed prose hints.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable checklists and severity tables rather than padded prose, and avoids explaining concepts Claude already knows; minor tightening possible in the Phase descriptions and report template, but it is largely efficient.	4 / 5
Actionability	Provides concrete runnable commands (e.g. '/blog translate en/ai-trends-2026.md --to de') and exact severity/severity-band thresholds plus specific frontmatter fields to inspect; some checks remain descriptive rather than giving the literal command to run, leaving minor gaps.	4 / 5
Workflow Clarity	Seven numbered phases give a clear sequence with explicit severity ratings and an error-handling table; validation/checkpoints are present (reject symlinks, html.escape, report only inside root) but the destructive/batch feedback loop is implicit rather than a validate->fix->retry cycle.	4 / 5
Progressive Disclosure	Well-organized into phase sections with cross-references to sibling skills (/blog translate, /blog localize, /blog multilingual) at one level deep; no bundle files exist to offload the detailed checklists, so the criteria tables are inlined where a reference file could carry them.	4 / 5
	Total	16 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs concrete audit actions with an explicit 'Use when' trigger list including multilingual synonyms. It is specific and complete, with only minor overlap risk against sibling localization skills.

Suggestions

Add a distinguishing qualifier to the 'multilingual audit' and 'translation check' triggers (e.g. 'blog multilingual audit') to reduce overlap with general translation skills.

Consider mentioning the directory/argument scope in the description body so the trigger ties directly to the '<directory>' argument-hint.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Builds a translation coverage matrix, flags stale translations, validates hreflang and schema, and emits a prioritized report with runnable fix commands' — covering the full audit workflow comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (audit completeness, consistency, hreflang, meta-tag parity, freshness) and 'when' via a concrete 'Use when...' clause with named trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including 'locale audit', 'blog locale-audit', 'check translations', 'multilingual audit', 'translation check', 'hreflang check', plus a non-English variant ('Uebersetzungen pruefen'), matching how a user would actually phrase the request.	5 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct (multilingual blog auditing with hreflang), but terms like 'multilingual audit' and 'translation check' could overlap with general translation/localization skills; minor overlap risk rather than fully isolated triggers.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: skills/blog-locale-audit/SKILL.md
Commit: 84f7abf

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.