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

94%

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

92%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, executable, concise multi-phase audit workflow with strong validation checkpoints and feedback loops. The main weakness is progressive disclosure: everything is inlined into SKILL.md with no bundle files or one-level-deep references to split out the report templates and severity matrices.

Suggestions

Move the full report template (Phase 7) and the per-phase severity matrices into a references/ file (e.g. REPORT_TEMPLATE.md) referenced one level deep, keeping only the Quick-start summary inline in SKILL.md.

Add a short '## References' or '## See also' section with clearly signaled links to any bundle files once they are created, so navigation is explicit rather than implicit.

Verify that cross-referenced commands (/blog translate, /blog localize, /blog multilingual) point to installed skills, or note them as optional dependencies to avoid dead-end guidance.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: severity tables and runnable command examples with no padding or explanation of concepts Claude already knows; the brief intro line is the only mild editorializing and earns its place.	5 / 5
Actionability	Fully executable guidance — concrete commands like '/blog translate en/ai-trends-2026.md --to de', html.escape(value, quote=True), exact report templates, and specific parity thresholds (DE +20% to +30%) cover the common cases.	5 / 5
Workflow Clarity	Clear 7-phase sequence with explicit validation checkpoints (Phase 1 rejects symlinked/traversal paths; Phase 7 escapes dynamic values and rejects outside-root report paths), an error-handling table, and stale-translation remediation commands forming a feedback loop.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent) and the ~190-line body is monolithic — full report templates and severity matrices are inlined rather than split into one-level-deep referenced files, so structure is present but content that should be separate is inline.	3 / 5
	Total	18 / 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, specific description with explicit what/when structure and comprehensive natural triggers including a German variant. Slight overlap risk with sibling blog translation skills keeps distinctiveness just below the top anchor.

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' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (audit/coverage matrix/hreflang/schema validation/report) and when via a clear 'Use when user says...' clause.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and a non-English variant: 'locale audit', 'check translations', 'multilingual audit', 'translation check', 'hreflang check', and 'Uebersetzungen pruefen'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (multilingual blog hreflang/parity audits) with distinct triggers, but minor overlap risk with the explicitly cross-referenced blog-translate/blog-localize/blog-multilingual skills; not a 5 because the domain touches several sibling skills.	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: brain/.raw/sources/claude-blog-skill/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.