blog-localize

Deep 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".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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.

The content is a well-structured, highly actionable five-phase workflow with strong validation and safety guidance. Its main weakness is progressive disclosure: it depends on an external cultural-adaptation reference file that is not bundled within the skill itself.

Suggestions

Bundle the cultural-adaptation profiles within this skill's own references/ directory (or duplicate the essential substitution tables inline) so the skill is self-contained rather than depending on ../blog-translate/references/cultural-adaptation.md.

Reduce redundancy between the Phase 2 cultural-audit table and the Phase 3f brand/legal quick-map table by merging or cross-referencing them to tighten token usage.

Add concrete command or code snippets for the WebSearch and page-fetch steps (e.g., an example fetch with the SSRF checks applied) to lift actionability from mostly-executable to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no padding about what localization or SSRF is), using compact tables and tight prose, but has minor redundancy between the cultural-audit table and the brand/legal quick-map tables that could be trimmed. Not a 5 because a few sections could be tightened further.	4 / 5
Actionability	Provides concrete substitution tables (Walmart -> MediaMarkt), specific legal mappings (CCPA -> DSGVO/RGPD/LGPD), a copy-paste summary template, and explicit error responses, but as an instruction-only skill it relies on WebSearch/fetch without exact command syntax, leaving minor gaps that keep it below a fully copy-paste-ready 5.	4 / 5
Workflow Clarity	A clear five-phase sequence includes explicit validation checkpoints: a dedicated Quality Verification checklist, input validation in Phase 1 (reject symlinks/traversal/oversize/binary), and destructive-operation guards in Phase 5 (backup before overwrite, path confinement), plus an error-handling table with recovery actions — matching the level-5 anchor with feedback loops.	5 / 5
Progressive Disclosure	The body is well-sectioned and points to a single clearly-signaled one-level reference (../blog-translate/references/cultural-adaptation.md), but no bundle directories (references/scripts/assets) are present in this skill and the referenced file lives in an external sibling skill not verifiable here, so the core profile data is externalized to a path the skill does not carry — leaving it below the well-structured level 4.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

The description is specific, complete, and well-triggered, naming concrete actions and providing explicit natural-language trigger phrases including multilingual synonyms. It clearly distinguishes itself from sibling translation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'swap brand examples, adapt CTAs, substitute legal references, localize statistic sources... and adjust formality' — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor rather than the minor-gaps level 4.	5 / 5
Completeness	Explicitly states both what it does ('Deep cultural adaptation of translated blog posts') and when to use it with concrete trigger phrases ('Use when user says...'), satisfying the level-5 anchor for both what and when.	5 / 5
Trigger Term Quality	Covers natural English phrases ('localize blog', 'blog localize', 'cultural adaptation', 'adapt for Germany') plus multilingual synonyms ('lokalisieren', 'localiser', 'adaptar'), matching the comprehensive synonym coverage expected at level 5.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cultural adaptation as a layer above translation) with market-specific profiles (DACH, Francophone, Hispanic, Japanese) and distinct triggers that are unlikely to fire for sibling translate/audit skills, matching the minimal-conflict-risk level 5.	5 / 5
	Total	20 / 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-localize/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.