localize

Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/localize/SKILL.md

Quality

Content

77%

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

The body is highly actionable with clear, validated workflows across all ten modes, but it is a long monolithic document whose template content could be split into reference files and whose prose intro adds some unnecessary framing.

Suggestions

Externalize the large output templates (translator brief, VO recording script, QA verdict, cultural-review table) into reference files under references/ and link to them one level deep.

Trim the conceptual intro paragraph and the repeated "Ask: May I write..." preamble to recover tokens.

Keep the operational checklists and grep patterns inline since they drive execution.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational (file paths, grep patterns, output templates), but the opening framing paragraph ("Localization is not just translation..."), repeated "Ask: May I write..." boilerplate, and some conceptual prose could be tightened; it is not a clean score-3 lean document and not verbose enough to drop to 1.	2 / 3
Actionability	Provides concrete, executable guidance throughout — exact paths ("assets/data/strings/", "assets/audio/vo/[locale]/"), key-naming conventions, grep patterns, full markdown output templates, and specific AskUserQuestion prompts with defined options — matching the fully-executable anchor.	3 / 3
Workflow Clarity	Each mode is clearly sequenced with explicit validation checkpoints (pre-freeze checklist, validate mode, QA PASS/FAIL gate), feedback loops (validate→fix, freeze-violation warnings), and a Recommended Workflow ordering the modes, satisfying the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Well-organized with per-mode headers, but it is a single ~440-line monolithic file with no bundle files and large inline templates (translator brief, VO script, QA verdict) that could be externalized into one-level-deep references; since it is well over 50 lines, organized sections alone do not reach 3.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and distinctive, naming a comprehensive set of localization actions, but it omits an explicit "Use when..." trigger clause and lacks some natural user phrasings, which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when localizing a game, translating UI/dialogue/VO, or preparing multi-locale release and certification."

Include common natural variations users would say ("translate", "localize", "i18n", "l10n") to improve trigger-term coverage.

Consider trimming the long action list slightly so the description reads as triggers rather than a feature inventory.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage" — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Strongly answers "what" with a long action list, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ("localization", "translations", "hardcoded strings") but leans on process jargon (VO, RTL, string freeze) and omits common variations a user would say ("translate", "localize", "i18n", "l10n"), so it lands at the some-keywords-but-missing-variations anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It carves a clear, narrow niche (game localization pipeline) with distinctive triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 9 missing, 9 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/localize/SKILL.md
Commit: 984023d

Reviewed: 3 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.