localize

Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.

Quality

76%

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

70%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 highly actionable, well-sequenced pipeline skill with strong validation checkpoints and verdict logic, but it is a monolithic single file with inlined per-mode detail that belongs in reference files, plus a padded motivational intro that wastes tokens.

Suggestions

Move mode-specific depth into one-level-deep reference files (e.g. references/cultural-review.md, references/vo-pipeline.md, references/translator-brief-template.md) and keep SKILL.md as the overview with mode summaries.

Delete or compress the motivational intro paragraph and the embedded meta-commentary blocks; keep only the operational rule each one encodes.

Replace named-but-unstated grep targets ('Engine-specific RTL flags in scene/prefab files') with literal search patterns so scan/RTL modes are fully executable.

Dimension	Reasoning	Score
Conciseness	The bulk is tight operational guidance, but there is real padding: the intro ('Localization is not just translation... Poor localization breaks immersion, confuses players, and blocks platform certification') is motivational filler Claude doesn't need, and the embedded meta-commentary blocks in status/QA modes are wordy. Fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4, which requires only minor trimming — several sections could lose a paragraph.	3 / 5
Actionability	Concrete, executable guidance throughout: exact file paths ('assets/data/strings/strings-en.json'), key-naming convention with examples ('ui.hud.health_label'), copy-paste 'May I write...' approval prompts, a full freeze-status file template, and table formats for every report. Not 5: some endpoints stay high-level ('Report findings', 'Grep patterns to check: Engine-specific RTL flags' names patterns rather than giving literal regexes), leaving minor execution gaps.	4 / 5
Workflow Clarity	Every mode is a clearly sequenced process with explicit validation checkpoints: the pre-freeze checklist, validate mode, the first-match-wins QA verdict logic with defined precedence (FAIL > NOT ASSESSED > PASS WITH CONDITIONS > PASS), and approval gates before every write. The recommended workflow section orders the whole pipeline. This matches the top anchor: clear sequence, explicit validation, error-recovery/feedback logic, and checklists.	5 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and the skill is a single ~450-line file. Internal section structure is good (one section per mode), but content that clearly belongs in separate reference files — the cultural-review checklists, the VO pipeline, the translator-brief template — is all inlined. Fits 'some structure but... content that should be separate is inline'; not 2 because section headers and navigation within the file are clear, not minimal.	3 / 5
	Total	15 / 20 Passed

Description

75%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 specific, well-scoped description with strong trigger vocabulary and low conflict risk, weakened by a missing 'Use when...' trigger clause and absent common synonyms like 'translation' or 'l10n' that users would naturally say.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions localization, translation, l10n, hardcoded strings, string freeze, or shipping the game in additional locales.'

Add common synonyms users actually say — 'translation', 'translate strings', 'localisation', 'l10n' — to broaden natural trigger coverage without inflating the description.

Dimension	Reasoning	Score
Specificity	The description lists six concrete actions — 'find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze' — which comprehensively covers the localization pipeline domain. Not below 4, because coverage is comprehensive rather than having minor gaps; each named action maps to a real skill mode.	5 / 5
Completeness	Has a clear 'what' (the pipeline and its concrete actions) but no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guideline, a missing explicit 'when' caps completeness at 3; it is not 4 because 'when' is entirely absent, not merely implicit.	3 / 5
Trigger Term Quality	Good natural keywords: 'localization', 'hardcoded strings', 'string tables', 'string freeze', 'cultural review'. However, common user phrasings like 'translation', 'translate strings', 'l10n', 'localise', or 'internationalization' are absent — most users say 'translate the game' before 'localization pipeline'. Fits 'good keyword coverage; a few natural terms missing', not 5 (which requires synonyms/extensions like 'PDFs, PDF, .pdf').	4 / 5
Distinctiveness Conflict Risk	'Localization pipeline' with terms like 'string freeze', 'RTL', 'VO', and 'string tables' carves out a clear niche (game localization) with triggers unlikely to fire for other skills. No neighboring anchor fits better — it is not merely 'mostly distinct'; the trigger vocabulary is unique to this domain.	5 / 5
	Total	17 / 20 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: 10 missing, 10 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/localize/SKILL.md
Commit: b21fa0f

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.