CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

i18n-translate

Complete and maintain frontend i18n translations for this project. Covers finding missing translation keys, detecting untranslated entries, and adding translations for all supported locales (en, zh, zh-TW, fr, ja, ru, vi). Use for any task involving frontend locale files, missing translation keys, untranslated UI text, `t(...)` keys, `useTranslation()`, static i18n keys, button/label/ toast/dialog/placeholder/validation copy, or adding/fixing even a single i18n key. Use when review findings mention missing i18n, when new UI text needs translation, or when the user asks to add translations, fix i18n, or complete missing translations. Always load and follow this skill before translating, adding locale keys, or editing frontend i18n files.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

Highly actionable and operationally airtight content: complete executable tooling, a clear validated workflow, and thorough translation guidance. The weaknesses are repetition of the script-only mandate across multiple sections and the inlining of ~180 lines of utility scripts that would be better shipped as persistent bundle files.

Suggestions

Consolidate the 'never edit locale JSON directly, always use add-missing-keys.mjs' mandate into the single Hard Constraint section and reference it from the other sections instead of restating it six times.

Ship find-missing-keys.mjs, find-untranslated.mjs, and add-missing-keys.mjs as bundled scripts/ files so they persist and are simply invoked, rather than re-created inline on every run — this cuts SKILL.md to roughly a third.

Merge the Mandatory Preflight's source-text rules with the Translation Guidelines' Source Text Rules section to remove the duplicated guidance about not copying conversation text.

DimensionReasoningScore

Conciseness

The three script listings are lean and load-bearing, but the script-only mandate is restated roughly six times (Hard Constraint, Small Fix Path, Step 4, Key Rules), and the Preflight rules duplicate the later Source Text Rules. Mostly efficient, but clear tightening opportunities keep it at anchor 3 rather than 4.

3 / 5

Actionability

Fully executable guidance throughout: three complete copy-paste-ready scripts, exact commands ("cd web && bun run i18n:sync", "node scripts/add-missing-keys.mjs"), exact file paths, and a per-locale newKeys template covering all seven locales.

5 / 5

Workflow Clarity

Clear 5-step sequence (sync/report, find missing, find untranslated, add, verify) with an explicit validation checkpoint and feedback loop — "verify: should say 'All t() keys found'" — satisfying the batch-operation validation requirement.

5 / 5

Progressive Disclosure

No bundle files exist and section headers are clear, but ~180 lines of the body are three utility scripts the skill instructs to re-create each run ("Create and run `web/scripts/find-missing-keys.mjs`") — content that belongs in bundled scripts/ files is inlined, matching the 'could be better organized; content that should be separate is inline' anchor.

3 / 5

Total

16

/

20

Passed

Description

95%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 description: concrete capability list, explicit multi-clause 'Use when' triggers, and highly distinctive trigger terms covering both user phrasings and technical identifiers. Only minor gap is omitting the verification/sync maintenance actions from the capability list.

DimensionReasoningScore

Specificity

Lists three concrete actions ("finding missing translation keys, detecting untranslated entries, and adding translations for all supported locales (en, zh, zh-TW, fr, ja, ru, vi)") with an explicit locale list, matching the 'several specific actions; minor gaps' anchor — verification/sync maintenance actions are not mentioned, keeping it below the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' (complete and maintain frontend i18n translations; find missing keys, detect untranslated entries, add translations) and 'when' via multiple concrete 'Use for any task involving...' and 'Use when...' clauses with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms, API names, and file-level triggers: "frontend locale files, missing translation keys, untranslated UI text, `t(...)` keys, `useTranslation()`, static i18n keys, button/label/toast/dialog/placeholder/validation copy", plus user phrasings like "add translations, fix i18n, complete missing translations".

5 / 5

Distinctiveness Conflict Risk

Clear niche (frontend i18n locale files) with distinct triggers such as "`t(...)` keys", "`useTranslation()`", and specific locale file names; minimal overlap risk with generic translation or code-review skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository

langbot-app/langbot-new-api

Path

.agents/skills/i18n-translate/SKILL.md

Reviewed

Table of Contents

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.