CtrlK
BlogDocsLog inGet started
Tessl Logo

translate-docs

Translate and sync bilingual user documentation between docs/zh/ and docs/en/ following the source-of-truth rules in docs/AGENTS.md.

58

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/translate-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, well-structured instruction skill with concrete commands, explicit prerequisites, and a clear four-step workflow ending in verification. Its main weaknesses are a redundant paragraph that restates the locale-sync rules and the absence of an explicit fix-and-re-verify feedback loop for the batch translation workflow.

Suggestions

Delete the redundant paragraph after the locale-sync bullets ('When non-changelog pages change in either locale... sync the Chinese changelog.') since it fully restates the preceding rules.

Add an explicit feedback loop to the Verify step, e.g. 'If the diff shows terminology drift or punctuation regressions, fix the source locale first, re-sync the mirror, and re-run the diff.'

Consolidate overlapping items between 'Rules and conventions' and 'Common mistakes' (e.g. the one-sided-fix and placeholder rules appear in both) into one section.

DimensionReasoningScore

Conciseness

The body is dense and efficient — concrete commands, exact punctuation characters, and placeholder values with no concept explanations Claude already knows. A trimmable redundancy exists: the paragraph 'When non-changelog pages change in either locale, sync the mirror before release. When the English changelog changes, sync the Chinese changelog.' restates the preceding bullets, and 'Common mistakes' overlaps 'Rules and conventions'. That minor over-explanation fits anchor 4 rather than anchor 5's 'every token earns its place'.

4 / 5

Actionability

Guidance is mostly executable: 'git diff main..HEAD --stat docs/', 'pnpm --filter docs run build', exact full-width punctuation lists, specific callout labels, and neutral placeholders (example.com, YOUR_API_KEY). Minor gaps remain — no example of locating a mirror path or a before/after translation snippet, and the term table itself is delegated to an external file — so it fits anchor 4 ('mostly executable guidance... minor gaps') rather than anchor 5.

4 / 5

Workflow Clarity

The four-step workflow (detect what needs syncing → translate page by page → apply terminology/typography rules → verify) is clearly sequenced, with a prerequisites gate and a verify step ('git diff docs/' scan plus docs build). However, there is no explicit feedback loop for error recovery (e.g. 'if drift is found, fix and re-verify') for what is a batch, page-by-page operation, which keeps it at anchor 4's 'most checkpoints present; minor validation gaps' rather than anchor 5.

4 / 5

Progressive Disclosure

The single-file body is well organized into Overview, Prerequisites, Locale sync rules, Workflow, Rules and conventions, and Common mistakes, and all detailed terminology/typography material is appropriately delegated one level deep to the clearly and repeatedly signaled docs/AGENTS.md rather than inlined. No bundle files exist to require further splitting, and nothing that belongs in a separate file is inlined — matching the well-organized single-file case for anchor 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 about the domain and repository paths and clearly states what the skill does, but it omits any 'when to use' trigger guidance and misses natural synonyms like 'Chinese', 'English', and 'localization'. These gaps leave the trigger-related dimensions at the midpoint despite otherwise concrete wording.

Suggestions

Add an explicit trigger clause, e.g. 'Use when either locale under docs/zh/ or docs/en/ changes, or when the user asks to translate or sync Chinese/English documentation.'

Include natural synonyms and file terms users would say — 'Chinese', 'English', 'localization', 'i18n' — to improve trigger term coverage.

Mention one or two additional concrete actions (e.g. verifying terminology against the term table, running the docs build) to raise specificity beyond two actions.

DimensionReasoningScore

Specificity

The description names the domain (bilingual documentation between docs/zh/ and docs/en/) and exactly two concrete actions ('Translate and sync'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not list further actions such as terminology verification or mirror syncing scope, so it does not reach anchor 4.

3 / 5

Completeness

The 'what' is clear (translate and sync bilingual docs between the two locale directories), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is at best weakly implied by the reference to source-of-truth rules.

3 / 5

Trigger Term Quality

Relevant keywords are present ('Translate', 'sync', 'bilingual', 'documentation', 'docs/zh/', 'docs/en/'), but common variations users would naturally say are missing — notably 'Chinese', 'English', 'localization', or 'i18n'. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms') and falls short of anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The bilingual zh/en documentation sync niche with repo-specific paths (docs/AGENTS.md, docs/zh/, docs/en/) is mostly distinct with only minor overlap risk against generic translation requests. It lacks the explicit 'Use when...' trigger phrases that anchor 5's example includes, so it fits anchor 4 rather than 5; it is far more specific than anchor 3's generic 'works with document files'.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MoonshotAI/kimi-code
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.