CtrlK
BlogDocsLog inGet started
Tessl Logo

baoyu-translate

This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", "这篇文章翻译一下", or provides a URL/file with translation intent. Supports three modes (quick/normal/refined) with custom glossary support.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-structured, action-oriented skill body with excellent progressive disclosure and concrete commands. Its main weakness is the missing validation checkpoint after the batch chunk-merge step, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after the chunked subagent merge (Step 3.1.6): verify all chunks merged in correct order and terminology is consistent with the shared 02-prompt.md glossary before proceeding to review/polish.

Provide at least one fully resolved example invocation of the chunk script (e.g., `bun scripts/main.ts article.md --max-words 5000 --output-dir article-zh-CN/`) so the CLI guidance is copy-paste ready rather than requiring {baseDir}/${BUN_X} substitution.

Tighten the 'User Input Tools' section and de-duplicate the overlapping normal-vs-refined step descriptions to reduce token overhead without losing the workflow structure.

DimensionReasoningScore

Conciseness

Mostly efficient and table-driven, assuming Claude's competence without explaining basic translation concepts; minor verbosity in the 'User Input Tools' section and some duplication between the normal and refined mode step descriptions keep it just below lean.

4 / 5

Actionability

Provides a concrete chunking command, explicit file-naming conventions, EXTEND.md resolution paths, a defaults table with CLI flags, and an output-directory file table, but the placeholder variables ({baseDir}, ${BUN_X}) require manual resolution and no fully copy-paste-ready example invocation is given.

4 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced and refined mode has a critique→revision→polish feedback loop, but the batch chunked-translation merge (Step 3.1.6) lacks any validation/consistency checkpoint; per the rubric, missing validation in a batch operation caps this dimension at 3.

3 / 5

Progressive Disclosure

The body is an overview that points to well-signaled, one-level-deep references (extend-schema.md, first-time-setup.md, glossary-en-zh.md, workflow-mechanics.md, refined-workflow.md, subagent-prompt-template.md), all of which resolve to real files, with content appropriately split for easy navigation.

5 / 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 that explicitly states both capability and trigger conditions with comprehensive bilingual natural-language keywords. Only minor specificity gaps prevent a perfect score.

DimensionReasoningScore

Specificity

Names several concrete capabilities — 'translate', 'localize', 'proofread translation', 'refined translation', 'three modes (quick/normal/refined)', and 'custom glossary support' — but omits chunking/image-localization, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

Explicitly answers both 'what' ('Supports three modes (quick/normal/refined) with custom glossary support') and 'when' ('This skill should be used when the user asks to...') with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage in both English and Chinese — 'translate', '翻译', '精翻', 'translate to Chinese', '改成中文', 'localize', '本地化', 'proofread translation', '快翻', '这篇文章翻译一下' — plus a URL/file intent clause, covering synonyms and bilingual variants a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear translation niche with distinctive bilingual triggers unlikely to fire for unrelated skills; conflict risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

68%

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

Validation11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 2 missing, 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

11

/

16

Passed

Repository
JimLiu/baoyu-skills
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.