CtrlK
BlogDocsLog inGet started
Tessl Logo

translate

Translate English or Japanese tech articles into natural, fluent Chinese. Use whenever the user asks for Chinese translation, says "translate to Chinese" or "翻译", or provides English/Japanese content (pasted text or a file) to convert into Chinese. Chinese output only — not for translating into other languages.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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.

The content is concise and well-structured for a simple translation skill, with clear sections and a sensible internal process. Its weaknesses are the absence of a validation/review checkpoint in the workflow and the lack of any concrete translation example or output template.

Suggestions

Add an explicit validation step to the Process (e.g., after 意译优化, verify the Chinese output preserves every technical term and all original Markdown formatting before emitting it) to lift workflow clarity above 3.

Include one short before/after translation example (a sentence or two with the preserved-term list applied) so the guidance is concrete and copy-paste illustrative, improving actionability.

Consider a compact 'keep untranslated' rule example showing how a term like 'Fine-tuning' survives in a translated sentence, making the constraint executable rather than only stated.

DimensionReasoningScore

Conciseness

The body is lean: a focused role statement, tight constraints, a three-step internal process, and a minimal output spec, with every token earning its place and no padding of concepts Claude already knows.

5 / 5

Actionability

Guidance is concrete in intent (preserve Markdown, keep a named term list untranslated, three named translation steps, output only the final result) but there is no executable example or template, so it is more specific direction than copy-paste-ready instruction.

3 / 5

Workflow Clarity

The three translation steps are clearly sequenced, but there is no validation checkpoint comparing the final output against the source for accuracy or completeness; the rubric caps workflow clarity at 3 when validation is absent, which applies here.

3 / 5

Progressive Disclosure

This is a simple sub-50-line single-purpose skill with no bundle files and no need for external references; its well-organized sections (Role, Constraints, Process, Output, Input) satisfy the simple-skill exception for a top score.

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.

The description is strong: it explicitly states what the skill does and when to use it, with natural bilingual trigger terms and a clear Chinese-only niche. Specificity is the only slightly lower dimension because the sole concrete action is 'translate', with no enumerated sub-actions.

DimensionReasoningScore

Specificity

The description states concrete actions ('Translate English or Japanese tech articles into natural, fluent Chinese') but the only action named is translation; it lists no multiple specific operations, sitting just below the comprehensive-multi-action anchor.

4 / 5

Completeness

It explicitly answers both 'what' (translate EN/JA tech articles into natural fluent Chinese) and 'when' ('Use whenever the user asks for Chinese translation, says... or provides...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

It covers natural phrases users say ('translate to Chinese', '翻译'), the source languages, and the implicit file/text input form, giving comprehensive natural-term coverage including a Chinese synonym.

5 / 5

Distinctiveness Conflict Risk

The Chinese-only output constraint and explicit EN/JA→Chinese direction carve a clear niche with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
feiskyer/claude-code-settings
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.