CtrlK
BlogDocsLog inGet started
Tessl Logo

chinese-code-review

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。

71

Quality

88%

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

92%

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, highly actionable, and clearly sequenced, with strong templates and a checklist. Its only notable gap is progressive disclosure: everything is inline with no one-level-deep reference files, despite content that would benefit from being split out.

Suggestions

Move the substantial Commit Message bilingual-format section (type table + examples) into a references/ file and link to it from SKILL.md, keeping only a concise summary inline.

Extract the 中英混排代码注释规范 rules into a separate reference file so SKILL.md stays a focused overview of review communication.

Add a short navigation table at the top pointing to those reference files once split, so reviewers can quickly jump to commit-format or commenting-norm details.

DimensionReasoningScore

Conciseness

The body is lean and built from tables, before/after example pairs, and copy-paste templates; it assumes Claude already knows code review and avoids padding with basic concept explanations.

3 / 3

Actionability

Provides concrete executable guidance: severity labels ([必须修复]/[建议修改]/[仅供参考]), a commit-message type table with examples, review-comment templates, and a final checklist — all copy-paste ready.

3 / 3

Workflow Clarity

The "审查流程建议" section sequences 开始审查前 → 审查顺序 (6 ordered checks) → 给出总结, and the closing checklist reinforces it; no destructive/batch operation requires validation feedback loops here.

3 / 3

Progressive Disclosure

No bundle files exist and all content sits inline in a ~150-line SKILL.md; the well-organized sections help, but sizable reference-style blocks (commit-message bilingual format, comment-norm rules) could be split into separate files rather than kept inline.

2 / 3

Total

11

/

12

Passed

Description

85%

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, complete, and clearly niche with explicit trigger guidance and a no-auto-trigger directive. Its main weakness is trigger-term quality, which leans on the slash command rather than a broad set of natural user phrases.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对" — each a specific, distinct action rather than vague abstraction.

3 / 3

Completeness

Explicitly answers what (话术模板、分级标注、反模式应对) and when ("仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发"), satisfying the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Trigger relies mainly on the slash command "/chinese-code-review" with supporting terms "中文 review" and "国内团队"; coverage of natural phrasings a user might say is relevant but lacks common variations.

2 / 3

Distinctiveness Conflict Risk

Clear niche (Chinese-language review communication for domestic teams) with an explicit no-auto-trigger directive, making conflicts with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

81%

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

Validation13 / 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

Total

13

/

16

Passed

Repository
jnMetaCode/superpowers-zh
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.