CtrlK
BlogDocsLog inGet started
Tessl Logo

requesting-code-review

完成任务、实现重要功能或合并前使用,用于验证工作成果是否符合要求

52

Quality

58%

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 ./skills/requesting-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is well-structured, actionable, and avoids padding, with a clear review-request workflow and severity-based feedback triage. Its main weaknesses are a verbose example that duplicates earlier commands, an external template that is referenced but not shown, and a referenced bundle file (code-reviewer.md) that is absent from the provided bundle.

Suggestions

Trim or condense the '示例' transcript so it does not repeat the git SHA commands already given in '如何请求'; keep only the novel filled-in dispatch values.

Either inline the code-reviewer.md prompt template (or its key fields) so the dispatch step is fully self-contained, or confirm the bundle file exists and is reachable at the stated path.

Make the validation checkpoint explicit in step 3, e.g. '修复所有 Important 问题后才能继续下一个任务' framed as a gate, to lift workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but the transcript-style '示例' section repeats the git SHA commands already shown under '如何请求' and the '何时请求审查'/'与工作流的集成' sections overlap, so it could be tightened.

2 / 3

Actionability

Provides executable copy-paste git commands and clearly explained placeholders, but the actual review-prompt template lives in the external code-reviewer.md and is not reproduced, so the core dispatch instruction is concrete yet incomplete inline.

2 / 3

Workflow Clarity

The three-step sequence (get SHA → dispatch → handle feedback) is clear and the severity triage (Critical/Important/Minor) acts as a checkpoint, but the 'proceed only after fix' validation is implicit rather than an explicit validate-then-retry loop.

2 / 3

Progressive Disclosure

Content is organized into clear sections with a one-level-deep, clearly signaled reference to code-reviewer.md, but no bundle file exists to verify that reference is real, so the navigation cannot be confirmed as sound.

2 / 3

Total

8

/

12

Passed

Description

67%

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 cleanly states both what the skill does and when to use it, with natural trigger conditions around task completion and merges. It is held back by listing only a single action and by not naming 'code review' directly, which slightly weakens specificity, trigger coverage, and distinctiveness.

Suggestions

Lead with the concrete capability name, e.g. '派遣代码审查子代理验证工作成果' so the action and agent are explicit rather than the generic '验证'.

Add the natural keyword '代码审查'/'review' alongside '验证' so users who say 'review my code' trigger the skill.

Name one or two more concrete actions (e.g. '审查 diff、检查是否符合计划要求') to lift specificity from a single action to multiple.

DimensionReasoningScore

Specificity

Names a concrete action ('验证工作成果是否符合要求' / verify work meets requirements) and its domain, but lists only one action rather than multiple specific concrete actions, so it stops short of the top anchor.

2 / 3

Completeness

Explicitly answers both what ('验证工作成果是否符合要求') and when ('完成任务、实现重要功能或合并前使用'), with explicit trigger guidance rather than implied timing.

3 / 3

Trigger Term Quality

Includes natural trigger terms a user would say ('完成任务', '实现重要功能', '合并'), but omits the most common variation — '代码审查'/'review' itself — relying on '验证' instead, so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

The merge/task-completion triggers carve out a somewhat specific niche, but '验证工作成果' is generic enough to overlap with testing or general verification skills, so it is not a clear conflict-free niche.

2 / 3

Total

9

/

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.