CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

从固定点(commit、branch、tag 或 merge-base)开始,按 Standards(代码是否符合本仓库记录的编码标准?)和 Spec(代码是否符合来源 issue/PRD 的要求?)两个轴线审查变更。两个审查会在并行子代理中运行,并并排报告。适用于用户想审查 branch、PR、进行中的变更,或要求 “review since X” 时。

80

Quality

100%

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

100%

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

The body is an efficient, highly actionable process skill: concrete git commands, verbatim sub-agent briefs, an explicit pre-flight validation checkpoint, and well-organized sections. It scores at the top of every dimension.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — no explanation of what git diff or a code smell is — and the inlined Fowler smell catalog is genuinely additive reference material rather than padding. Not level 2 because it lacks the unnecessary explanatory prose that would lower it.

3 / 3

Actionability

Provides concrete executable commands ('git diff <fixed-point>...HEAD', 'git rev-parse', 'git log ... --oneline') and verbatim sub-agent briefs with word limits. Not level 2 because guidance is copy-paste ready rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

Five-step sequence with an explicit validation checkpoint (Step 1: confirm the fixed point resolves and the diff is non-empty before spawning parallel agents) and a fallback for missing spec. Not level 2 because validation is explicit and前置 rather than implicit or omitted, which the guideline requires for batch/parallel operations.

3 / 3

Progressive Disclosure

No bundle files exist, so the self-contained body is evaluated on its own organization: clear sectioned structure (numbered Process, 'Why two axes') with a clearly signaled one-level reference to docs/agents/issue-tracker.md. Not level 2 because organization is clean and references are shallow, not a monolithic wall or nested pointers.

3 / 3

Total

12

/

12

Passed

Description

100%

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 well-triggered: it states concrete actions, explicit use-conditions, and natural trigger phrasing within a distinct niche. It scores at the top of every dimension.

DimensionReasoningScore

Specificity

Names multiple concrete actions — dual-axis review (Standards/Spec), running both as parallel sub-agents, and side-by-side reporting — rather than vague language. It is not level 2 because it goes beyond naming the domain to enumerate specific operations.

3 / 3

Completeness

Explicitly answers what (dual-axis review of diff between fixed point and HEAD) and when ('适用于用户想审查 branch、PR、进行中的变更,或要求 review since X 时'). Not level 2 because the 'when' is stated explicitly, not merely implied.

3 / 3

Trigger Term Quality

Includes natural terms users would say: '审查 branch、PR、进行中的变更' and 'review since X'. Not level 2 because coverage spans the common real-world phrasings rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (fixed-point diff dual-axis review) with distinct triggers unlikely to fire for unrelated skills. Not level 2 because the trigger conditions are specific enough to avoid overlap with generic review skills.

3 / 3

Total

12

/

12

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
vinvcn/mattpocock-skills-zh-CN
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.