CtrlK
BlogDocsLog inGet started
Tessl Logo

antd-test-review

审查 ant-design 测试用例是否值得保留。在用户要求验证测试 case、review 测试质量、判断测试是否合理、是否“用 A 证明 A”、是否重复、是否锁定实现细节,或决定测试应删除、保留还是改写时使用。

72

Quality

87%

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

75%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, domain-specific judgment framework with concrete anti-patterns, an explicit output format, classification criteria, and a clear sequenced process. The main weakness is moderate redundancy across the principles, process, and quick-reference sections that could be tightened.

Suggestions

Consolidate the overlapping criteria: 核心判断四/五, 执行流程 3/4, and 快速拦截 all restate style-self-proof, duplicate-coverage, and independent-evidence rules — consider letting 核心判断 hold the principles and having 执行流程/快速拦截 reference them rather than restate.

Provide one or two concrete, filled-in rg examples (real keyword + component path) alongside the template so the search step is copy-paste ready.

If the 核心判断 detail grows further, split the anti-pattern catalog into a references/ file and keep SKILL.md as the overview + process, which would also raise progressive_disclosure.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — no padding with basics — but the same criteria (style self-proof, duplicate coverage, independent evidence) are restated across 核心判断, 执行流程, and 快速拦截, a moderate trim opportunity. Not a 3 because the restatements serve distinct reader purposes (principles vs procedure vs cheat sheet); not a 5 because the redundancy is noticeable.

4 / 5

Actionability

Concrete guidance throughout: specific anti-patterns (toHaveStyle, toHaveClass, toBeTruthy), a copy-paste output format, explicit classification criteria, and a search command template. Not a 5 because the only command (rg with <关键字>/<component> placeholders) is templated rather than copy-paste ready; not a 3 because the judgment guidance is specific and covers common cases.

4 / 5

Workflow Clarity

执行流程 is a clear 5-step sequence (静态审查 → 提炼契约 → 查独立依据 → 查重复 → 分类结论) with decision checkpoints at each step ('如果回答不稳→判无实际作用', '找不到独立依据→判低价值'). Not a 5 because there is no explicit re-validation/retry loop, though one is arguably unnecessary for a non-destructive judgment task.

4 / 5

Progressive Disclosure

Well-organized into clear section headers (目标/何时使用/不做的事/核心判断/输出要求/执行流程/约束/快速拦截) with easy navigation; no bundle files exist and the skill is self-contained. Not a 5 because it exceeds 50 lines and the anchor's reference-splitting is N/A, so the simple-skill exception does not fully apply; minor organization gaps remain.

4 / 5

Total

16

/

20

Passed

Description

100%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, third-person description that explicitly covers both what the skill does and when to use it, with concrete trigger phrases and a distinctive ant-design test-review niche. No first/second-person voice or vague fluff.

DimensionReasoningScore

Specificity

Names the domain (ant-design test cases) and lists multiple concrete actions/judgments: 验证测试 case、判断是否'用 A 证明 A'、是否重复、是否锁定实现细节、决定删除/保留/改写 — comprehensive coverage of concrete actions.

5 / 5

Completeness

Explicitly answers both what ('审查 ant-design 测试用例是否值得保留') and when ('在用户要求…时使用') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural Chinese trigger phrases a user would actually say when reviewing tests (验证测试 case、review 测试质量、判断测试是否合理、是否重复、决定测试应保留/改写/删除), including synonyms like 合理/无意义 and 保留/改写/删除.

5 / 5

Distinctiveness Conflict Risk

Clear niche (ant-design test-case retention decisions framed as 保留/改写/删除) with distinct triggers and minimal conflict risk against general code-review skills.

5 / 5

Total

20

/

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
ant-design/ant-design
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.