CtrlK
BlogDocsLog inGet started
Tessl Logo

chat-x-unit-test

帮助开发者为 Vue 3 组件编写单元测试。当用户需要添加单元测试时使用。

56

Quality

70%

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 ./bcs-services/bcs-project-manager/.cursor/skills/chat-x-unit-test/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body is a lean, actionable template with real commands and a solid starter scaffold for a simple skill. Its weaknesses are structural: a duplicated resources section pointing at bundle files that are missing, a dangling reference to non-existent IF-THEN rules, and no explicit run-and-fix verification step.

Suggestions

Remove the duplicated '📦 可用资源' section and the dangling 'IF-THEN 规则' note, or replace them with concrete load conditions (e.g. '遇到 mock 需求时加载 references/mock-patterns.md').

Ship the three referenced files (mock-patterns.md, test-qa.md, test-strategies.md) or delete the links that point at them.

Add an explicit verification step after the template, e.g. '编写后运行 npx vitest run src/components/<component>,修复失败用例后再继续', and flesh out the vi.mock example so it is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly efficient (terse commands, a compact template, one-line category descriptions), but the '📦 可用资源' section is duplicated verbatim and the trailing note '根据 SKILL.md 中的 IF-THEN 规则判断是否需要加载' references rules that do not exist in the document — unnecessary padding that keeps it below the level-4 anchor.

3 / 5

Actionability

It provides concrete, runnable commands ('pnpm --filter @blueking/chat-x test', 'npx vitest run src/components/your-component') and a near-complete executable template, matching 'mostly executable guidance with minor gaps'. The gaps — the empty vi.mock stub ('/* ... */') and placeholder component names needing substitution — keep it from the copy-paste-ready level-5 anchor.

4 / 5

Workflow Clarity

As a simple single-purpose skill the action is unambiguous: co-located file naming convention, a starting template, and explicit run commands. It sits between the simple-skill level-5 exception and level 3 because there is no explicit verify/fix checkpoint after writing (e.g., 'run the tests and fix failures before finishing'), though the run commands are given.

4 / 5

Progressive Disclosure

References are listed one level deep with clear paths, but the three referenced files (references/mock-patterns.md, test-qa.md, test-strategies.md) do not exist in the bundle, and the resource section is duplicated verbatim — matching 'some structure but could be better organized' rather than the well-organized level-4 anchor.

3 / 5

Total

14

/

20

Passed

Description

62%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 concise, in third person, and clearly states both what the skill does and when to use it. Its main weaknesses are thin trigger-term coverage (no vitest/spec-file vocabulary) and a single-action capability statement rather than a broader list of concrete capabilities.

Suggestions

Broaden specificity by listing concrete capabilities, e.g. '编写渲染/Props/事件/Slot 测试,mock 依赖,运行 vitest'。

Add trigger-term synonyms users naturally say, such as 'vitest', '测试用例', 'spec 文件', and '@vue/test-utils'。

Sharpen the 'when' clause with concrete triggers, e.g. '当用户提到单元测试、vitest、需要为组件新建 .spec.ts 文件或修复失败的测试时使用'。

DimensionReasoningScore

Specificity

The description names the domain ("Vue 3 组件") and one concrete action ("编写单元测试" — write unit tests), matching the 'names domain and 1-2 concrete actions' anchor. It does not list several specific actions (test types, mocking, running tests), so it is below the level-4 anchor.

3 / 5

Completeness

It answers both 'what' ("帮助开发者为 Vue 3 组件编写单元测试") and an explicit 'when' ("当用户需要添加单元测试时使用"), placing it above the level-3 anchor where 'when' is missing. It falls short of level 5 because the trigger phrases lack concrete specificity (no mention of spec files, vitest, or test failures).

4 / 5

Trigger Term Quality

"单元测试" and "添加单元测试" are relevant natural terms, but common variations a user would actually say — 'vitest', '测试用例', 'spec 文件', '@vue/test-utils' — are absent, fitting the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The Vue 3 component unit-testing niche is mostly distinct with clear triggers, with only minor overlap risk against a generic frontend- or JavaScript-testing skill — matching the 'mostly distinct' anchor rather than level 5's clear niche with minimal conflict risk.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TencentBlueKing/bk-bcs
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.