test-case

当用户需要编写一个单元测试时，触发该 skill，编写单元测试。

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/system/test-case/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is highly actionable with concrete examples, commands, and a well-sequenced workflow including validation and retry. The only meaningful weakness is minor redundancy that could be trimmed for token efficiency.

Suggestions

Remove or shorten the 'When to Use' section since it restates the frontmatter description verbatim.

Consolidate the repeated mock-guidance into a single rule to avoid restating it across the 通用规则 and 带 API 请求的函数 sections.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and procedural, but the 'When to Use' section duplicates the frontmatter description and mock-guidance is restated across sections, leaving room to tighten.	2 / 3
Actionability	It provides executable, copy-paste-ready guidance: exact file-path mappings, real import code, concrete commands like 'pnpm test <file-path> <test-name>', and explicit coverage thresholds (90%/100%).	3 / 3
Workflow Clarity	A clear three-phase sequence (任务准备 → 测例编写 → 结果验证) includes an explicit validation checkpoint (run tests, check coverage ≥90%) and a feedback loop that returns to 测例编写 on failure.	3 / 3
Progressive Disclosure	No bundle files exist and the SKILL.md is a single, well-organized document with clear sections and one-level relative links; per the simple-skills note this is sufficient for a top score.	3 / 3
	Total	11 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 clearly identifies a single niche (unit testing) with an explicit trigger clause, but is thin on enumerated capabilities and trigger-term variation. It is functional but could be enriched with more concrete actions and synonym coverage.

Suggestions

List multiple concrete capabilities, e.g. '编写单元测试，覆盖行与分支、配置文件位置约定与 mock 策略'.

Add natural trigger variations such as '测试', '测试用例', 'test case', '覆盖率' alongside '编写单元测试'.

Dimension	Reasoning	Score
Specificity	The description names the domain (unit testing) and one action ('编写一个单元测试'), but does not enumerate concrete capabilities like coverage thresholds, mock strategy, or file-location conventions.	2 / 3
Completeness	It explicitly answers both 'what' (编写单元测试) and 'when' (当用户需要编写一个单元测试时), satisfying the explicit-trigger requirement that prevents a cap at 2.	3 / 3
Trigger Term Quality	'当用户需要编写一个单元测试时' is a natural phrasing a user would say, but only a single keyword cluster is present with no common variations such as '测试', '测试用例', 'test case', or '覆盖率'.	2 / 3
Distinctiveness Conflict Risk	'单元测试' is a clear, distinct niche with an explicit trigger unlikely to fire for unrelated skills, even though it could overlap with other testing-style skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: labring/FastGPT
Path: .agents/skills/system/test-case/SKILL.md
Commit: dc97c08

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.