CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fastgpt-integration-test-case

为 FastGPT 生成、维护或合并去重按业务归档的集成测试用例 Markdown,以一个业务验收目标覆盖多个相关场景,支持接口、UI、端到端和服务集成测试及单页阅读器。不用于单独编写 Vitest 测试或系统升级迁移用例。

Quality

81%

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

88%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 dense, highly actionable instruction body: exact paths, copy-paste CLI commands, a validated 8-step generation workflow with explicit verification and anti-fabrication checkpoints, and a properly factored template/script bundle. The only weaknesses are moderate repetition of the category-completeness rule and reference-style format conventions kept inline rather than split into a separate file.

Suggestions

Consolidate the repeated 'don't force basic/abnormal/boundary completeness' guidance (生成步骤 4, 用例类型 section, Markdown 约定) into a single stated rule to save tokens.

Move the frontmatter field conventions (the Markdown 约定 bullet list) or the types/evidence rules into a references/ file, keeping SKILL.md as an overview that links to assets/case-template.md and the new reference.

DimensionReasoningScore

Conciseness

Every section carries operational rules and assumes competence — no generic testing concepts, library intros, or padding (e.g. "不能把现有 bug 写成正确预期"、"不臆造接口、HTTP 方法、错误码"). Not 5 because the 'don't force basic/abnormal/boundary completeness' rule recurs in three places (生成步骤 4, 用例类型 section, Markdown 约定) and some long compound bullets in the types/evidence section could be tightened.

4 / 5

Actionability

Fully executable guidance throughout: exact path pattern `.agents/test/<业务域>/<子业务>/<可选细分>/<ID>-<业务目标>.md`, copy-paste commands (`node .../scripts/catalog.mjs validate|list|serve` with concrete flag examples), concrete endpoint and port (`http://127.0.0.1:4317/`, `GET /api/cases`), the exact file to edit for parser changes (`scripts/case-format.cjs` + `catalog.mjs sync-reader`), and a real, complete template at assets/case-template.md.

5 / 5

Workflow Clarity

"根据业务生成用例" is a numbered 1–8 sequence with explicit validation checkpoints and feedback loops: 局部校验并在阅读器检查 (step 8), 交付前运行 validate, recording 阻塞条件 instead of faking passes, and a verify-fix path for tool changes (use a temporary case directory, don't leave demo data, re-run validate). Error-recovery guidance is explicit (待确认项, 阻塞条件及待补证据).

5 / 5

Progressive Disclosure

Good structure with real one-level-deep bundle references that all exist: [用例模板](assets/case-template.md) carries the per-case scaffolding, and scripts/catalog.mjs / scripts/case-format.cjs are documented by function. Not 5 because ~40 lines of frontmatter field conventions and types/evidence rules remain inlined in SKILL.md where a references/ file would fit the rubric's ideal split; not 3 because the references that exist are clearly signaled and the body is well-sectioned.

4 / 5

Total

18

/

20

Passed

Description

66%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 specific, third-person description that names multiple concrete actions and explicit non-goals, giving it good distinctiveness within the FastGPT niche. Its main weakness is the absence of any explicit 'Use when...' trigger clause, which caps completeness at 3 and limits discoverability against natural user phrasing.

Suggestions

Add an explicit trigger clause, e.g. "当用户提到为 FastGPT 编写、整理、合并或去重集成测试用例(接口/UI/e2e/服务集成)时使用".

Include natural trigger synonyms users might say — 集成测试用例、测试用例文档、用例库、回归用例、test cases — to broaden keyword coverage.

Briefly distinguish from the sibling execution skill (e.g. "筛选并执行已有用例请使用 test-runner skill") to reduce conflict risk with that closely related skill.

DimensionReasoningScore

Specificity

"生成、维护或合并去重按业务归档的集成测试用例 Markdown"、"支持接口、UI、端到端和服务集成测试及单页阅读器" list several concrete actions with explicit exclusions ("不用于单独编写 Vitest 测试或系统升级迁移用例"). Not 5 because the actions are compressed into dense phrases and capabilities like CLI validation/querying of the case library only appear in the body, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (generate, maintain, merge, deduplicate business-archived integration test case Markdown), but there is no 'Use when...' clause or equivalent explicit trigger guidance — only negative scope ("不用于..."). Per the rubric guideline, a missing 'Use when' clause caps completeness at 3; it is not 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural terms a user would say are present: "FastGPT"、"集成测试"、"测试用例"、"接口、UI、端到端". Not 3 because keyword coverage is genuinely good and domain-anchored; not 5 because common variations and synonyms (回归用例、用例库、测试用例文档、English 'test cases') are absent.

4 / 5

Distinctiveness Conflict Risk

"为 FastGPT" and the explicit exclusions of Vitest tests and migration cases carve out a distinct niche with low conflict against generic skills. Not 5 because a closely related sibling execution skill (fastgpt-integration-test-runner) exists and the description itself does not disambiguate it; not 3 because the FastGPT-specific scope clearly separates it from most other skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

labring/FastGPT

Path

.agents/skills/system/fastgpt-integration-test-case/SKILL.md

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.