test-validate

运行项目测试（涵盖 Python 后端、Vue 前端及多语言校验）

Quality

68%

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 ./.cursor/skills/test-validate/SKILL.md

Quality

Content

87%

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

The content is concise and highly actionable, with executable commands and a useful coverage-guidance table, and it is well organized with only a single one-level external reference. Its main gap is the lack of an explicit multi-step workflow with validation checkpoints, since it functions as a command reference rather than a guided process.

Suggestions

Add a short numbered workflow for the most common case (e.g. make change → run affected tests → confirm fail-before/pass-after → run coverage), with an explicit validation checkpoint.

Clarify how to choose between backend and frontend commands when a change spans both stacks.

Surface the `.cursor/rules/testing.mdc` reference earlier or as a dedicated section so it is not buried in a footnote-style tip.

Dimension	Reasoning	Score
Conciseness	The body is lean: it presents copy-paste commands with terse comments, a dense guidance table, and one specific tip, without explaining concepts Claude already knows (e.g. what pytest or npm is), so every token earns its place.	3 / 3
Actionability	It provides fully executable, specific commands (e.g. `pytest tests/test_frontend_locales.py`, `cd web && npm run test:coverage`) and a concrete per-change-type test table, making the guidance copy-paste ready.	3 / 3
Workflow Clarity	Commands and a guidance table are present, but the skill is a command catalog rather than a sequenced multi-step workflow with explicit validation checkpoints; the bug-fix row implies a fail-then-pass check but no explicit validate→fix→retry loop is stated.	2 / 3
Progressive Disclosure	No bundle files exist, so the self-contained body is evaluated on its own organization: well-structured sections (backend, frontend, coverage table, tip) with a single clearly signaled one-level external pointer to `.cursor/rules/testing.mdc`, fitting the well-organized simple-skill case.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 clear and scoped to Python backend, Vue frontend, and multilanguage validation, but it states only one action and omits any explicit 'Use when...' trigger guidance. It reads as a competent but incomplete description that would benefit from a trigger clause and more concrete action verbs.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to run tests, verify changes, or check frontend/backend locale consistency.'

List concrete actions beyond 'run', such as 'run unit tests, generate coverage reports, check locale key alignment'.

Include common trigger variations users might say (e.g. "跑测试", "unit test", "覆盖率") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The single concrete action "运行项目测试" is named with a scoped parenthetical (Python 后端、Vue 前端及多语言校验), but only one verb is given rather than a list of multiple specific actions, matching the 'names domain and some actions, not comprehensive' anchor.	2 / 3
Completeness	It clearly states what the skill does (run project tests with stated coverage), but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like "测试" (test), "Python 后端", "Vue 前端", and "多语言校验" are present, but common user variations (e.g. "跑测试", "unit test", "覆盖率") are missing, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	"运行项目测试" is broadly applicable and could overlap with other testing-related skills, though the Python/Vue/multilanguage scoping narrows it somewhat, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: 4thfever/cultivation-world-simulator
Path: .cursor/skills/test-validate/SKILL.md
Commit: 001b129

Reviewed: 2 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.