run-unit-tests

Use when asked to run unit tests.

Quality

58%

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/run-unit-tests/SKILL.md

Quality

Content

78%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 content is lean, assumes Claude's competence, and leads with an executable command, fitting a simple single-purpose skill well. Main weaknesses are minor: the opening restates the description, the working-directory context is prose rather than an executable sequence, and there is no explicit pass/fail verification step.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, giving a concrete command directly; only minor wording ('This skill is used to run unit tests...') slightly restates the description and could be trimmed.	4 / 5
Actionability	It provides a concrete, executable command ('uv run --group test pytest packages/flet/tests') that is mostly copy-paste ready, with only a minor gap: the working-directory context is described in prose rather than shown as part of an executable sequence.	4 / 5
Workflow Clarity	For a simple single-action skill the single command is unambiguous and the relative-path caveat is noted; it lacks an explicit verification step (e.g. reading the pytest exit status/output) but the task is non-destructive so this is only a minor gap.	4 / 5
Progressive Disclosure	This is a short single-purpose skill with no external bundle files needed; content is organized into a clear Instructions section with the command inline, which is appropriate for a skill of this size.	5 / 5
	Total	17 / 20 Passed

Description

37%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 brief and technically correct but minimal: it names a single action ('run unit tests') with a narrow trigger and no concrete specifics, synonyms, or richer trigger phrasing. It avoids fluff and verbosity but stops at the most generic expression of the task.

Suggestions

Add concrete specifics such as the framework and command, e.g. 'Run flet Python package unit tests with pytest using uv' so the what is more actionable in the description.

Expand trigger terms with natural synonyms users say, e.g. 'Use when the user asks to run, execute, or run pytest for flet unit tests.'

Clarify scope to reduce conflict risk, e.g. mentioning it targets the Flet/Python test suite rather than generic unit tests.

Dimension	Reasoning	Score
Specificity	The phrase 'run unit tests' names the domain (unit testing) but offers only the minimal generic action of 'running' tests with no concrete variations or specifics.	2 / 5
Completeness	It has a clear 'what' (run unit tests) and a 'Use when asked to run unit tests' trigger, but the 'when' is only weakly implied and caps here per the missing-explicit-trigger-guidance rule; it answers both what and when at a basic level but the when is narrow.	3 / 5
Trigger Term Quality	'Use when asked to run unit tests' repeats a single generic phrase the user would say; it lacks synonyms like 'execute tests', 'run pytest', or natural variations users actually use.	2 / 5
Distinctiveness Conflict Risk	'run unit tests' is somewhat specific to a testing niche but 'unit tests' is a broad category that could overlap with many testing-related skills; conflict risk is moderate.	3 / 5
	Total	10 / 20 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: flet-dev/flet
Path: .agents/skills/run-unit-tests/SKILL.md
Commit: 8f74fe9

Reviewed: 7 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.