run-integration-tests

Use when asked to run integration tests.

Quality

62%

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-integration-tests/SKILL.md

Quality

Content

68%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 pointer skill: a single section, an exact test location, and a clear one-level reference to the repo's README. Its weakness is that all executable substance — commands, options, and validation steps — is delegated to an external file the skill does not itself carry, leaving actionability and workflow detail thin.

Suggestions

Inline the one or two concrete commands needed to run the suite (e.g. the pytest/pytest-asyncio invocation with any required flags or env vars) instead of delegating everything to the external README.

Add a brief validation/checkpoint note (how to interpret failures, what a passing run looks like) so the workflow doesn't depend entirely on an out-of-bundle file.

Clarify the README reference as a skill-relative or repo-relative path and note its role (setup instructions vs. full test instructions) so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	Three lines with a single '## Instructions' header: 'Integration tests are in `sdk/python/packages/flet/integration_tests` directory. Read `sdk/.../README.md` for further instructions.' No concepts Claude already knows are explained; every token carries information. The single redundant word ('directory') does not reach the level-4 'minor instances of over-explanation' bar.	5 / 5
Actionability	Concrete guidance exists — an exact directory path and a specific next action ('Read `sdk/python/packages/flet/integration_tests/README.md`') — but no runnable command or example, so key execution details are missing, matching anchor 3. Not 4 because nothing in the body is directly executable as-is.	3 / 5
Workflow Clarity	A minimal two-step sequence is present (locate the test directory, read the README) but the actual test-running workflow is entirely delegated to an external file, leaving sequence details and checkpoints implicit — anchor 3. Not higher because the skill itself defines no unambiguous end-to-end workflow for running the tests.	3 / 5
Progressive Disclosure	The body is a concise overview with a clearly signaled, one-level-deep pointer ('Read ... README.md for further instructions'), and no bundle files exist to nest — matching anchor 4. Not 5 because the reference points to a repo path outside the skill's own bundle rather than well-organized skill material, a minor navigation/organization gap.	4 / 5
	Total	15 / 20 Passed

Description

36%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 provides an explicit 'Use when' trigger but entirely omits what the skill does, leaving it unable to communicate its capabilities. Trigger phrasing is natural but lacks variations or synonyms that would improve retrieval. Distinctiveness rests solely on the term 'integration tests'.

Suggestions

State the capability explicitly, e.g. 'Runs the Python SDK integration test suite and reports failures' — the 'what' is currently missing entirely, which caps completeness at 2.

Broaden trigger coverage with natural variations such as 'integration testing', 'run the test suite', or 'run tests in sdk/python' so users' phrasing matches without over-claiming.

Add a distinguishing detail (e.g. the flet/python-sdk scope or how these differ from unit tests) to reduce overlap with a generic test-running skill.

Dimension	Reasoning	Score
Specificity	The phrase 'run integration tests' names the domain but the description states no capability or action — 'Use when asked to run integration tests' describes only invocation, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no concrete action of the skill is ever listed.	2 / 5
Completeness	Only the 'when' clause is present ('Use when asked to run integration tests') with no 'what' whatsoever — the skill's actual capability is never stated. This matches anchor 2 ('only when is present without what') and cannot be 3 because there is no clear 'what' either.	2 / 5
Trigger Term Quality	'asked to run integration tests' includes one natural phrase a user would say, but coverage stops there — no synonyms like 'integration testing', 'test suite', 'CI', or path/extension variants — matching 'Some relevant keywords but missing common variations or synonyms'. Not 4 because only a single trigger phrase is present.	3 / 5
Distinctiveness Conflict Risk	'integration tests' is somewhat specific but the description offers no other distinguishing triggers, so it could still overlap with a unit-test or general test-execution skill — matching anchor 3. Not 4 because a single qualifier is the only differentiator.	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-integration-tests/SKILL.md
Commit: 9748de3

Reviewed: 4 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.