deflake

Stabilize a flaky test with a minimal, assertion-preserving fix — never by weakening or deleting the check.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

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, highly actionable, and clearly sequenced with explicit validation checkpoints and a feedback loop. As a compact single-file skill it organizes its material well and needs no external progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding explaining what a flaky test or vitest is; every line (allowed fixes, hard rules, verify) earns its place.	3 / 3
Actionability	Concrete, executable guidance throughout: 'testTimeout (3rd arg to it)', 'vi.waitFor', 'vi.useFakeTimers()', 'npx vitest run <file>', and a concrete failure path via '<workdir>/failure.md'.	3 / 3
Workflow Clarity	Clear sequence from reading the test and reproducing the mechanism, through applying the smallest fix and hard rules, to explicit validation (repeated runs that 'must pass every time') with a failure.md feedback loop and final PR/report steps.	3 / 3
Progressive Disclosure	A single, well-organized self-contained skill under 60 lines with clearly labeled sections (allowed fixes, hard rules, verify); no bundle files are present and no deep nesting, so well-organized sections warrant a 3 for a simple skill.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific and clearly differentiated around flaky-test stabilization, but it lacks an explicit 'Use when...' trigger clause and misses common trigger-term variations like 'deflake', which limit completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a test fails then passes on a rerun of the same commit (a flaky test).'

Include the natural trigger term 'deflake' and common variations like 'flaky', 'intermittent test failure', or 'test flakiness'.

Keep the assertion-preserving constraint but ensure the what/when split is explicit rather than implied.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Stabilize a flaky test with a minimal, assertion-preserving fix') plus a hard constraint ('never by weakening or deleting the check'), listing multiple specific concrete behaviors.	3 / 3
Completeness	Clearly states what the skill does, but there is no explicit 'Use when...' trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'flaky test' and 'fix' are natural terms a user would say, but the common trigger term 'deflake' is absent and coverage of variations is partial.	2 / 3
Distinctiveness Conflict Risk	The narrow niche of flaky-test stabilization with an assertion-preserving constraint is distinct and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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: QwenLM/qwen-code
Path: .qwen/skills/deflake/SKILL.md
Commit: 8878264

Reviewed: 5 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.