deflake

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

Quality

81%

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

92%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.

Tight, actionable, and well-sequenced instruction skill with explicit verification and a failure fallback; its only gap is the absence of a complete executable code example, which is acceptable for an instruction-only skill but keeps actionability just below perfect.

Dimension	Reasoning	Score
Conciseness	Lean ~57-line body that assumes Claude's competence (no explanation of what vitest or flakiness is); every section and parenthetical earns its place by clarifying a non-obvious constraint.	5 / 5
Actionability	Gives concrete commands and APIs ('npx vitest run <file>', 'vi.waitFor', 'vi.useFakeTimers()', testTimeout as 3rd arg to 'it') and four enumerated fix categories, but lacks a complete copy-paste code example.	4 / 5
Workflow Clarity	Clear sequence (read issue → reproduce → apply smallest fix → verify → report) with an explicit validation checkpoint ('it must pass every time', standard verify gate) and a failure.md feedback loop for error recovery.	5 / 5
Progressive Disclosure	A single well-organized file with clear section headers and only one-level-deep, clearly signaled external references (prepare-pr/SKILL.md, Shared Rules); no bundle files are needed for a skill this size.	5 / 5
	Total	19 / 20 Passed

Description

70%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, well-scoped description with strong distinctiveness, but it omits an explicit 'Use when…' trigger clause and lacks synonym coverage, capping completeness and trigger 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).' to satisfy the completeness 'when' requirement.

Broaden trigger terms with synonyms like 'intermittent test failure' or 'fix flaky test' so the description matches more natural phrasings.

Consider naming one or two more concrete capabilities (e.g. raising test timeouts, seeding RNG/faking timers) to lift specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (flaky tests) with two concrete actions — 'Stabilize a flaky test with a minimal, assertion-preserving fix' and 'never by weakening or deleting the check' — but stops short of enumerating multiple distinct capabilities.	4 / 5
Completeness	Has a clear 'what' (stabilize a flaky test with a minimal fix) but no explicit 'when'/'Use when…' trigger clause, which the rubric caps at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('Stabilize', 'flaky test', 'assertion') but misses common synonyms like 'intermittent test failure' or 'fix flaky'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (flaky-test deflaking) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	16 / 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: QwenLM/qwen-code
Path: .qwen/skills/deflake/SKILL.md
Commit: 6decff0

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.