fix-tests

Use this skill to reproduce and fix flaky and disabled tests.

Quality

75%

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/fix-tests/SKILL.md

Quality

Content

88%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 well-sequenced, highly actionable workflow with concrete commands, explicit validation checkpoints, and a verification feedback loop, held back only by minor verbosity and a lack of progressive file structure.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-driven, with only minor instances of over-explanation (e.g. the illustrative tables and the 'let's say 33%' aside) that could be trimmed, fitting the 'efficient with minor trims' anchor at 4 rather than a fully lean 5.	4 / 5
Actionability	It gives copy-paste-ready commands with documented substitutions — `npm run test -- --repeat=<count> ...`, `git cl upload -f`, `git cl try -B ... -p runner_args='...'`, `git cl try-results`, `bb get <id>` — covering the common cases fully, matching the top anchor.	5 / 5
Workflow Clarity	The multi-agent workflow is explicitly sequenced (local-repro + bot-repro in parallel, then fix-test, then Results) with validation checkpoints and a feedback loop — 'CRITICAL: If the test fails again ... repeat the verification cycle' — matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	As a single-file skill with no bundle, it is well organized into clearly headed sections (Workflow, Reproduction agents, Next steps, Results) with the one external reference (`devtools-version-control` skill) signaled at one level; at ~90 lines it exceeds the simple-skill threshold, so it sits at 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

48%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 states a clear purpose and a reasonably distinct niche, but it is phrased in the penalized second-person voice, omits an explicit 'Use when' trigger clause, and lacks keyword synonyms.

Suggestions

Rewrite in third person and add an explicit trigger clause, e.g. 'Reproduces and fixes flaky and disabled tests. Use when the user reports an intermittent or failing test, a disabled test, or links a flaky-test bug.'

Add natural synonyms to broaden trigger coverage: 'intermittent tests', 'test failures', 'deflake', and 'flakiness'.

Keep it concise — a single sentence pairing the concrete actions (reproduce locally + via stressor bots, then fix) with the trigger clause would raise both specificity and completeness.

Dimension	Reasoning	Score
Specificity	The phrase 'reproduce and fix flaky and disabled tests' names the domain plus two concrete actions (reproduce, fix), which anchors at 3, but the second-person imperative 'Use this skill to...' triggers the mandated 1-point specificity penalty, landing at 2.	2 / 5
Completeness	The 'what' is clear ('reproduce and fix flaky and disabled tests') but there is no explicit 'Use when...' clause or equivalent trigger guidance — the 'when' is only weakly implied, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	'flaky and disabled tests', 'reproduce', and 'fix' are natural terms a user might say, but common synonyms like 'intermittent', 'deflake', or 'test failures' are missing, so coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	'flaky and disabled tests' is a clear, narrow niche unlikely to collide with unrelated skills, though it could overlap slightly with general testing skills, so it sits at 4 rather than a fully distinct 5.	4 / 5
	Total	12 / 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: ChromeDevTools/devtools-frontend
Path: .agents/skills/fix-tests/SKILL.md
Commit: de3f9ca

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.