fix

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

77%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.

A well-sequenced, actionable debugging workflow with a genuine validation feedback loop. Its main defect is progressive disclosure: it references a flaky-taxonomy.md file that does not exist in the bundle while also inlining that taxonomy.

Suggestions

Add the missing references/flaky-taxonomy.md file (or remove the 'Load flaky-taxonomy.md' instruction and rely on the inlined table) so the reference is not a dangling pointer.

Tighten the opening line and 'Suggest:' framing in step 6, and merge the Output recap with prior steps, to remove redundancy and push conciseness toward lean.

For each category in step 4, pair the guidance bullet with a minimal executable code snippet (e.g. an actual web-first assertion replacement) to lift actionability to fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is efficient with clear sections and executable commands and does not over-explain Playwright basics, but the opening line re-states the description and a few phrases ('Suggest:', the Output recap) could be trimmed, so it is just below the 'every token earns its place' anchor 5.	4 / 5
Actionability	It provides copy-paste-ready npx commands and a diagnosis table, but the per-category fixes are guidance-level bullets (e.g. 'Create test data per-test via API or fixtures') rather than executable code, leaving minor gaps versus the fully copy-paste anchor 5.	4 / 5
Workflow Clarity	A clear six-step sequence (reproduce, trace, categorize, fix, verify, prevent) includes explicit validation ('All 10 must pass') and a feedback loop ('If any fail, go back to step 3'), matching the explicit-validation-and-recovery anchor.	5 / 5
Progressive Disclosure	Section structure is clear and the single-file scope is appropriate, but the instruction to 'Load flaky-taxonomy.md from this skill directory' is a dangling reference (no references/ directory and the file is absent) and the taxonomy is also inlined as a table, creating an inconsistent, non-navigable reference.	3 / 5
	Total	16 / 20 Passed

Description

86%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 strong, well-structured description that clearly answers both what and when with comprehensive natural-language triggers. Its only weakness is specificity: it names a single action rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Playwright tests") and a single concrete action ("Fix failing or flaky") but does not list multiple specific concrete actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor 4/5.	3 / 5
Completeness	It explicitly states what ('Fix failing or flaky Playwright tests') and when ('Use when user says...') with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	It lists seven natural trigger phrases a user would actually say ('fix test', 'flaky test', 'test failing', 'debug test', 'test broken', 'test passes sometimes', 'intermittent failure'), giving comprehensive synonym coverage.	5 / 5
Distinctiveness Conflict Risk	The Playwright scope and flaky/intermittent triggers carve a clear niche, but generic phrases like 'fix test' and 'debug test' carry minor overlap risk with general test-debugging skills, so it sits just below the minimal-conflict anchor 5.	4 / 5
	Total	17 / 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: alirezarezvani/claude-skills
Path: engineering-team/playwright-pro/skills/fix/SKILL.md
Commit: 19392f7

Reviewed: ~8 hours 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.