CtrlK
BlogDocsLog inGet started
Tessl Logo

e2e-tests-studio

REQUIRED when modifying any file in packages/playground-ui or packages/playground. Triggers on: React component creation/modification/refactoring, UI changes, new playground features, bug fixes affecting studio UI. Generates Playwright E2E tests that validate PRODUCT BEHAVIOR, not just UI states.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated workflow, but it is a single monolithic file with internal redundancy and no progressive disclosure to supporting reference files. Tightening the repetition and splitting the pattern/fixture catalog would lift both conciseness and progressive disclosure.

Suggestions

Move the six Behavior Test Patterns and the Kitchen-Sink Fixture reference into bundled reference files (e.g., references/patterns.md, references/fixtures.md) and link to them one level deep from SKILL.md to improve progressive disclosure.

Remove the redundancy between the opening 'What NOT/TO test' lists and the closing 'Anti-Patterns to Avoid' table (keep one) and drop the 'Quick Reference' table that restates commands already shown in the steps.

Add an explicit 'if a test fails' feedback loop in Step 7 (read failure -> fix behavior assertion -> re-run) to make the validation checkpoint a true retry loop.

DimensionReasoningScore

Conciseness

The 449-line body is mostly efficient and project-specific, but includes redundancy — the opening 'What NOT to test / What TO test' lists are restated by the 'Anti-Patterns to Avoid' table, and the 'Quick Reference' repeats commands already in the steps — so it could be tightened, matching the level-2 anchor rather than the lean level-3.

2 / 3

Actionability

It provides fully executable, copy-paste-ready Playwright code across six labeled patterns, concrete shell commands ('pnpm build:cli', 'pnpm test:e2e'), real routes, test IDs, and fixture scaffolding, matching the level-3 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

A clearly sequenced Step 1–Step 7 process ends in Step 7 'Run and Validate' with an explicit Test Quality Checklist acting as a validation gate, matching the level-3 anchor's 'clear sequence with explicit validation steps; checklists for complex processes'.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and all guidance — six long code patterns, the fixture guide, and the anti-pattern table — lives inline in one monolithic file, so content that should be separate is inline; it is well-sectioned (avoiding a 1) but lacks any one-level-deep reference split, matching the level-2 anchor.

2 / 3

Total

10

/

12

Passed

Description

90%

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 well-scoped, third-person, and clearly states both what the skill does and when it triggers. Its main weakness is specificity: it names essentially one action rather than a comprehensive set of concrete capabilities.

Suggestions

Expand the 'what' beyond a single action by listing the concrete outputs the skill produces (e.g., writes BDD-shaped specs, generates kitchen-sink fixtures, refactors existing UI-focused tests into behavior tests).

Consider adding a short 'Use when...' clause mirroring the 'Triggers on' list so the trigger phrasing matches the canonical description pattern.

DimensionReasoningScore

Specificity

Names a concrete domain ('modifying any file in packages/playground-ui or packages/playground') and one well-specified action ('Generates Playwright E2E tests that validate PRODUCT BEHAVIOR, not just UI states'), but does not enumerate multiple distinct concrete actions, so it falls short of the level-3 anchor.

2 / 3

Completeness

It explicitly answers both 'what' ('Generates Playwright E2E tests that validate PRODUCT BEHAVIOR, not just UI states') and 'when' ('REQUIRED when modifying any file in...'; 'Triggers on:...'), satisfying the level-3 anchor with explicit trigger guidance.

3 / 3

Trigger Term Quality

'Triggers on: React component creation/modification/refactoring, UI changes, new playground features, bug fixes affecting studio UI' covers several natural phrasings a developer would actually say, matching the level-3 'good coverage of natural terms' anchor; it is not merely jargon.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to two specific packages plus a distinctive Playwright behavior-testing niche, making it unlikely to fire for unrelated skills; this matches the level-3 'clear niche with distinct triggers' anchor.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
mastra-ai/mastra
Reviewed

Table of Contents

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.