CtrlK
BlogDocsLog inGet started
Tessl Logo

e2e-testing-patterns

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-structured, actionable skill body with executable examples and a clean one-level reference into the real references/details.md bundle. It would benefit from trimming generic testing-truisms Claude already knows and from adding explicit validation/feedback checkpoints to the debugging workflow.

Suggestions

Remove the 'Testing Pyramid' ASCII diagram and collapse the generic 'What to Test / What NOT to Test / Best Practices / Common Pitfalls' lists into the patterns that are non-obvious, cutting tokens that restate knowledge Claude already has.

Add explicit feedback checkpoints to the 'Debugging Failing Tests' sequence (e.g. '4. If the test still fails after trace review, isolate it with --grep and re-run; only mark fixed when it passes 5x consecutively') to raise workflow clarity.

DimensionReasoningScore

Conciseness

The body includes content Claude already knows — the ASCII 'Testing Pyramid' diagram plus generic lists ('What to Test', 'What NOT to Test', 'Best Practices', 'Common Pitfalls') — so it could be tightened, though it is organized into sections rather than padded prose, keeping it above the lowest anchor.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code and commands — the bad/good selector comparison in Cypress, `npx playwright test --headed`/`--debug`, and a `test.step` example — meeting the executable-code anchor rather than pseudocode.

3 / 3

Workflow Clarity

The 'Debugging Failing Tests' section gives a clear 1–5 escalation sequence, but it lacks explicit validation checkpoints or feedback loops (e.g. 'if still flaky, check X'), fitting the sequence-present-but-checkpoints-implicit anchor.

2 / 3

Progressive Disclosure

SKILL.md is an organized overview that signals a single one-level-deep reference ('Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.'), and that bundle file exists and is correctly referenced, matching the well-signaled reference anchor.

3 / 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.

A strong, mostly well-constructed description with explicit trigger guidance and good natural keyword coverage. Its main weakness is the imperative 'Master ...' voice rather than third person, which lowers the specificity score.

Suggestions

Rewrite in third person to match the rubric's voice requirement, e.g. 'Builds reliable end-to-end test suites with Playwright and Cypress that catch bugs, improve confidence, and enable fast deployment.'

Replace outcome-oriented phrasing ('catch bugs, improve confidence, enable fast deployment') with more concrete technical actions (e.g. 'write, run, and debug E2E test suites') to strengthen specificity.

DimensionReasoningScore

Specificity

Names concrete tools (Playwright, Cypress) and several actions ('implementing E2E tests, debugging flaky tests, establishing testing standards'), meeting the multi-action bar; however the imperative 'Master end-to-end testing' reads as second-person voice rather than the required third person, reducing the specificity score by one per the rubric guideline.

2 / 3

Completeness

It explicitly states what ('build reliable test suites that catch bugs, improve confidence, and enable fast deployment') and includes an explicit 'Use when implementing E2E tests, debugging flaky tests, or establishing testing standards' trigger clause, satisfying both halves.

3 / 3

Trigger Term Quality

Covers natural terms a user would actually say — 'E2E tests', 'end-to-end testing', 'flaky tests', 'Playwright', and 'Cypress' — including both the spelled-out and abbreviated forms, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The E2E-testing niche with named tools and distinct triggers ('flaky tests', 'E2E tests') is unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wshobson/agents
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.