CtrlK
BlogDocsLog inGet started
Tessl Logo

e2e-testing-patterns

Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do.

49

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/e2e-testing-patterns/SKILL.md

The canonical home for this skill is e2e-testing-patterns in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 admirably concise and free of padding, but it stays at the level of abstract direction: no executable code, commands, or library names, no validation checkpoints, and its only reference points to a non-existent `resources/` path. It reads as a skeleton rather than actionable guidance.

Suggestions

Add concrete, executable guidance — name tools (e.g. Playwright/Cypress), include a minimal runnable test snippet, and specify commands for running in CI.

Insert validation/feedback checkpoints into the workflow (e.g. after building selectors, verify the test runs green locally before parallelizing in CI) to lift workflow clarity above the destructive/batch cap of 3.

Fix the dangling reference: either create `resources/implementation-playbook.md` with the promised patterns/templates and link it correctly, or remove the broken pointer.

DimensionReasoningScore

Conciseness

The ~36-line body is lean and assumes Claude's competence: "Identify critical user journeys and success criteria", "Build stable selectors and test data strategies" — no padding, no explaining what a test framework is, every line earns its place.

5 / 5

Actionability

Instructions are high-level hints ("Implement tests with retries, tracing, and isolation", "Run in CI with parallelization and artifact capture") with no concrete code, commands, library names, or copy-paste examples — minimal concrete guidance, missing the specific steps to execute.

2 / 5

Workflow Clarity

The four numbered steps give a rough sequence (identify → build → implement → run in CI) but there are no validation checkpoints or feedback loops, and destructive/CI batch operations lack the validate-then-proceed guidance the rubric requires — capping workflow clarity at 3.

3 / 5

Progressive Disclosure

Structure is minimal: the single reference `resources/implementation-playbook.md` is mentioned but the `resources/` directory does not exist in the bundle, the path is not a working link, and detailed patterns/templates that clearly belong in a referenced file are instead absent entirely.

2 / 5

Total

12

/

20

Passed

Description

53%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 'what' (reliable, fast E2E test suites) in third person with no over-claims, but it lacks an explicit 'Use when...' trigger clause and misses common natural keywords users would say, capping completeness and trigger-term quality at 3.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when setting up or debugging end-to-end tests, fixing flaky tests, or building E2E suites with Playwright/Cypress."

Include natural user-facing keywords and synonyms like "E2E tests", "flaky tests", "Playwright", "Cypress", and "browser automation".

Replace the outcome-style 'catch regressions before users do' with a concrete capability (e.g. "write, run, and debug E2E test suites") to lift specificity above 3.

DimensionReasoningScore

Specificity

Quotes "Build reliable, fast, and maintainable end-to-end test suites" and "catch regressions before users do" — names the domain with 1-2 concrete actions (build suites, catch regressions) but the actions are high-level outcomes rather than enumerating what the skill concretely does.

3 / 5

Completeness

Has a clear 'what' (build reliable E2E test suites) but the description field itself contains no 'Use when...' trigger clause, so 'when' is absent from the description — capping completeness at 3 per the rubric's missing-trigger guidance.

3 / 5

Trigger Term Quality

Includes "end-to-end test suites" and "regressions" but omits the natural synonyms/phrases users actually say ("E2E tests", "Playwright", "Cypress", "flaky tests", "smoke tests"); relevant keywords present but common variations missing.

3 / 5

Distinctiveness Conflict Risk

The E2E testing niche is reasonably distinct from unit/integration testing skills and unlikely to trigger for unrelated skills; minor overlap risk with general 'testing' or 'CI/CD' skills but mostly distinct.

4 / 5

Total

13

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.