CtrlK
BlogDocsLog inGet started
Tessl Logo

author-e2e-tests

Use when writing or maintaining Playwright e2e tests for Positron -- new test files, test cases, test infrastructure, or performance/metric tests. For a named test that is already failing or flaking, in CI or on your machine, use debug-e2e-test instead.

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

78%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-organized, actionable skill body that keeps the overview tight and pushes detail into a verified reference bundle. Tightening the duplicated fixtures/mistakes summaries and adding an explicit validate-then-retry loop for risky changes would push it higher.

Suggestions

Consolidate the 'Quick Reference: Available Fixtures' table and 'Common Mistakes' list to point earlier/only at references/fixtures.md and references/common-mistakes.md to reduce body duplication.

Add an explicit validate-fix-retry checkpoint (e.g. run the targeted test, and on failure re-check imports/suiteId/tags before retrying) for the destructive/risky workflow cap.

Inline one concrete POM method-call example (e.g. app.workbench.console.executeCode) so the most common interaction does not require opening references/page-objects.md.

DimensionReasoningScore

Conciseness

Efficient and assumes Claude's Playwright knowledge -- no padding about what e2e tests are -- but sections like the fixtures table and 'Critical/Quality issues' lists restate content also covered in references, leaving minor trimming opportunities.

4 / 5

Actionability

Provides a copy-paste-ready file template, concrete fixture signatures, and exact run commands, with minor gaps (e.g. some POM method names are deferred to source rather than shown).

4 / 5

Workflow Clarity

The 'Start Here: Read a Neighbor Test' -> structure -> tags -> run sequence is clear with explicit checkpoints (verify method names against source, never guess), though destructive/batch validation is implicit rather than a formal validate-fix-retry loop.

4 / 5

Progressive Disclosure

SKILL.md is a lean overview with clearly signaled one-level-deep references to six real bundled files under references/ (verified to exist); navigation is explicit and no references nest beyond one level.

5 / 5

Total

17

/

20

Passed

Description

87%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-scoped description that clearly states what the skill does and when to use it, with a clean boundary against a related debugging skill. Minor gains are possible by widening the natural trigger-term vocabulary.

DimensionReasoningScore

Specificity

Names concrete actions ('writing or maintaining Playwright e2e tests') and enumerates specific artifacts ('new test files, test cases, test infrastructure, or performance/metric tests'); minor gaps since it stops just short of a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ('writing or maintaining Playwright e2e tests') and when ('Use when writing or maintaining... new test files, test cases, test infrastructure, or performance/metric tests') with concrete trigger phrases and a disambiguating 'use debug-e2e-test instead' boundary.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('e2e tests', 'Playwright', 'failing or flaking', 'performance/metric tests') plus file-extension-adjacent phrasing, but misses a few common synonyms like 'integration tests' or explicit .test.ts triggers.

4 / 5

Distinctiveness Conflict Risk

Niche is tightly scoped to Positron Playwright e2e authoring, and the explicit hand-off to debug-e2e-test for failing/flaking tests minimizes overlap with the sibling skill.

5 / 5

Total

18

/

20

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
posit-dev/positron
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.