browser-e2e-tester

Browser-based E2E testing for feature verification. Use when running end-to-end tests, validating features in browser, verifying user flows, or testing feature completion.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-e2e-tester/SKILL.md

Quality

Content

65%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 concise, actionable overview with real executable snippets and a clear workflow, but it is held back by missing validation/feedback checkpoints in the workflow and a broken reference file listed in the body.

Suggestions

Add explicit validation checkpoints and a feedback loop to the workflow (e.g. verify the test server is up before executing; on failure capture artifacts and retry/re-report) so the SETUP→EXECUTE→VERIFY→REPORT flow supports destructive or batch test runs.

Fix the broken reference: either create references/BROWSER-AUTOMATION.md or remove the pointer from the References section so navigation is reliable.

Make the Quick Start snippet fully self-contained by showing how project_dir is obtained and what to import beyond E2ETester, so the example runs without inference.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — no padded explanations of what E2E testing is, no library tutorials — with tight code, dataclass, and table blocks; only minor decorative restatement in the ASCII workflow keeps it from a 5.	4 / 5
Actionability	Quick Start gives copy-paste-ready Python ('from scripts.e2e_tester import E2ETester; tester = E2ETester(project_dir); result = await tester.test_feature("auth-001")'), a concrete TestResult dataclass, a JSON acceptance format, and a frameworks table, with only minor gaps (e.g. project_dir and imports undefined) preventing a 5.	4 / 5
Workflow Clarity	The four-phase SETUP→EXECUTE→VERIFY→REPORT sequence is clear, but the workflow lacks explicit validation checkpoints and feedback loops (no server-started check, no validate→fix→retry on failure, no flake-retry guidance in the body); for a batch/risky test-execution skill the rubric caps this at 3.	3 / 5
Progressive Disclosure	Structure and signaling are decent with one-level-deep references and a per-purpose script list, but the body advertises 'references/BROWSER-AUTOMATION.md' which does not exist on disk, breaking navigation and leaving it at anchor 3 rather than the well-organized anchor 4-5.	3 / 5
	Total	14 / 20 Passed

Description

78%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-formed description that clearly states both capability and triggering contexts in third person. The main weakness is specificity: its enumerated actions are largely synonyms rather than a diverse, concrete action set.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Browser-based E2E testing for feature verification') but its actions ('running end-to-end tests', 'validating features', 'verifying user flows', 'testing feature completion') are near-synonymous verb clusters rather than several distinct concrete actions, matching anchor 3 and falling short of the comprehensive multi-action coverage of anchor 5.	3 / 5
Completeness	It explicitly answers both 'what' (Browser-based E2E testing for feature verification) and 'when' (Use when running end-to-end tests, validating features in browser, verifying user flows, or testing feature completion) with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	It includes natural phrases users would say ('running end-to-end tests', 'validating features in browser', 'verifying user flows', 'testing feature completion') with good keyword coverage, but stops short of the comprehensive synonym/extension coverage (e.g. 'E2E', 'browser tests') that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	The browser-based E2E-testing niche is mostly distinct with specific triggers, though it could minorly overlap with general test-runner or verification skills, fitting anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/browser-e2e-tester/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.