webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Quality

68%

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 ./.agents/skills/webapp-testing/SKILL.md

The canonical home for this skill is webapp-testing in anthropics/skills

Quality

Content

71%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 concise, actionable, and well-sequenced with a useful decision tree and feedback branch, but its progressive disclosure is undermined by a Reference Files section that points to a non-existent examples/ directory. Fixing the broken references is the highest-impact improvement.

Suggestions

Create the referenced examples/ files (element_discovery.py, static_html_automation.py, console_logging.py) or remove the Reference Files section so no path is advertised that doesn't exist.

Replace the 'your_automation.py' placeholder with at least one complete end-to-end runnable example combining with_server.py with a full Playwright test to close the actionability gap.

Tighten the Best Practices section and inline code comments to remove redundancy, and fix the 'abslutely' typo, to push conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's Playwright knowledge (it does not explain what Playwright or headless mode is), but has minor over-explanation in inline code comments and slight redundancy in the Best Practices section, plus a typo ('abslutely'); this fits 'efficient; minor instances of over-explanation' rather than the fully lean 5 anchor.	4 / 5
Actionability	Provides copy-paste-ready with_server.py commands (single and multiple servers) and a complete Playwright automation snippet, matching 'mostly executable guidance with minor gaps'; the gap is the 'your_automation.py' placeholder and the Reconnaissance section showing fragments rather than a full runnable script, which keeps it below 5.	4 / 5
Workflow Clarity	A clear decision tree sequences the approach and includes an explicit feedback branch ('Fails/Incomplete -> Treat as dynamic') plus a networkidle pitfall checkpoint; the testing/interaction task is not destructive or batch, so the score-3 cap does not apply, but explicit verification of inspected output is only implicit, keeping it at 4 rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized and the scripts/with_server.py reference is real and correctly signaled (black-box, run --help first), but the 'Reference Files' section points to an examples/ directory (element_discovery.py, static_html_automation.py, console_logging.py) that does not exist in the bundle, so references are present but broken/undermining navigation.	3 / 5
	Total	15 / 20 Passed

Description

66%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 is specific and voice-appropriate with a clear 'what', but it omits any explicit 'Use when...' trigger guidance, which caps completeness and weakens trigger-term quality. Adding a concrete trigger clause would notably improve it.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when testing or debugging local web apps, capturing browser screenshots, or inspecting frontend/console behavior.'

Add natural synonyms users say, such as 'e2e', 'end-to-end testing', or 'web app', to broaden trigger coverage.

Mention key supporting verbs (e.g. form submission, network/log inspection) to round out the capability list toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('testing local web applications using Playwright') and lists four concrete actions ('verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs'), matching the 'several specific actions; minor gaps' anchor rather than 5 only because a few common testing tasks (e.g. form submission, network interception) are absent.	4 / 5
Completeness	Clearly answers 'what' but provides no explicit 'when should Claude use it' clause; per the rubric guideline, a missing 'Use when...' clause caps completeness at 3, so it does not reach 4.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('testing local web applications', 'UI behavior', 'browser screenshots', 'browser logs') plus the tool name 'Playwright'; falls short of 5 because synonyms like 'e2e', 'end-to-end', or 'web app' are missing.	4 / 5
Distinctiveness Conflict Risk	The Playwright + local-webapp-testing niche is mostly distinct with minor overlap risk against generic browser-automation skills; it lacks the explicit distinct trigger phrases that would lift it to 5.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: every-app/open-seo
Path: .agents/skills/webapp-testing/SKILL.md
Commit: 3632f40

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.