webapp-testing

Web application testing principles. E2E, Playwright, deep audit strategies.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/webapp-testing/SKILL.md

Quality

Content

57%

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

The body is well-structured and points cleanly to a real runtime script, but it leans on generic testing principles Claude already knows and lacks executable E2E code plus explicit validation feedback loops. Tightening to project-specific guidance with a sample spec and a retry loop would raise the weaker dimensions.

Suggestions

Trim generic best-practice lists (testing pyramid, basic E2E dos/don'ts) in favor of project-specific guidance Claude would not already know.

Add a copy-paste-ready Playwright spec example instead of only naming conventions like "user-can-checkout.spec.ts".

Insert a validate→fix→retry loop after the runner script (e.g. re-run on failure after fixing the cause) to give the workflow explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	The body uses lean tables with little prose padding, but a large share (testing pyramid, "use data-testid", "wait for elements", anti-patterns) restates generic testing knowledge Claude already has, fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the every-token-earns-its-place level 3.	2 / 3
Actionability	It gives an executable runner command ("python scripts/playwright_runner.py <url> --a11y") and concrete Playwright config values, but offers no actual E2E test code/spec example beyond naming patterns, matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The deep-audit flow is sequenced (Map → Scan → Test) and CI steps are listed, but there are no explicit validation checkpoints or a validate→fix→retry feedback loop after running tests, which caps the score at 2 per the guidelines.	2 / 3
Progressive Disclosure	Content is organized into clearly numbered sections and the only external artifact (scripts/playwright_runner.py, a real file) is signaled with a one-level reference table, matching the 'clear overview with well-signaled one-level-deep references' anchor with no nested references.	3 / 3
	Total	9 / 12 Passed

Description

57%

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 identifies a clear, distinctive niche but stops at naming concepts rather than concrete actions and omits an explicit 'Use when...' trigger. Adding a trigger clause and a few action verbs would lift completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. "Use when writing E2E tests with Playwright, auditing web app routes, or testing user flows."

Replace abstract nouns with concrete actions (e.g. "Scan routes, run Playwright specs, audit accessibility") to raise specificity.

Add common trigger variations like "end-to-end tests", "browser automation", and "test user flows" for broader natural-term coverage.

Dimension	Reasoning	Score
Specificity	Phrases like "Web application testing principles" and "E2E, Playwright, deep audit strategies" name the domain and some concepts, but list no concrete actions (e.g. scan, run, assert), matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill covers (testing principles, E2E, Playwright, audits) but has no explicit "Use when..." trigger clause, so per the guidelines completeness is capped at 2 even though the what-side is clear.	2 / 3
Trigger Term Quality	"E2E" and "Playwright" are natural terms users say, but common variations like "end-to-end tests", "browser testing", and "test user flows" are absent, fitting the 'some relevant keywords but missing common variations' anchor and falling short of the broad level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	The E2E/Playwright/web-app-audit framing is a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the level-3 anchor; it is more specific than the overlapping level-2 example.	3 / 3
	Total	9 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/webapp-testing/SKILL.md
Commit: 04514f0

Reviewed: about 11 hours 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.