webapp-testing

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

Quality

61%

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

68%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 a well-structured, lean reference with an executable script and concrete config guidance, but its audit workflow lacks explicit validation checkpoints and there is no runnable Playwright spec example. Adding a verify-step to the audit flow and one real spec snippet would lift the weaker dimensions.

Suggestions

Insert an explicit verification checkpoint into the Deep Audit flow (e.g. "Scan: confirm each route returns 2xx/3xx before testing") so workflow clarity clears the score-3 cap.

Add one copy-paste-ready Playwright spec example (test() with data-testid selector and auto-wait assertion) to move actionability toward fully executable.

Drop or shrink the ASCII testing pyramid, which restates a concept Claude already knows, to push conciseness to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with almost no prose padding and assumes Claude's competence throughout, but the ASCII testing pyramid re-explains a concept Claude already knows, keeping it just below the lean-every-token-earns-its-place bar at 5.	4 / 5
Actionability	Provides copy-paste-ready script invocations ("python scripts/playwright_runner.py <url> --a11y") and concrete config values (Retries: 2 on CI, Trace: on-first-retry), but the bulk is principles/tables with no actual Playwright spec code example, leaving minor gaps versus the fully-executable anchor at 5.	4 / 5
Workflow Clarity	The Deep Audit sequence (Map → Scan → Test) and CI pipeline steps are listed, but there are no explicit validation/verification checkpoints (e.g. confirm routes respond before testing, assert exit code before uploading artifacts), matching the steps-listed-but-validation-gaps anchor at 3.	3 / 5
Progressive Disclosure	The body is well-organized into nine labeled sections and the one bundle file (scripts/playwright_runner.py) is referenced one level deep with clear usage and exists on disk, fitting the good-structure-clear-references anchor at 4 rather than 5 because the skill is a single inline reference rather than an overview pointing to multiple detailed materials.	4 / 5
	Total	15 / 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 names a clear domain and a couple of specific tools but lacks an inline trigger clause and relies on broad phrasing, so it lands around the midpoint. Moving the when_to_use trigger phrasing into the description and adding concrete actions would lift specificity and completeness.

Suggestions

Fold the trigger guidance into the description itself (e.g. append "Use when writing E2E tests with Playwright or auditing web app routes and user flows") so completeness is not capped at 3.

Replace the generic "testing principles / deep audit strategies" phrasing with concrete actions like "generate Playwright specs, map routes, run a11y checks" to raise specificity.

Add natural synonyms users say ("end-to-end tests", "browser automation", "flaky test debugging") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Web application testing principles") plus a couple of specific areas ("E2E, Playwright, deep audit strategies"), but these are topics rather than a comprehensive list of concrete actions, matching the score-3 anchor and falling short of the several-specific-actions bar at 4.	3 / 5
Completeness	The description field gives a clear "what" but no "when"/"Use when..." clause (that guidance lives in the separate when_to_use field), so per the missing-trigger-guidance cap it cannot exceed 3 and matches the clear-what-without-when anchor.	3 / 5
Trigger Term Quality	"E2E" and "Playwright" are natural terms users say, but common variations/synonyms ("end-to-end tests", "browser tests", "flaky tests") are absent and "deep audit strategies" is jargon, fitting the some-relevant-keywords-but-missing-variations anchor at 3 rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	The Playwright/E2E niche is mostly distinct from sibling skills with only minor overlap risk against generic testing skills, fitting the mostly-distinct anchor at 4 better than the clear-niche-minimal-conflict anchor at 5 because "Web application testing" still reads somewhat broad.	4 / 5
	Total	13 / 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
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: 211561c

Reviewed: 8 days 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.