playwright-pom

Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.

Quality

57%

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/playwright/pom/SKILL.md

Quality

Content

53%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 lean, well-organized index that respects token budget completely, but it delegates everything to two guide files that do not exist in the bundle, leaving the skill with no usable content. What remains is a clear table of contents pointing at nothing.

Suggestions

Add the referenced guide files (page-object-model.md and pom-vs-fixtures-vs-helpers.md) to the bundle so the index links resolve; a progressive-disclosure structure is only as good as the files it points to.

Include a minimal quick-start inline (e.g., a short page-object example or a one-line rule of thumb for POM vs fixtures) so the skill retains some actionable value even before the guides are read.

Add a one-line "when to read which guide" cue per table row so the single navigation step carries a concrete decision rule rather than topic labels alone.

Dimension	Reasoning	Score
Conciseness	The body is ~18 lines of purely navigational content with zero padding or explanation of concepts Claude already knows — every token (title, tagline, guide count, index table) earns its place.	5 / 5
Actionability	The body contains no concrete code, commands, or actionable guidance — it only describes what the guides cover ("covering Page Object Model implementation and the decision framework") and links out, and even that minimal pointer cannot be executed because the referenced files do not exist in the bundle.	2 / 5
Workflow Clarity	The single action — pick the appropriate guide from a well-labeled two-row table — is unambiguous, but there is no sequencing, no guidance on applying the guides' content, and the only available step (open a guide) fails at runtime since the linked files are absent; this sits between anchor 2's broken rough sequence and anchor 4's clear steps.	3 / 5
Progressive Disclosure	The structure is nominally the ideal anchor-5 shape (concise overview, one-level-deep, clearly signaled guide index), but both referenced paths — [page-object-model.md](page-object-model.md) and [pom-vs-fixtures-vs-helpers.md](pom-vs-fixtures-vs-helpers.md) — are dangling: no bundle files exist in references/, scripts/, assets/, or alongside SKILL.md, so navigation and the content split the structure promises are broken.	2 / 5
	Total	12 / 20 Passed

Description

61%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 concise, distinct, third-person description that clearly states the domain and the decision-framework angle, but it lacks an explicit "Use when..." invocation trigger, which caps its completeness. Trigger keyword coverage is good within the niche, though a few natural user phrasings are absent.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about page objects, structuring Playwright tests, or choosing between POM, fixtures, and helpers for test organization."

Include one or two more natural trigger phrases users would actually say, such as "organize Playwright tests" or "test code maintainability", to broaden keyword coverage.

Anchor the "what" with a couple of concrete actions (e.g. "structure page objects, convert tests to POM, decide between fixtures and helpers") so capabilities read as actions rather than topic areas.

Dimension	Reasoning	Score
Specificity	"when to use POM, how to structure page objects, and when fixtures or helpers are a better fit" names the domain plus specific topic areas, but these are topics rather than the multiple concrete actions of anchor 4 — coverage is not comprehensive.	3 / 5
Completeness	The "what" is clear ("Page Object Model patterns for Playwright... how to structure page objects"), but the "when to use POM / when fixtures or helpers are a better fit" phrases are in-domain decision guidance, not skill-invocation triggers — no "Use when..." clause or equivalent explicit trigger guidance exists, capping completeness at 3.	3 / 5
Trigger Term Quality	Natural keywords are well covered — "Page Object Model", "POM", "Playwright", "page objects", "fixtures", "helpers" — including the acronym synonym, but a few natural user phrases like "structure Playwright tests" or "test maintainability" are missing.	4 / 5
Distinctiveness Conflict Risk	"Page Object Model patterns for Playwright" carves out a clear niche with distinct triggers and only minor overlap risk with a general Playwright-testing skill; it is not fully minimal-conflict because any Playwright test-organization question could plausibly route here.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/playwright/pom/SKILL.md
Commit: a2e6ee3

Reviewed: 2 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.