Name: playwright-skill
Rating: 37.6 (1 reviews)
Author: administrakt0r

playwright-skill

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.

Quality

35%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/playwright-skill/SKILL.md

The canonical home for this skill is playwright-skill in administrakt0r/AI-Agents-Safe-Coding-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 highly actionable with many runnable examples and a clear, branched workflow, but it suffers from repetitive restatements of the same directives and references to bundle files (API_REFERENCE.md, lib/helpers.js, run.js) that are not actually present.

Suggestions

Consolidate the repeated directives (detect servers, /tmp, headless:false, parameterize URLs) into a single section and remove the restatements in 'How It Works', 'Execution Pattern', and 'Notes'.

Either include API_REFERENCE.md, lib/helpers.js, and run.js in the bundle or remove/qualify the references so they are not dangling.

Add an explicit validation checkpoint in the workflow (e.g., confirm the detected server responds before writing/running the script) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient code with no concept over-explanation, but the same directives (detect servers first, write to /tmp, headless:false, parameterize URLs) are restated across 'CRITICAL WORKFLOW', 'How It Works', 'Execution Pattern', 'Tips', and 'Notes', which could be tightened; not a 2 because the bulk is actionable code rather than fluff.	3 / 5
Actionability	It provides many complete, copy-paste-ready JavaScript examples (screenshot, login, form, broken-links, responsive) plus exact commands ('cd $SKILL_DIR && node run.js ...') covering the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	There is a clear numbered sequence with a server-detection decision branch (1/multiple/none servers), but no explicit validate-then-proceed checkpoint or error-recovery feedback loop, so it sits at 'clear sequence with most checkpoints; minor validation gaps' rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized and advanced content is pointed to API_REFERENCE.md (one level deep, clearly signaled), but that file plus lib/helpers.js and run.js are not present in the bundle (no references/, scripts/, or assets/ dirs), leaving dangling references and inline example bulk that could be split.	3 / 5
	Total	15 / 20 Passed

Description

0%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 path-resolution boilerplate that never states the skill's purpose (Playwright browser automation) or its triggers, failing all four dimensions. It should be rewritten to describe capabilities and use-conditions.

Suggestions

Rewrite the description to state the skill's purpose, e.g. 'Automates browser tasks with Playwright: write and run custom scripts for testing, screenshots, form/login flows, and link checks.'

Add an explicit 'Use when...' trigger clause naming natural terms users say: browser automation, Playwright, UI testing, screenshots, login flows, broken links.

Move the path-resolution guidance into the body; keep the description focused on what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	The description only covers path-resolution mechanics ("determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below") and names zero concrete browser-automation actions, matching the 'entirely vague; no concrete actions' anchor.	1 / 5
Completeness	Neither what the skill does nor when to use it is stated; the text is exclusively about command-path resolution, so both 'what' and 'when' are missing per the cap guidance.	1 / 5
Trigger Term Quality	It contains no natural trigger terms a user would say (no 'browser', 'Playwright', 'test', 'automate', 'screenshot'); only generic installation/path jargon appears, matching the 'no natural keywords' anchor.	1 / 5
Distinctiveness Conflict Risk	The text is generic boilerplate ("This skill can be installed in different locations...") that could prefix virtually any skill, guaranteeing high overlap/conflict risk.	1 / 5
	Total	4 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/playwright-skill/SKILL.md
Commit: 57c135b

Reviewed: 3 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.