Name: screenshots
Rating: 64.8 (1 reviews)
Author: administrakt0r

screenshots

Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.

Quality

77%

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

The canonical home for this skill is screenshots 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.

A highly actionable, well-sequenced skill body with executable code and a verification step, held back by verbosity and a monolithic single-file structure that should offload the script template and routing table into reference files.

Suggestions

Move the full Playwright script template into references/script-template.mjs and the framework routing table into references/routes.md, keeping SKILL.md as an overview with one-level-deep links to lift progressive_disclosure.

Trim Step 7's advanced options that duplicate logic already present in the main script template, or fold them into the template as documented fields, to improve conciseness.

Add an explicit feedback loop after Step 9: if any screenshot is missing or not 2880x1800, re-run the script for just those entries to lift workflow_clarity.

Dimension	Reasoning	Score
Conciseness	The ~395-line body is mostly efficient and avoids explaining concepts Claude already knows, but the full inline script template plus Step 7's advanced options (which repeat patterns already in the template) and verbose AskUserQuestion option lists could be trimmed.	3 / 5
Actionability	It provides a complete, mostly copy-paste-ready Playwright Node.js script with real selectors, plus concrete commands (mkdir, node, rm, sips/file) and ready-to-run snippets for element shots, full page, and dark mode, covering the common cases.	5 / 5
Workflow Clarity	Nine numbered steps give a clear sequence with a verification checkpoint in Step 9 (ls + pixel dimensions) and an Error Handling section, satisfying the batch-operation validation expectation; the gap is a missing explicit validate-and-retry feedback loop for failed captures.	4 / 5
Progressive Disclosure	The body is well sectioned by headers, but no bundle files exist and all ~400 lines (the full script template, framework routing table, advanced options) are inlined in SKILL.md rather than split into one-level-deep reference files.	3 / 5
	Total	15 / 20 Passed

Description

83%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 strong, third-person description that clearly answers both what it does and when to use it, with natural trigger terms and a distinct marketing-screenshot niche. Its only weakness is a narrow action vocabulary.

Dimension	Reasoning	Score
Specificity	"Generate marketing screenshots of your app using Playwright" names the domain, output type (marketing-quality), and tool concretely, but the action set is narrow (essentially one verb), leaving minor coverage gaps versus the anchor that lists several specific actions.	4 / 5
Completeness	It explicitly states the what ("Generate marketing screenshots of your app using Playwright") and the when ("Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation") with concrete trigger phrases, matching the anchor that requires both.	5 / 5
Trigger Term Quality	"Product Hunt, social media, landing pages, or documentation" plus "marketing-quality app screenshots" gives good natural keyword coverage users would say, though some synonyms (app store, app images, promo shots) are missing.	4 / 5
Distinctiveness Conflict Risk	"marketing screenshots of your app using Playwright" with Product Hunt / landing page triggers carves a clear niche with minimal conflict, but there is minor overlap risk with a generic browser-automation or Playwright screenshot skill.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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

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.