CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/screenshots/SKILL.md

The canonical home for this skill is screenshots in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

52%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 skill provides a thorough, actionable guide for generating marketing screenshots with Playwright, including a solid script template and clear multi-step workflow. However, it is significantly over-long, inlining extensive framework-specific routing tables, component discovery checklists, and advanced options that should either be in separate files or omitted entirely since Claude can infer much of this. The monolithic structure and verbosity are its primary weaknesses.

Suggestions

Extract the framework routing table (Step 3.2), advanced screenshot options (Step 7), and the full script template into separate referenced files to improve progressive disclosure and reduce the main file's token footprint.

Remove or drastically condense sections that explain things Claude already knows: common localhost ports, what dashboard components are, how to identify marketing assets in a codebase, and the tips section which largely restates earlier content.

Fix the script template placeholders to be valid JavaScript (e.g., use `const AUTH = { needed: false, ... }` instead of `[true|false]`) so the template is truly copy-paste ready.

Add an explicit validation checkpoint after running the script: check that files exist, are non-zero size, and have expected dimensions before presenting results to the user, with a retry path if screenshots are blank or incorrect.

DimensionReasoningScore

Conciseness

The skill is significantly verbose at ~250+ lines. It over-explains many things Claude already knows (how to read routes in various frameworks, what dashboard components are, common localhost ports). The framework routing table, component discovery checklist, and marketing asset hints are largely unnecessary padding. The tips section at the end restates things already covered.

2 / 5

Actionability

The skill provides a complete, executable Playwright script template with concrete code for authentication, screenshot capture, and verification. The script is copy-paste ready with clear placeholders. Minor gap: the script template uses placeholder syntax like `[true|false]` and `[APP_URL]` which aren't valid JS, requiring Claude to adapt rather than directly execute.

4 / 5

Workflow Clarity

The 9-step workflow is clearly sequenced with logical progression from prerequisites through verification. Step 9 includes verification commands. However, there's no explicit error recovery loop — if screenshots come out wrong (blank pages, missing content, wrong resolution), there's no validate-fix-retry cycle. The error handling section lists problems but doesn't integrate them into the workflow as checkpoints.

4 / 5

Progressive Disclosure

Everything is inlined into a single massive file with no references to supporting files. The framework routing table (Step 3.2), advanced screenshot options (Step 7), and the full script template could all be split into separate reference files. For a skill this long, the monolithic structure makes it hard to navigate and wastes context window on sections that may not be relevant to a given invocation.

2 / 5

Total

12

/

20

Passed

Description

82%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.

This is a solid skill description with a clear 'Use when' clause that provides concrete trigger scenarios. Its main weakness is the lack of specificity about what capabilities the skill offers beyond basic screenshot generation—it could benefit from listing specific features like device framing, viewport customization, or annotation. The description is concise and uses proper third-person voice.

Suggestions

Add 2-3 more specific capabilities beyond 'generate screenshots', such as 'apply device frames, customize viewport sizes, add annotations' to improve specificity.

Include additional trigger terms like 'mockups', 'app store screenshots', 'promotional images', or 'hero images' to capture more user intent variations.

DimensionReasoningScore

Specificity

Names the domain (marketing screenshots) and one concrete action (generate screenshots using Playwright), but doesn't elaborate on specific capabilities like annotations, device frames, multiple viewport sizes, or other features.

3 / 5

Completeness

Clearly answers both 'what' (generate marketing screenshots of your app using Playwright) and 'when' (Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation) with explicit trigger phrases.

5 / 5

Trigger Term Quality

Includes good natural trigger terms like 'screenshots', 'Product Hunt', 'social media', 'landing pages', 'documentation', and 'Playwright'. Missing some variations like 'app store screenshots', 'promotional images', 'hero images', or 'mockups'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive niche combining marketing screenshots with Playwright automation. Unlikely to conflict with general screenshot tools, generic Playwright testing skills, or general marketing skills due to the specific combination of purpose and tool.

5 / 5

Total

17

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.