CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudflare-browser-rendering

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-structured and highly actionable with copy-paste-ready code and a clean one-level-deep reference system. Weaker spots are verbose overview/restated concepts and missing explicit validation feedback loops in the primary workflow for batch/scraping operations.

Suggestions

Trim the 'Browser Rendering Overview' section — remove explanations of what screenshots/PDFs/scraping are that Claude already knows, keeping only Cloudflare-specific facts.

Add explicit validation checkpoints to the Quick Start workflow (e.g., try-finally cleanup, verify the screenshot/PDF succeeded, retry on timeout) so the batch/scraping flow has a validate-then-proceed feedback loop instead of listing safety items only in a checklist.

De-duplicate the Puppeteer-vs-Playwright comparison and trigger-term guidance, which currently appear in both the frontmatter keywords and multiple body sections.

DimensionReasoningScore

Conciseness

Mostly efficient with substantial executable code and API references, but the 'Browser Rendering Overview' section explains concepts Claude already knows (what screenshots/PDFs are) and the Puppeteer-vs-Playwright comparison and trigger guidance are repeated, which could be tightened.

3 / 5

Actionability

Quick Start and API sections provide copy-paste-ready TypeScript, wrangler.jsonc, install/deploy commands, and concrete issue solutions (keep_alive, XPath workaround, binding passthrough) that cover the common cases.

5 / 5

Workflow Clarity

Quick Start is a clear numbered sequence and issues follow an Error/Why/Prevention/Solution structure, but the main workflow lacks explicit validation/checkpoint feedback loops for risky batch scraping and SSRF-prone operations; the rubric caps batch/destructive workflows without embedded validation at 3.

3 / 5

Progressive Disclosure

Clear overview body with a 'When to Load References' trigger map and per-section 'Load references/X.md when ...' signals; all six referenced files exist and are one level deep, making navigation easy.

5 / 5

Total

16

/

20

Passed

Description

87%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 strong: it names a specific niche, lists concrete actions, and includes an explicit 'Use for' trigger clause covering both use cases and common errors. Main weakness is slight under-coverage of action synonyms and file extensions in the trigger terms.

DimensionReasoningScore

Specificity

Names the domain ('Cloudflare Browser Rendering with Puppeteer/Playwright') plus several concrete actions ('screenshots, PDFs, web scraping') and error conditions, but the action list is not exhaustive — minor coverage gaps keep it below a comprehensive 5.

4 / 5

Completeness

Explicitly states what the skill does (Cloudflare Browser Rendering with Puppeteer/Playwright) and provides an explicit 'Use for ...' clause with concrete trigger phrases including error conditions, satisfying both what and when.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('screenshots', 'PDFs', 'web scraping', 'rendering errors', 'timeout issues') alongside library names, with good but not comprehensive coverage — missing common synonyms and file extensions.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Cloudflare Browser Rendering via Puppeteer/Playwright) with distinct triggers, making overlap with unrelated skills unlikely.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/cloudflare-browser-rendering/skills/cloudflare-browser-rendering/SKILL.md

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.