html-to-pdf

Convert HTML files or URLs to high-fidelity PDFs using Puppeteer; auto-detects or forces RTL for Hebrew/Arabic when RTL content is present.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/html-to-pdf/SKILL.md

Quality

Content

75%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 copy-paste commands, a complete worked example, and a genuine error-recovery feedback loop, and it correctly references real bundle files. Its weakest point is conciseness: substantial generic governance boilerplate and a self-contradicting validation section add tokens without PDF-specific value.

Suggestions

Remove or collapse the generic governance boilerplate (When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, Quick Validation, Deterministic Output Rules, Completion Checklist) that is not specific to HTML→PDF conversion.

Resolve the contradiction between the 'Validation Shortcut' (run scripts/validate_skill.py --help) and the 'Quick Validation' section claiming 'No local script validation step is required'.

Consider moving the full 44-line single-page HTML example into a references/ file (e.g. examples/single-page.html) referenced from the body to tighten SKILL.md further.

Dimension	Reasoning	Score
Conciseness	The PDF-specific core (CLI table, RTL handling, page-fit rule, verification loop) is lean and assumes competence, but ~8 generic governance sections (When Not to Use, Output Contract, Validation and Safety Rules, Deterministic Output Rules, Completion Checklist, etc.) are template boilerplate, and the 'Quick Validation' section self-contradicts ('No local script validation step is required' despite a Validation Shortcut that runs the validator).	3 / 5
Actionability	Seven numbered copy-paste-ready commands cover install, local→PDF, URL→PDF, RTL, stdin, executable-path, and a complete single-page A4 HTML example, plus a CLI parameter table with defaults — fully executable and covering the common cases.	5 / 5
Workflow Clarity	The 'Verification workflow' provides an explicit 5-attempt feedback loop (default → reduce scale → reduce margin → both → fix HTML/CSS) with visual validation checks, but the primary 'Recommended Workflow' uses vague validation ('Run a final validation pass') and the contradictory 'Quick Validation' section leaves a minor checkpoint gap.	4 / 5
Progressive Disclosure	Well-organized into clear section headers, and the heavy implementation is appropriately externalized to real, correctly-referenced bundle files (assets/html-to-pdf.js, scripts/validate_skill.py) at one level deep; minor gaps are the inlined full HTML example and governance boilerplate that could be trimmed or split.	4 / 5
	Total	16 / 20 Passed

Description

66%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 specific and distinct, clearly stating what the skill does and naming its niche (Puppeteer-based HTML/URL→PDF with RTL handling). Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when converting a web page or HTML file to a PDF, generating print-ready invoices/reports, or producing Hebrew/Arabic (RTL) PDFs.'

Include file extensions and synonyms among trigger terms (e.g. '.html', '.pdf', 'web page to PDF') to improve trigger_term_quality toward 5.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Convert HTML files or URLs to high-fidelity PDFs using Puppeteer' and 'auto-detects or forces RTL for Hebrew/Arabic' — with minor coverage gaps (no mention of headers/footers or multi-page options).	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause, so completeness is capped at 3 per the rubric; the 'when RTL content is present' phrase is a sub-feature condition, not a usage trigger.	3 / 5
Trigger Term Quality	Contains natural terms a user would say — 'HTML files', 'URLs', 'PDFs', 'Hebrew/Arabic', 'RTL' — but omits file extensions (.html, .pdf) and common synonyms like 'web page to PDF'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (HTML/URL→PDF via Puppeteer with RTL support) with minor overlap risk against generic PDF skills; lacks the explicit trigger clause that would make it a 5.	4 / 5
	Total	15 / 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: aipoch/medical-research-skills
Path: scientific-skills/Other/html-to-pdf/SKILL.md
Commit: 63c61d3

Reviewed: 10 hours 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.