pdf-size

Use when auditing a site that publishes downloadable PDFs (reports, white papers, legal documents, manuals). Applies to any site where PDFs are linked as indexable content resources.

Quality

53%

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 ./skills/pdf-size/SKILL.md

Quality

Content

57%

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 with good progressive disclosure to a real one-level reference file, and its guidance is concrete with precise byte thresholds. Its main weaknesses are redundancy between the 'Check' and 'Code Review' sections and the absence of any inline executable command.

Suggestions

Merge the 'Check' and 'Code Review' sections — they duplicate the HEAD-request/Content-Length/threshold guidance — into one section with the precise byte thresholds.

Include at least one inline executable command (e.g. a curl HEAD request or the Ghostscript compression one-liner) rather than delegating all code to the reference.

Tighten 'Explain' so it does not repeat the truncation fact already covered in the intro and Quick Reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basic concepts Claude already knows, but the 'Check' and 'Code Review' sections repeat nearly the same HEAD-request/Content-Length/threshold guidance, and 'Explain' reiterates the truncation fact already in the intro and Quick Reference, so it could be tightened.	2 / 3
Actionability	Guidance is concrete (specific byte thresholds 10,485,760 / 15,728,640, HEAD requests, Content-Length, named tools, 200/Content-Type checks), but all executable code is delegated to references/rule.md with no copy-paste command inline in the body, leaving it instruction-level rather than fully executable.	2 / 3
Workflow Clarity	A Check-then-Fix sequence is present and a verification step exists ('Verify PDF URLs return 200 status and appropriate Content-Type'), but the checkpoint is buried in the duplicated 'Code Review' section and there is no re-check-after-fix feedback loop, leaving the sequence present but checkpoints somewhat implicit.	2 / 3
Progressive Disclosure	The body is a well-organized overview (Quick Reference, Check, Fix, Explain, Code Review) that clearly signals a single one-level-deep reference ('see references/rule.md'), and that file exists and holds the deeper code/tables, giving easy navigation and an appropriate content split.	3 / 3
	Total	9 / 12 Passed

Description

50%

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 has an explicit 'Use when...' trigger and a clear domain, but it never states the concrete action (checking linked PDF sizes against Googlebot's truncation limits), leaving the 'what' vague. Trigger terms cover document types but miss the size/compression phrasing users would actually say.

Suggestions

State the concrete action explicitly, e.g. 'Checks linked PDF file sizes against Googlebot's crawl and truncation limits and flags oversized PDFs for compression or an HTML companion page.'

Add trigger terms users would naturally say, such as 'PDF too large', 'compress PDF', 'PDF not indexing', or 'PDF crawl budget'.

Make the 'what' as explicit as the 'when' — name the audit outcome (flag oversized PDFs, recommend compression) rather than only 'auditing a site that publishes downloadable PDFs'.

Dimension	Reasoning	Score
Specificity	It names the domain ('auditing a site that publishes downloadable PDFs (reports, white papers, legal documents, manuals)') but the actual action is left as the generic verb 'auditing' — it never states what is being audited (file size against crawl limits), so it is not a comprehensive list of concrete actions.	2 / 3
Completeness	The 'when' is explicit ('Use when auditing a site that publishes downloadable PDFs') but the 'what' is only implied — 'auditing' never says the skill checks PDF sizes against Googlebot limits and flags oversized files, so it does not clearly answer both what and when.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('downloadable PDFs', 'reports, white papers, legal documents, manuals') but misses the common variations a user would actually say for this task ('PDF too large', 'compress PDF', 'PDF not indexing', 'crawl budget').	2 / 3
Distinctiveness Conflict Risk	The PDF-SEO niche is somewhat specific, but the trigger 'auditing a site that publishes downloadable PDFs' is broad enough to overlap with general PDF-handling or broader SEO audit skills rather than carving a clearly distinct trigger.	2 / 3
	Total	8 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/pdf-size/SKILL.md
Commit: 48405aa

Reviewed: about 7 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.