pdf-verification

Verify PDF page counts and file integrity programmatically using PyPDF2 after generation

Quality

71%

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 ./benchmarks/gdpval/skills/pdf-verification/SKILL.md

Quality

Content

81%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 content is highly actionable with executable scripts, clear sequencing, and explicit validation/feedback loops. Its main weakness is redundancy: four near-duplicate verification scripts that could be consolidated for better token efficiency.

Suggestions

Consolidate the four near-identical PdfReader scripts into one parameterized function covering single, multiple, and file-size checks to reduce duplication.

Move the optional file-size check and the final 'Example Task Completion Check' into a single canonical verification recipe rather than restating the same pattern.

Tighten the Purpose and Common Issues sections to avoid restating the same failure modes ('empty pages', 'corrupted files') across multiple sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining PDF/library basics, but it repeats near-identical PdfReader page-count scripts across four sections that could be consolidated into one parameterized example.	3 / 5
Actionability	All guidance is fully executable and copy-paste ready (pip install, complete Python scripts), with examples covering the common single-file, multi-file, file-size, and final-check cases.	5 / 5
Workflow Clarity	A clear install-then-verify sequence is paired with explicit validation (verify_pdf returns False on mismatch) and a real feedback loop ('If verification fails, regenerate before proceeding'), plus a best-practices checklist.	5 / 5
Progressive Disclosure	The skill is self-contained with well-organized section headers and no external references needed, but at ~157 lines the redundant script variants represent minor organization gaps that keep it below a 5.	4 / 5
	Total	17 / 20 Passed

Description

62%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 clear and reasonably specific about a post-generation PDF verification niche, with both a what and a when clause. It would benefit from broader natural trigger terms and a more explicit 'Use when...' phrasing.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when generating PDFs, when specific page counts are required, or before marking a PDF task complete.'

Broaden trigger terms to include synonyms and extensions users naturally say: 'PDFs', '.pdf files', 'document integrity', 'page count validation'.

Consider naming one more concrete capability (e.g. detecting corrupted or empty files) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the PDF domain and two concrete actions ('verify page counts and file integrity'), but coverage is limited to verification rather than a comprehensive action set, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	Clearly states what (verify page counts and file integrity) and provides an explicit when ('after generation'), though the trigger guidance could be more specific and uses no canonical 'Use when...' phrasing, so it does not reach 5.	4 / 5
Trigger Term Quality	Contains relevant natural terms ('PDF', 'page counts', 'file integrity') but is missing common variations and synonyms like 'PDFs', '.pdf', or 'document', fitting the some-keywords-but-missing-variants anchor.	3 / 5
Distinctiveness Conflict Risk	The post-generation verification niche is mostly distinct from general PDF skills, with only minor overlap risk; trigger breadth is too narrow for a 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-verification/SKILL.md
Commit: 3827781

Reviewed: 13 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.