pdf-verification-check

Verify generated PDFs for integrity and page count using PyPDF2 before task completion.

Quality

67%

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-check/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers an executable, well-sequenced verification workflow with a clear validate-and-remediate feedback loop, organized into clean sections. Its only weakness is mild redundancy in the Integration Example and Rules that could be trimmed for token efficiency.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean (steps plus a single executable script), but the 'Integration Example' duplicates the script as a truncated '# ... insert logic here ...' stub and the Rules section restates the steps, so it could be tightened.	2 / 3
Actionability	The verification script is complete, executable Python using PdfReader, with a concrete files_to_check map and a sys.exit status code, making it copy-paste ready.	3 / 3
Workflow Clarity	The four-step sequence (Identify, Run, Validate, Remediate) is explicitly ordered with a validation checkpoint and a feedback loop (fix and regenerate on failure), matching the highest anchor.	3 / 3
Progressive Disclosure	This is a single-purpose skill with no bundle files and well-organized sections (When to Use, Steps, Script, Rules, Dependencies); per the simple-skill guideline, clear organization earns the top score without external references.	3 / 3
	Total	11 / 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 is clear and third-person, naming a concrete domain and actions, but it lacks an explicit 'Use when' trigger and broad natural-term coverage, leaving it solidly mid-tier rather than exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating PDFs and verifying output integrity or page counts before declaring a task complete.'

Broaden trigger terms to include natural user phrasings like 'PDF files', '.pdf', or 'check the PDF'.

Name additional concrete actions (e.g. detect corrupted/empty files) to raise specificity.

Dimension	Reasoning	Score
Specificity	The phrase 'Verify generated PDFs for integrity and page count using PyPDF2' names the domain and two concrete actions (integrity check, page count), but it stops short of listing multiple distinct capabilities.	2 / 3
Completeness	The 'what' is explicit (verify integrity and page count), and 'before task completion' gestures at a 'when', but there is no explicit 'Use when...' trigger clause, which caps completeness per the guidelines.	2 / 3
Trigger Term Quality	It surfaces relevant terms like 'generated PDFs', 'page count', and 'integrity', but omits common natural variations a user might say such as '.pdf', 'PDF files', or 'verify PDF'.	2 / 3
Distinctiveness Conflict Risk	The niche is fairly specific (post-generation PDF verification), but it could still overlap with general PDF-generation or PDF-manipulation skills that also touch on output checking.	2 / 3
	Total	8 / 12 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-check/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.