pdf-page-verification-correction

Iterative workflow to verify PDF page counts and adjust layout parameters until requirements are met

Quality

63%

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-page-verification-correction/SKILL.md

Quality

Content

77%

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 a clear, validated workflow and a real feedback loop. Its main weaknesses are a monolithic single-file structure and modest redundancy that could be tightened.

Suggestions

Split the detailed adjustment strategies and full reference code into a references file (e.g., ADJUSTMENT_STRATEGIES.md) and link to it from the main body to improve progressive disclosure.

Remove the restated-intro sentence that duplicates the frontmatter description to tighten conciseness.

Keep only the most representative verification snippet (fitz or PyPDF2) inline and move the alternative into a reference, reducing token weight.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight, executable code, but the opening line restates the description and the ~225-line volume is high for a single iterative loop, so it could be trimmed.	2 / 3
Actionability	It provides fully executable fitz/PyPDF2 page-counting code, concrete adjustment strategies, and a copy-paste-ready create_pdf_with_validation loop with structured return values.	3 / 3
Workflow Clarity	The 5-step sequence (Create, Verify, Compare, Adjust, Iterate) includes an explicit validation checkpoint and a create-verify-adjust feedback loop with success/failure handling.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a monolithic 225-line single file with reference code and adjustment strategies inline and no split-out references for navigation.	2 / 3
	Total	10 / 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 clearly conveys what the skill does but omits any explicit "Use when..." trigger guidance, capping completeness. Trigger terms are only partially aligned with natural user phrasing.

Suggestions

Add an explicit "Use when..." clause naming natural trigger phrases (e.g., "Use when a generated PDF exceeds a target page limit or must fit a fixed page count").

Expand the action list from two verbs to multiple concrete operations (e.g., verify, count, adjust layout, shrink margins/fonts/images) to lift specificity.

Mirror common user phrasings like "PDF too many pages", "fit PDF to N pages", or "reduce PDF page count" for better trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names concrete actions ("verify PDF page counts" and "adjust layout parameters") but does not enumerate multiple specific actions as the score-3 anchor requires.	2 / 3
Completeness	It clearly answers "what" (verify and adjust PDF page counts) but has no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	"PDF page counts" is a term a user might say, but "iterative workflow" and "layout parameters" are technical phrasings and common user variants (e.g. "PDF too long", "fit on one page") are missing.	2 / 3
Distinctiveness Conflict Risk	The page-count-control niche is fairly specific, but the absence of explicit distinct triggers means it could still overlap with general PDF skills.	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-page-verification-correction/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.