pdf-page-verification-correction

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

Quality

61%

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

70%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 a strong, executable iteration workflow with excellent validation and feedback-loop clarity, but it is held back by redundant duplicate implementations and the absence of any progressive disclosure (everything inlined in a 220-line SKILL.md). It would score higher by trimming the duplicate library variant and moving the long code into a bundled script.

Suggestions

Remove the duplicate PyPDF2 verify_page_count variant (keep one) or move the alternative into a references file to tighten conciseness.

Move the full create_pdf_with_validation and ADJUSTMENT_STRATEGIES code into a scripts/ file referenced from SKILL.md, leaving only the workflow overview and a minimal example inline, to improve progressive disclosure.

Implement the 'expand' branch in adjust_params (or document why only 'shrink' is supported) so the actionability gap is closed.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable code with no over-explanation of PDF/library basics, but it pads with a duplicate verification implementation (fitz and PyPDF2 variants) and overlaps between the Tips and Common Adjustment Order sections, matching the score-3 anchor of mostly efficient with some tightening possible; not a 4 because the duplication is noticeable.	3 / 5
Actionability	Concrete, executable functions (verify_page_count, check_page_requirement, adjust_params, create_pdf_with_validation) with a copy-paste-ready example, but minor gaps remain: create_pdf is a `pass` stub and adjust_params only implements the 'shrink' direction, matching score-4 rather than the fully-covered score-5.	4 / 5
Workflow Clarity	A clearly sequenced 5-step workflow with an explicit validation checkpoint on every iteration (verify_page_count), a feedback loop (check -> adjust -> retry), and error recovery (failure dict after max_iterations), matching the score-5 anchor; the batch/iterative operation includes validation so the destructive-cap rule does not apply.	5 / 5
Progressive Disclosure	Section headers (When to Use, Prerequisites, Workflow Steps, Tips, Common Adjustment Order) give reasonable structure, but all ~220 lines are inlined with no references or bundle files, and the full code could live in a script; this matches the score-3 anchor of some structure with content that could be separated kept inline, and the under-50-line simple-skill exception does not apply.	3 / 5
	Total	15 / 20 Passed

Description

53%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 conveys a clear, specific purpose and a distinct niche, but it omits any 'Use when...' trigger guidance and lacks natural keyword variations, which together cap completeness and trigger quality at the midpoint. It reads as a competent what-statement without the when-statement that would make it reliably discoverable.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating PDFs that must fit a strict page limit (reports, maps, summaries) and the initial page count is uncertain.'

Include natural keyword variations users actually say — 'PDFs', '.pdf', 'page limit', 'too many pages', 'fit on one page' — to improve trigger term quality.

Consider naming the adjustment lever explicitly (e.g. 'by tuning image size, margins, fonts, and table density') to lift specificity toward several concrete actions.

Dimension	Reasoning	Score
Specificity	Names the PDF-page-count domain and two concrete actions ('verify PDF page counts', 'adjust layout parameters'), matching the score-3 anchor of 1-2 concrete actions without comprehensive coverage; not a 4 because it does not list several specific actions.	3 / 5
Completeness	It clearly states what the skill does ('verify PDF page counts and adjust layout parameters') but provides no 'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3, and 'until requirements are met' describes loop termination, not when to invoke the skill.	3 / 5
Trigger Term Quality	'PDF page counts' is a natural phrase, but common variations and synonyms users say (PDFs, .pdf, page limit, reduce pages) are absent, matching the score-3 anchor of relevant keywords missing common variations; not a 4 due to thin keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The PDF page-count verification/correction niche is mostly distinct with only minor overlap risk against general PDF skills, matching the score-4 anchor; not a 5 because trigger phrases that would fully distinguish it are missing.	4 / 5
	Total	13 / 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-page-verification-correction/SKILL.md
Commit: 3827781

Reviewed: 10 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.