Agent skill

PDF Page Verification Correction

by HKUDS in HKUDS/OpenSpace

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

MITAuto-check passedDocuments & Office

Install PDF Page Verification Correction

skills CLI
$ npx skills add HKUDS/OpenSpace --skill pdf-page-verification-correction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/OpenSpace pdf-page-verification-correction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/pdf-page-verification-correction .claude/skills/pdf-page-verification-correction && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pdf-page-verification-correction
GitHub stars
7.8k
Token cost
~1.5k tokens
SKILL.md length
230 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 5 steps: Initial PDF Creation → Verify Page Count → Compare Against Target → …
  • Tasks that involve PDF
  • SKILL.md covers When to Use, Prerequisites, Workflow Steps and Example Usage, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

PDF Page Verification Correction is an agent skill from HKUDS/OpenSpace. Iterative workflow to verify PDF page counts and adjust layout parameters until requirements are met

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Documents & Office, covering PDF. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

When your agent uses it

  • Tasks that involve PDF

Example prompts

  • “/pdf-page-verification-correction”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Initial PDF Creation
  2. Verify Page Count
  3. Compare Against Target
  4. Adjust Layout Parameters
  5. Iterative Correction Loop

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PDF Page Verification Correction loads about 1.5k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 230 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 230 words, ~1,545 tokens.

Download SKILL.mdSave it as .claude/skills/pdf-page-verification-correction/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pdf-page-verification-correction
description
Iterative workflow to verify PDF page counts and adjust layout parameters until requirements are met

PDF Page Count Verification and Correction

This skill provides a systematic approach to ensure PDFs meet target page count requirements through iterative verification and layout adjustment.

When to Use

  • Creating PDFs with strict page limits (e.g., reports, summaries, maps)
  • When initial PDF generation may produce variable page counts
  • When layout elements (images, tables, text) can cause unpredictable overflow

Prerequisites

  • Python with PyPDF2 or fitz (PyMuPDF) installed
  • PDF generation capability (ReportLab, matplotlib, etc.)

Workflow Steps

Step 1: Initial PDF Creation

Generate the PDF with your initial layout parameters:

python
def create_pdf(output_path, params):
    """Create PDF with given layout parameters"""
    # Your PDF generation logic here
    # params can include: image_size, table_density, font_size, margins
    pass
Step 2: Verify Page Count

Check the generated PDF's page count:

python
import fitz  # PyMuPDF

def verify_page_count(pdf_path):
    """Return the number of pages in the PDF"""
    doc = fitz.open(pdf_path)
    page_count = len(doc)
    doc.close()
    return page_count

# Alternative with PyPDF2
from PyPDF2 import PdfReader

def verify_page_count_pypdf2(pdf_path):
    reader = PdfReader(pdf_path)
    return len(reader.pages)
Step 3: Compare Against Target
python
def check_page_requirement(actual, target_max, target_exact=None):
    """
    Check if page count meets requirements
    
    Returns: (meets_requirement, adjustment_needed)
    """
    if target_exact is not None:
        meets = (actual == target_exact)
        direction = "shrink" if actual > target_exact else "expand" if actual < target_exact else None
    else:
        meets = (actual <= target_max)
        direction = "shrink" if actual > target_max else None
    
    return meets, direction
Step 4: Adjust Layout Parameters

If page count exceeds target, adjust one or more parameters:

python
# Common adjustment strategies
ADJUSTMENT_STRATEGIES = {
    'images': {
        'action': 'reduce_size',
        'param': 'image_scale',
        'step': 0.1,  # Reduce by 10%
        'min': 0.5
    },
    'tables': {
        'action': 'reduce_density',
        'param': 'rows_per_page',
        'step': 2,  # Reduce by 2 rows per page
        'min': 5
    },
    'fonts': {
        'action': 'reduce_size',
        'param': 'font_size',
        'step': 1,  # Reduce by 1pt
        'min': 8
    },
    'margins': {
        'action': 'reduce',
        'param': 'margin_inches',
        'step': 0.1,  # Reduce by 0.1 inches
        'min': 0.3
    }
}

def adjust_params(current_params, direction, strategy='images'):
    """Apply adjustment to parameters"""
    adjusted = current_params.copy()
    strat = ADJUSTMENT_STRATEGIES[strategy]
    
    if direction == 'shrink':
        param = strat['param']
        current_val = adjusted.get(param, 1.0)
        new_val = max(current_val - strat['step'], strat['min'])
        adjusted[param] = new_val
    
    return adjusted
Step 5: Iterative Correction Loop
python
def create_pdf_with_validation(
    output_path, 
    initial_params, 
    target_max_pages,
    max_iterations=5
):
    """
    Create PDF with iterative page count verification and correction
    
    Args:
        output_path: Where to save the final PDF
        initial_params: Starting layout parameters
        target_max_pages: Maximum allowed pages
        max_iterations: Maximum adjustment attempts
    
    Returns:
        dict with 'success', 'final_page_count', 'iterations', 'final_params'
    """
    params = initial_params.copy()
    
    for iteration in range(max_iterations):
        # Create PDF
        create_pdf(output_path, params)
        
        # Verify
        page_count = verify_page_count(output_path)
        
        # Check requirements
        meets_req, direction = check_page_requirement(
            page_count, target_max_pages
        )
        
        if meets_req:
            print(f"✓ PDF created successfully: {page_count} pages")
            return {
                'success': True,
                'final_page_count': page_count,
                'iterations': iteration + 1,
                'final_params': params
            }
        
        # Adjust and retry
        print(f"Iteration {iteration + 1}: {page_count} pages (need ≤{target_max_pages})")
        params = adjust_params(params, direction)
    
    # Failed to converge
    return {
        'success': False,
        'final_page_count': page_count,
        'iterations': max_iterations,
        'final_params': params,
        'error': f"Failed to meet page requirement after {max_iterations} iterations"
    }

Example Usage

python
# Initial parameters
params = {
    'image_scale': 1.0,
    'font_size': 10,
    'margin_inches': 0.5,
    'rows_per_page': 15
}

# Create map PDF limited to 1 page
result = create_pdf_with_validation(
    output_path='property_map.pdf',
    initial_params=params,
    target_max_pages=1,
    max_iterations=5
)

if not result['success']:
    # Consider more aggressive adjustments or content reduction
    print(f"Warning: {result['error']}")

Tips

  1. Prioritize adjustments: Start with less intrusive changes (margins, image scale) before more significant ones (font size, content removal)

  2. Track iteration history: Log each iteration's parameters and page count to identify which adjustments are most effective

  3. Set reasonable limits: Don't reduce parameters below readable/viewable thresholds

  4. Consider content-based solutions: If layout adjustments fail, consider removing or summarizing content

  5. Use multiple strategies sequentially: Try image reduction first, then table density, then fonts

Common Adjustment Order

  1. Reduce margins (least visible impact)
  2. Reduce image sizes
  3. Reduce table density / increase pagination
  4. Reduce font sizes
  5. Remove or summarize content (last resort)

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/pdf-page-verification-correction of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

PDF Page Verification Correction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

PDF Page Verification Correction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PDF Page Verification Correction this skillHKUDS/OpenSpace7.8k—~1.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Gzh Designisjiamu/gzh-design-skill4k—~2.2kAutomated safety check: PassAGPL-3.0
GenOffice Document CLIgenspark-ai/genoffice9.2k—~19kAutomated safety check: PassApache-2.0
Harness Book Best Practicewquguru/harness-books3.2k—~4.1kAutomated safety check: PassNone
Bookforge Korean Ebook PDF Makergongnyang/bookforge3161 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Gzh Design

    isjiamu/gzh-design-skill

    微信公众号文章排版引擎,将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取,自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入(非 Markdown…

    4k GitHub stars~2.2k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • GenOffice Document CLI

    genspark-ai/genoffice

    Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.

    9.2k GitHub stars~19k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Harness Book Best Practice

    wquguru/harness-books

    Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.

    3.2k GitHub stars~4.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Produces book-style Korean ebook PDFs from a topic or finished manuscript, with six design styles, real book parts and quality-check gates before output.

    316 GitHub starsUsed in 1 repo~1.7k tokens
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo
  • Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.8k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.8k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.8k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.8k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about PDF Page Verification Correction

What does PDF Page Verification Correction do?

Iterative workflow to verify PDF page counts and adjust layout parameters until requirements are met. PDF Page Verification Correction is an agent skill from HKUDS/OpenSpace.

When should I use PDF Page Verification Correction?

PDF Page Verification Correction fits situations like: tasks that involve PDF.

How do I install PDF Page Verification Correction in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill pdf-page-verification-correction -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-page-verification-correction in HKUDS/OpenSpace) into .claude/skills/pdf-page-verification-correction in your project. Claude Code loads it when a task matches its description.

How do I install PDF Page Verification Correction in Codex?

Run `npx skills add HKUDS/OpenSpace --skill pdf-page-verification-correction -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-page-verification-correction in HKUDS/OpenSpace) into .agents/skills/pdf-page-verification-correction in your project. Codex loads it when a task matches its description.

Can I use PDF Page Verification Correction in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/OpenSpace --skill pdf-page-verification-correction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pdf-page-verification-correction, .gemini/skills/pdf-page-verification-correction, .github/skills/pdf-page-verification-correction and .opencode/skills/pdf-page-verification-correction in your project.

What does PDF Page Verification Correction need to run?

SKILL.md names no scripts, command-line tools or credentials: PDF Page Verification Correction is instructions for the agent only. Our summary lists: Python 3.

Does PDF Page Verification Correction access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is PDF Page Verification Correction safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does PDF Page Verification Correction use?

PDF Page Verification Correction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PDF Page Verification Correction use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to PDF Page Verification Correction?

Skills that share tags, products or a category with PDF Page Verification Correction: Markitdown (ImCa0/just-laws, 781 stars), Gzh Design (isjiamu/gzh-design-skill, 4k stars), GenOffice Document CLI (genspark-ai/genoffice, 9.2k stars) and Harness Book Best Practice (wquguru/harness-books, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PDF Page Verification Correction?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,754 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.