Agent skill

PDF Checklist Workflow

by HKUDS in HKUDS/OpenSpace

Generate structured PDF documents with tables, sections, and scoring using Python libraries in executecodesandbox

MITAuto-check passedDocuments & Office

Install PDF Checklist Workflow

skills CLI
$ npx skills add HKUDS/OpenSpace --skill pdf-checklist-workflow -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace pdf-checklist-workflow --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-checklist-workflow .claude/skills/pdf-checklist-workflow && 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-checklist-workflow
GitHub stars
7.8k
Token cost
~2.3k tokens
SKILL.md length
542 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Generate structured PDF documents with tables, sections, and scoring using Python libraries in executecodesandbox

  • Works in 5 steps: Choose a PDF Library → Write PDF Generation Code in… → Execute the Code → …
  • Tasks that involve PDF
  • SKILL.md covers Overview, Step-by-Step Instructions, Best Practices and Template for Quick Start, plus 1 more section
  • Calls pip and python

What it does

PDF Checklist Workflow is an agent skill from HKUDS/OpenSpace. Generate structured PDF documents with tables, sections, and scoring using Python libraries in executecodesandbox

Its SKILL.md is about 2.3k 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. It works with Python. 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-checklist-workflow”

Requirements

  • Python 3

Workflow steps

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

  1. Choose a PDF Library
  2. Write PDF Generation Code in execute_code_sandbox
  3. Execute the Code
  4. Verify Output
  5. Handle Common Issues

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

    Shell commands in SKILL.md call:

    • pip
    • python

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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 Checklist Workflow loads about 2.3k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 542 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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). 542 words, ~2,321 tokens.

Download SKILL.mdSave it as .claude/skills/pdf-checklist-workflow/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pdf-checklist-workflow
description
Generate structured PDF documents with tables, sections, and scoring using Python libraries in execute_code_sandbox

PDF Checklist/Report Generation Workflow

This skill provides a reusable pattern for creating structured PDF documents such as checklists, reports, or assessments using Python in a sandboxed environment.

Overview

Use this workflow when you need to:

  • Generate PDF checklists, reports, or assessments
  • Create structured documents with tables, sections, and headers
  • Include scoring criteria or evaluation frameworks
  • Produce downloadable artifacts for users

Primary method: Use execute_code_sandbox for Python PDF generation Fallback method: If execute_code_sandbox fails, create and run Python scripts via shell commands

Step-by-Step Instructions

Step 1: Choose a PDF Library

Select a Python library based on your needs:

LibraryBest ForComplexity
reportlabProfessional reports, complex layoutsMedium
fpdf / fpdf2Simple documents, quick generationLow
matplotlibCharts, graphs, visual elementsMedium
Step 2: Write PDF Generation Code in execute_code_sandbox

Use the execute_code_sandbox tool with Python code that:

  1. Imports the chosen PDF library
  2. Defines document structure (title, sections, tables)
  3. Adds content (text, tables, scores, criteria)
  4. Saves to a file path like /workspace/output.pdf
  5. Outputs the path using ARTIFACT_PATH: prefix for download

Determine workspace directory dynamically: Before generating PDFs, identify the correct output path:

bash
# Option 1: Use current directory
WORKDIR=$(pwd)

# Option 2: Check common workspace locations
if [ -d "/workspace" ]; then WORKDIR="/workspace"
elif [ -d "$HOME/workspace" ]; then WORKDIR="$HOME/workspace"
else WORKDIR=$(pwd); fi

In Python code, use environment variables or dynamic path detection:

python
import os
workspace = os.environ.get('WORKSPACE', os.getcwd())
output_path = os.path.join(workspace, 'output.pdf')

Example using fpdf2:

python
from fpdf import FPDF

class PDFChecklist(FPDF):
    def header(self):
        self.set_font('Arial', 'B', 16)
        self.cell(0, 10, 'Assessment Checklist', 0, 1, 'C')
        self.ln(10)
    
    def section_title(self, title):
        self.set_font('Arial', 'B', 12)
        self.cell(0, 10, title, 0, 1, 'L')
        self.ln(5)
    
    def add_checklist_item(self, item, criteria, score):
        self.set_font('Arial', '', 10)
        self.cell(100, 8, item, 1)
        self.cell(60, 8, criteria, 1)
        self.cell(30, 8, str(score), 1)
        self.ln()

# Create PDF
pdf = PDFChecklist()
pdf.add_page()
pdf.set_auto_page_break(auto=True, margin=15)

# Add sections
pdf.section_title('Evaluation Criteria')
pdf.add_checklist_item('Requirement 1', 'Must meet standard', 5)
pdf.add_checklist_item('Requirement 2', 'Should be complete', 4)

# Save
output_path = '/workspace/checklist.pdf'
pdf.output(output_path)
print(f'ARTIFACT_PATH:{output_path}')

Example using reportlab (more professional):

python
from reportlab.lib import colors
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch

def create_pdf_report(output_path):
    doc = SimpleDocTemplate(output_path, pagesize=letter)
    styles = getSampleStyleSheet()
    story = []
    
    # Title
    title_style = ParagraphStyle('CustomTitle', parent=styles['Heading1'],
                                  fontSize=18, spaceAfter=30, alignment=1)
    story.append(Paragraph("Assessment Report", title_style))
    story.append(Spacer(1, 0.3*inch))
    
    # Section header
    story.append(Paragraph("Evaluation Summary", styles['Heading2']))
    story.append(Spacer(1, 0.2*inch))
    
    # Data table
    data = [
        ['Criteria', 'Description', 'Score'],
        ['Completeness', 'All sections filled', '8/10'],
        ['Accuracy', 'Information verified', '9/10'],
        ['Clarity', 'Easy to understand', '7/10']
    ]
    
    table = Table(data, colWidths=[2*inch, 2.5*inch, 1*inch])
    table.setStyle(TableStyle([
        ('BACKGROUND', (0, 0), (-1, 0), colors.grey),
        ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
        ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
        ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
        ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
        ('BACKGROUND', (0, 1), (-1, -1), colors.beige),
        ('GRID', (0, 0), (-1, -1), 1, colors.black)
    ]))
    story.append(table)
    
    doc.build(story)
    print(f'ARTIFACT_PATH:{output_path}')

create_pdf_report('/workspace/report.pdf')
Step 3: Execute the Code

Call the tool:

execute_code_sandbox
  code: <your PDF generation code from Step 2>
  language: python
Step 3b: Fallback - Shell-Based Execution

If execute_code_sandbox fails repeatedly (e.g., "unknown error", timeouts), use this fallback:

1. Create the Python script via heredoc:

bash
cat > /tmp/generate_pdf.py << 'EOF'
# Your PDF generation code here
from fpdf import FPDF
import os

workspace = os.environ.get('WORKSPACE', os.getcwd())
output_path = os.path.join(workspace, 'checklist.pdf')

pdf = FPDF()
pdf.add_page()
pdf.set_font('Arial', 'B', 16)
pdf.cell(0, 10, 'Checklist', 0, 1, 'C')
pdf.output(output_path)
print(f'ARTIFACT_PATH:{output_path}')
EOF

2. Install required library if needed:

bash
pip install fpdf2 --quiet 2>/dev/null || pip install fpdf2

3. Execute the script:

bash
python /tmp/generate_pdf.py

4. Verify the output file was created:

bash
ls -lh $(pwd)/*.pdf 2>/dev/null || ls -lh /workspace/*.pdf 2>/dev/null

Important for fallback: When using shell execution, ensure the script outputs the ARTIFACT_PATH so the file can be downloaded. Adjust the path based on where the file was actually created.

Step 4: Verify Output

After execution, verify the PDF was created:

Option A - Use read_file:

read_file
  filetype: pdf
  file_path: /workspace/output.pdf

Option B - Use shell inspection:

run_shell
  command: ls -lh /workspace/*.pdf

Check that:

  • File exists and has reasonable size (>1KB)
  • No error messages in execution output
  • ARTIFACT_PATH was correctly output for download

If using fallback execution, check multiple possible locations:

bash
run_shell
  command: find . -name "*.pdf" -type f -exec ls -lh {} \; 2>/dev/null
Show full SKILL.md (212 more words)Show less
Step 5: Handle Common Issues
IssueSolution
Library not installedAdd !pip install fpdf2 or !pip install reportlab at code start
Font errorsUse standard fonts (Arial, Helvetica, Courier)
File not foundEnsure path is /workspace/filename.pdf
Empty PDFCheck that pdf.output() or doc.build() is called
Encoding issuesUse ASCII text or handle unicode properly
execute_code_sandbox failsSwitch to shell-based fallback (Step 3b): create script with heredoc, run with python
Wrong workspace pathUse dynamic detection: os.getcwd() or $(pwd) instead of hardcoded /workspace/
Permission errorsWrite to current directory or /tmp/ then move file

Best Practices

  1. Keep it simple first - Start with basic text, add tables/graphics later
  2. Use ARTIFACT_PATH prefix - Ensures the file is downloadable
  3. Test incrementally - Generate a minimal PDF before adding complexity
  4. Include error handling - Wrap file operations in try/except blocks
  5. Set appropriate margins - Prevent content from being cut off
  6. Have a fallback ready - If execute_code_sandbox fails after 2-3 attempts, switch to shell-based execution immediately
  7. Detect workspace dynamically - Don't assume /workspace/; use os.getcwd() or environment variables

Template for Quick Start

python
# Install library if needed
# !pip install fpdf2

from fpdf import FPDF
 import os

pdf = FPDF()
pdf.add_page()
pdf.set_font('Arial', 'B', 16)
pdf.cell(0, 10, 'Your Title Here', 0, 1, 'C')
pdf.ln(10)
pdf.set_font('Arial', '', 12)
pdf.multi_cell(0, 8, 'Your content here...')
 workspace = os.environ.get('WORKSPACE', os.getcwd())
 output_path = os.path.join(workspace, 'output.pdf')
 pdf.output(output_path)
 print(f'ARTIFACT_PATH:{output_path}')

Shell fallback template:

bash
# Create script
cat > /tmp/pdf_gen.py << 'PYEOF'
from fpdf import FPDF
import os
pdf = FPDF()
pdf.add_page()
pdf.set_font('Arial', 'B', 16)
pdf.cell(0, 10, 'Title', 0, 1, 'C')
workspace = os.environ.get('WORKSPACE', os.getcwd())
pdf.output(os.path.join(workspace, 'output.pdf'))
print(f'ARTIFACT_PATH:{workspace}/output.pdf')
PYEOF
# Run it
pip install fpdf2 -q 2>/dev/null; python /tmp/pdf_gen.py
  • execute_code_sandbox - Run Python code for PDF generation
  • read_file - Verify PDF content (type: pdf)
  • run_shell - Check file existence and size
  • create_file - Alternative for simple text files if PDF not required

© 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-checklist-workflow of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

PDF Checklist Workflow 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 Checklist Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PDF Checklist Workflow this skillHKUDS/OpenSpace7.8k—~2.3kAutomated safety check: PassMIT
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0
Software Certificate SkillIvanCodesDev/software-certificate-skill156—~1.6kAutomated safety check: PassMIT
Doc Cleanernotoriouslab/doc-cleaner309—~712Automated safety check: PassMIT
MineruNebutra/MinerU-Skill122—~504Automated safety check: PassMIT
Office To Mdshuyu-labs/WebCode278—~1kAutomated safety check: NotesCustom licence

Similar skills

  • 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
  • Software Certificate Skill

    IvanCodesDev/software-certificate-skill

    面向普通用户,从真实软件项目全自动生成中国软件著作权申请资料:一次收集登记事实,自动分析业务、选择可追溯源码、取得真实界面证据,生成申请表信息、规范黑白灰操作手册、代码前后30页或全部材料及真实 DOCX/PDF;内部验证、渲染、哈希与备份只进入系统临时运行区,项目最终仅保留正式资料。适配 Codex、Claude…

    156 GitHub stars~1.6k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Doc Cleaner

    notoriouslab/doc-cleaner

    Convert PDF, DOCX, XLSX, and text files to clean, structured Markdown.

    309 GitHub stars~712 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Mineru

    Nebutra/MinerU-Skill

    An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.

    122 GitHub stars~504 tokensUpdated 15 days ago
    Documents & OfficeAuto-check passed
  • Office To Md

    shuyu-labs/WebCode

    Convert Office documents (Word, Excel, PowerPoint, PDF) to Markdown format.

    278 GitHub stars~1k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check: notes
  • Cc Streaming Export Safety

    doccker/cc-use-exp

    当实现用户驱动的大文件导出或批量序列化(Excel/CSV/JSON/JSONL/PDF,数据量未知或超过 1 万行/10 MB)时触发;普通小文件下载、静态资源下载、非导出 Writer/Report 类不触发。防止 OOM、临时文件残留、同步导出阻塞 HTTP 线程和表格公式注入。

    1.1k GitHub stars~2.2k tokensUpdated 1 mo ago
    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

Works with

Questions about PDF Checklist Workflow

What does PDF Checklist Workflow do?

Generate structured PDF documents with tables, sections, and scoring using Python libraries in executecodesandbox. PDF Checklist Workflow is an agent skill from HKUDS/OpenSpace.

When should I use PDF Checklist Workflow?

PDF Checklist Workflow fits situations like: tasks that involve PDF.

How do I install PDF Checklist Workflow in Claude Code?

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

How do I install PDF Checklist Workflow in Codex?

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

Can I use PDF Checklist Workflow 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-checklist-workflow -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-checklist-workflow, .gemini/skills/pdf-checklist-workflow, .github/skills/pdf-checklist-workflow and .opencode/skills/pdf-checklist-workflow in your project.

What does PDF Checklist Workflow need to run?

Going by SKILL.md and its folder, PDF Checklist Workflow needs the command-line tools its instructions call (pip and python). Our summary lists: Python 3.

Does PDF Checklist Workflow access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is PDF Checklist Workflow 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 Checklist Workflow use?

PDF Checklist Workflow 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 Checklist Workflow use?

About 2.3k tokens (SKILL.md is roughly 9.3k 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 Checklist Workflow?

Skills that share tags, products or a category with PDF Checklist Workflow: Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Software Certificate Skill (IvanCodesDev/software-certificate-skill, 156 stars), Doc Cleaner (notoriouslab/doc-cleaner, 309 stars) and Mineru (Nebutra/MinerU-Skill, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PDF Checklist Workflow?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 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.