Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplum
Install on your platform
Showing OpenClaw.
- 1
Run this in your terminal
terminal$
What we know about this skill
Publisher
openai
Matched to the vendor's own GitHub organisation.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned openai/skills at 49f948faa9.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 49f948faa9
- Manifest
- skills/.curated/pdf/SKILL.md
- Scanned
- 3 files, 66 lines
About this skill
What it does
This skill enables AI agents to process PDF documents with a focus on preserving visual fidelity. It allows for reading text from PDFs, generating new PDFs programmatically, and reviewing existing PDF content while maintaining layout integrity through rendering pages using Poppler. The agent can also leverage Python libraries like reportlab and pdfplum for advanced PDF manipulation.
When to use it
- Extracting data from complex invoices: Retrieve specific information (dates, amounts, line items) from multi-page invoices where formatting is crucial.
- Generating reports with embedded images and tables: Create visually appealing reports that incorporate data visualizations and structured content extracted from various sources.
- Reviewing legal documents for accuracy: Compare a draft legal document to an original PDF, highlighting discrepancies in both text and layout.
- Creating accessible PDFs from existing documents: Convert complex documents into more accessible formats while maintaining visual structure.
Key capabilities
- PDF rendering using Poppler
- Text extraction from PDF content
- PDF generation with
reportlab - PDF manipulation with
pdfplum - Preservation of layout and formatting during processing
Example prompts
- "Extract all table data from this PDF invoice and summarize the total amount due."
- "Generate a new PDF report incorporating data from this spreadsheet, formatted to match the style of this example PDF."
- "Compare this draft contract (PDF) with the original version (PDF) and highlight any differences in text or layout."
Tips & gotchas
- Ensure Poppler is installed and configured correctly for optimal rendering.
- Complex PDF layouts may require adjustments to extraction parameters for accurate results.