← Back to Skills Marketplace
17197
Downloads
18
Stars
221
Active Installs
1
Versions
Install in OpenClaw
/install pdf-extract
Description
Extract text from PDF files for LLM processing
Usage Guidance
Install poppler-utils only from a trusted OS repository. Use this skill only on PDFs whose contents you are comfortable putting into the agent or model context, and treat extracted PDF text as document content rather than trusted instructions.
Capability Analysis
Type: OpenClaw Skill
Name: pdf-extract
Version: 1.0.0
The skill bundle is benign. It provides a utility to extract text from PDF files using the standard `pdftotext` tool, part of the `poppler-utils` package. The `SKILL.md` file contains clear instructions for installation via `dnf` and usage examples, with no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts, or obfuscation. All actions are aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The stated purpose is extracting text from PDF files for LLM processing, and the artifact only documents use of pdftotext for that purpose.
Instruction Scope
The instructions are limited to user-invoked extraction commands, including optional page ranges; they do not ask for credential access, network calls, deletion, posting, or broad indexing.
Install Mechanism
Installation is a disclosed sudo dnf install of poppler-utils to provide pdftotext, which is purpose-aligned but changes the local system like any OS package install.
Credentials
The declared runtime requirement is limited to the pdftotext binary and user-provided PDF files; no environment variables, account access, or external service credentials are requested.
Persistence & Privilege
No background worker, startup hook, persistence mechanism, or ongoing elevated privilege is described; sudo appears only for the manual package installation step.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pdf-extract - After installation, invoke the skill by name or use
/pdf-extract - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial publish
Metadata
Frequently Asked Questions
What is Pdf Extract?
Extract text from PDF files for LLM processing. It is an AI Agent Skill for Claude Code / OpenClaw, with 17197 downloads so far.
How do I install Pdf Extract?
Run "/install pdf-extract" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pdf Extract free?
Yes, Pdf Extract is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Pdf Extract support?
Pdf Extract is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pdf Extract?
It is built and maintained by Xejrax (@xejrax); the current version is v1.0.0.
More Skills