← Back to Skills Marketplace
PDF to Text
by
Rishabh Dugar
· GitHub ↗
· v1.0.0
· MIT-0
73
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install pdf-to-txt
Description
Extract plain text from all or selected pages of a PDF.
README (SKILL.md)
PDF to Text
What It Does
Extracts plain text from all or selected pages of a PDF.
When to Use
- Extract readable text from a PDF for processing or analysis
- Get raw text content from PDF documents
Required Inputs
Provide one of:
url— public URL to a PDFfile— base64-encoded PDF- Multipart upload with
filefield
Authentication
Send your API key in the CLIENT-API-KEY header.
Get your free API key at https://pdfapihub.com. Full API documentation is available at https://pdfapihub.com/docs.
Use Cases
- Full-Text Search Indexing — Extract text from PDFs to build searchable indexes
- AI/LLM Processing — Extract PDF text for feeding into language models or chatbots
- Content Migration — Pull text from legacy PDF documents for migration to new systems
- Plagiarism Detection — Extract text for comparison and duplicate detection
- Accessibility — Extract text from PDFs for screen readers or text-to-speech
Aliases
/v1/convert/pdf/textis an alias
Example Usage
curl -X POST https://pdfapihub.com/api/v1/convert/pdf/txt \
-H "CLIENT-API-KEY: your_api_key" \
-H "Content-Type: application/json" \
-d '{ "url": "https://pdfapihub.com/sample-pdfapi-intro.pdf", "output": "url" }'
Usage Guidance
This skill simply sends PDFs (or PDF URLs) to pdfapihub.com to obtain extracted text and requires you to provide an API key in the CLIENT-API-KEY header. Before installing or using: 1) Verify the reputation and privacy policy of pdfapihub.com (no homepage/publisher info is provided in the package). 2) Do not send sensitive or confidential PDFs to this service unless you trust its data-handling and retention policies. 3) Provide the API key securely (avoid pasting it into public chat history or code repositories). 4) If you need offline/local processing for sensitive documents, use a local PDF-to-text tool instead. 5) Confirm billing, rate limits, and where converted outputs are hosted (the example shows a CDN URL) so you understand where your data may reside.
Capability Analysis
Type: OpenClaw Skill
Name: pdf-to-txt
Version: 1.0.0
The skill bundle is a standard API wrapper for a PDF-to-text conversion service hosted at pdfapihub.com. All files (SKILL.md, skill.json, example.json) consistently describe legitimate functionality for extracting text from PDFs via an external API, with no evidence of malicious intent, data exfiltration beyond the stated purpose, or prompt injection attacks.
Capability Tags
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, example.json, and skill.json all align: the skill calls an external PDF-to-text API (pdfapihub.com) and accepts a URL, base64 file, or multipart upload. Required inputs and output options match the stated purpose.
Instruction Scope
Instructions are narrow and consistent with conversion: POST to https://pdfapihub.com/api/v1/convert/pdf/txt with CLIENT-API-KEY and payload. However, using the skill will transmit full PDF contents (or a public PDF URL) to a third-party service — this is expected for a cloud conversion API but is a privacy/exfiltration risk for sensitive documents and should be considered before use.
Install Mechanism
Instruction-only skill with no install spec or code files — nothing is written to disk or downloaded by the skill itself. Low install risk.
Credentials
The skill does not declare or require environment variables, but it requires an API key supplied in the CLIENT-API-KEY header. That is proportionate for a third-party API, but the skill provides no mechanism for securely storing or retrieving that key; the user must manage it outside the skill.
Persistence & Privilege
always is false, the skill is user-invocable and not forced into every agent run. It does not request system config paths or modify other skills. Autonomous invocation is allowed (platform default) and is not by itself a concern here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pdf-to-txt - After installation, invoke the skill by name or use
/pdf-to-txt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Extract plain text from all or selected pages of a PDF. Useful for full-text search indexing, AI/LLM processing, content migration, and accessibility workflows.
Metadata
Frequently Asked Questions
What is PDF to Text?
Extract plain text from all or selected pages of a PDF. It is an AI Agent Skill for Claude Code / OpenClaw, with 73 downloads so far.
How do I install PDF to Text?
Run "/install pdf-to-txt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PDF to Text free?
Yes, PDF to Text is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does PDF to Text support?
PDF to Text is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PDF to Text?
It is built and maintained by Rishabh Dugar (@rishabhdugar); the current version is v1.0.0.
More Skills