← Back to Skills Marketplace
182
Downloads
0
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install formula-ocr
Description
OCR and recognize mathematical formulas from PDFs and images using MinerU. Converts printed or handwritten equations into structured LaTeX or text representa...
README (SKILL.md)
Formula Ocr
Convert and extract content from .pdf / images (.png/.jpg/.jpeg/.webp) using MinerU (mineru-open-api).
Install
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Quick Start
# Extract formulas from PDF (requires token)
mineru-open-api extract paper.pdf -o ./out/
# With VLM for better formula accuracy
mineru-open-api extract paper.pdf --model vlm -o ./out/
Authentication
Token required for extract and crawl:
mineru-open-api auth # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable
Create token at: https://mineru.net/apiManage/token
Capabilities
- Supports local files and URLs
- Requires token (
mineru-open-api authorMINERU_TOKENenv) - Supported input: .pdf / images (.png/.jpg/.jpeg/.webp)
- Language hint with
--language(default:ch, useenfor English) - Page range with
--pages(where applicable)
Notes
- Formula recognition requires
extractwith token. The--formulaflag is enabled by default. - Output goes to stdout by default; use
-o \x3Cdir>to save to file - Binary formats (docx) require
-oflag (cannot stream to stdout) - All progress/status messages go to stderr
- MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU
Usage Guidance
This skill appears coherent, but check a few practical points before installing: 1) Verify the mineru-open-api npm package or the GitHub repo are the official MinerU distribution and review their source if you have security concerns (npm installs can run install-time scripts). 2) Be aware that using the skill will send PDFs/images to MinerU's service (mineru.net) — do not upload sensitive or confidential documents unless you trust the service and its privacy/retention policies. 3) MINERU_TOKEN grants access to your account; treat it like any API secret (store it securely and revoke/regenerate it if compromised). 4) If you require higher assurance, run the CLI in an isolated environment or review the repository code before installing. Overall the requests and instructions match the stated OCR purpose.
Capability Analysis
Type: OpenClaw Skill
Name: formula-ocr
Version: 0.4.0
The skill bundle provides instructions and metadata for integrating the MinerU OCR tool (by OpenDataLab) to recognize mathematical formulas. It correctly identifies its dependencies (mineru-open-api), required environment variables (MINERU_TOKEN), and provides standard usage examples without any evidence of malicious intent, data exfiltration, or prompt injection attacks in SKILL.md.
Capability Assessment
Purpose & Capability
Name/description request OCR of mathematical formulas. The skill only requires the mineru-open-api CLI and a MINERU_TOKEN, which are directly relevant to invoking MinerU's service—no unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to run mineru-open-api commands (extract, auth) on local files or URLs and to provide MINERU_TOKEN. It does not ask the agent to read unrelated files, other environment variables, or exfiltrate data to unexpected endpoints; the only external endpoint referenced is MinerU (mineru.net).
Install Mechanism
Install paths are standard: npm package (mineru-open-api) or go install from the project's GitHub repo. This is appropriate for a CLI-only integration. Note: npm packages (and go installs from remote repos) can run code at install time, so you should review the package/repo if you require a higher trust level.
Credentials
Only MINERU_TOKEN is required and declared as the primary credential. That single API token is proportional to a service that requires authentication. No other secrets or unrelated environment variables are requested.
Persistence & Privilege
The skill does not request always:true or any elevated persistent presence, and it does not indicate modifying system or other-skill configuration. Autonomous invocation (default) is allowed but not exceptional here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install formula-ocr - After installation, invoke the skill by name or use
/formula-ocr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.4.0
SEO: expand description for better ClawHub vector search discovery
v0.3.0
Rollback to original version
v0.2.1
SEO optimization v0.2.1
v0.2.0
SEO optimization v0.2.0
v1.0.1
Fix: declare MINERU_TOKEN credential in metadata
v1.0.0
Formula OCR - recognize and extract mathematical formulas from PDFs or images using MinerU. Use for
Metadata
Frequently Asked Questions
What is Formula Ocr?
OCR and recognize mathematical formulas from PDFs and images using MinerU. Converts printed or handwritten equations into structured LaTeX or text representa... It is an AI Agent Skill for Claude Code / OpenClaw, with 182 downloads so far.
How do I install Formula Ocr?
Run "/install formula-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Formula Ocr free?
Yes, Formula Ocr is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Formula Ocr support?
Formula Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Formula Ocr?
It is built and maintained by mzlzyCA (@mzlzyca); the current version is v0.4.0.
More Skills