← Back to Skills Marketplace
memect-ppx
by
HangHang Li
· GitHub ↗
· v0.2.3
· MIT-0
126
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install memect-ppx
Description
Parse PDFs and images into Markdown/JSON using the `ppx` CLI. Use when the user asks to OCR scanned PDFs or screenshots, extract tables from PDFs, convert PD...
Usage Guidance
This skill appears to do what it says: it uses the local 'ppx' CLI to OCR/parse documents. Before installing/using it, ensure you: (1) run it inside a dedicated virtual environment so pip installs don't affect system Python, (2) trust the memect-ppx package you will pip-install (PyPI packages execute code during install), and (3) avoid configuring remote/back-end endpoints or API keys for sensitive documents unless you trust that service (the optional backend options can send document data to whatever base_url you configure). The bundled scripts are small helper tools: check_ppx_env.sh only verifies the ppx binary, and sync_version.py updates SKILL.md from a repo pyproject.toml (a developer convenience you can skip).
Capability Analysis
Type: OpenClaw Skill
Name: memect-ppx
Version: 0.2.3
The skill is a legitimate wrapper for the `ppx` CLI tool, designed for PDF and image parsing into Markdown/JSON. It includes standard environment checks (scripts/check_ppx_env.sh), version synchronization (scripts/sync_version.py), and comprehensive documentation for configuration and troubleshooting. All instructions, including the setup of virtual environments and installation of the 'memect-ppx' package, are transparently documented and strictly aligned with the tool's functional requirements. No indicators of malicious intent, data exfiltration, or prompt injection were identified.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description are parsing OCR'd PDFs/images to Markdown/JSON and the only declared runtime dependency is the ppx CLI; that aligns with the skill's stated purpose.
Instruction Scope
SKILL.md guides the agent to check Python/ppx, create/use a virtualenv, run ppx parse, and inspect outputs. It does not instruct reading unrelated system files or exfiltrating unrelated secrets. It references optional LLM backends only for higher-quality table parsing.
Install Mechanism
The skill is instruction-only (no automated install spec). Runtime guidance suggests installing memect-ppx and dependencies via pip into a virtualenv. Installing Python packages pulls code from PyPI (normal but networked and executes native code during installation); this is expected for this task but worth noting.
Credentials
No required environment variables are declared. Reference docs show backend configurations that accept base_url and api_key fields; those are optional and user-provided. If you configure a remote backend and supply an API key/base_url, parsed document contents would be sent to that endpoint — that's expected but important to be aware of for sensitive documents.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. The included helper script sync_version.py can modify SKILL.md if run, but that is a developer convenience and not required at runtime. No other elevated persistence or system-wide configuration changes are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install memect-ppx - After installation, invoke the skill by name or use
/memect-ppx - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.2.3
启用 user-invocable，支持 /memect-ppx 斜杠调用
v0.2.2
更新显示名称为 memect-ppx
v0.2.1
优化 description，增加中文关键词覆盖，提高触发命中率
v0.2.0
优化 description，增加中文关键词覆盖，提高触发命中率
v0.0.2
Initial release
Metadata
Frequently Asked Questions
What is memect-ppx?
Parse PDFs and images into Markdown/JSON using the `ppx` CLI. Use when the user asks to OCR scanned PDFs or screenshots, extract tables from PDFs, convert PD... It is an AI Agent Skill for Claude Code / OpenClaw, with 126 downloads so far.
How do I install memect-ppx?
Run "/install memect-ppx" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is memect-ppx free?
Yes, memect-ppx is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does memect-ppx support?
memect-ppx is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created memect-ppx?
It is built and maintained by HangHang Li (@lihanghang); the current version is v0.2.3.
More Skills