← Back to Skills Marketplace
paper-parser-skill
by
KaiHangYang
· GitHub ↗
· v0.1.4
· MIT-0
110
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install paper-parser-skill
Description
CLI tool to search, download, and parse academic papers from arXiv into AI-friendly Markdown using MinerU API.
Usage Guidance
This tool will download PDFs locally and upload them to the MinerU service for parsing — only provide a MinerU token if you trust that service and avoid uploading confidential/unpublished material. Before installing: (1) Inspect the GitHub repo and PyPI package contents to confirm behavior; (2) Note the metadata mismatch: the registry omitted the required MINERU_API_TOKEN even though SKILL.md requires it—ask the publisher to correct metadata if you rely on registry info; (3) Use a dedicated, revocable token with minimal scope; store it securely in ~/.paper-parser/config.yaml and limit file permissions; (4) Install inside a virtualenv or container to limit blast radius from third-party code; (5) If you need offline parsing or cannot share PDFs, seek local alternatives. If you want higher assurance, request the actual package source and hashes or run the package in an isolated environment and audit network activity on first run.
Capability Assessment
Purpose & Capability
The skill's declared purpose (search/download/parse arXiv papers using MinerU) aligns with the instructions: it requires a MinerU API token and a local workspace. However, the registry metadata shown earlier lists no required environment variables or primary credential while the SKILL.md explicitly requires MINERU_API_TOKEN in the config file — this metadata mismatch is an incoherence that should be resolved.
Instruction Scope
Runtime instructions are scoped to searching arXiv, downloading PDFs to a local workspace, and uploading PDFs/metadata to MinerU for parsing. The SKILL.md explicitly warns about external processing and recommends not uploading sensitive documents. It does not instruct reading other unrelated system files or credentials.
Install Mechanism
There is no platform-level install spec (instruction-only). The SKILL.md tells users to pip install the package from PyPI, which is a standard but non-trivial install action (third-party code executed locally). This is expected for a CLI Python tool but carries the usual risks of executing third-party packages — the doc recommends using a virtualenv/container.
Credentials
The runtime requires a MinerU API token (MINERU_API_TOKEN) stored in ~/.paper-parser/config.yaml; that credential is appropriate for the stated parsing functionality. The concern is the mismatch between registry metadata (which lists no required env vars/credentials) and the SKILL.md (which lists the token as required). That inconsistency can mislead users about what secrets will be needed and stored. Also note the token grants external upload/processing rights—store a revocable, minimal-scope token and avoid uploading sensitive documents.
Persistence & Privilege
The skill is user-invocable and not forced-always. It requests a per-skill config file in the user's home directory and stores downloaded PDFs in a workspace; it does not request system-wide privileges or to modify other skills. No signs of elevated persistent platform privilege are present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paper-parser-skill - After installation, invoke the skill by name or use
/paper-parser-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.4
- Added explicit credentials metadata to require MINERU_API_TOKEN for parsing functionality.
- Enhanced documentation with additional privacy, security, and installation safety warnings.
- Clarified the need for a dedicated MinerU API token and recommended virtual environments for installation.
- No code changes in this version; documentation and metadata updates only.
v0.1.3
v0.1.3 introduces a recommended async workflow and new CLI commands for improved automation and stability.
- Added async parsing commands: pp submit and pp check for non-blocking paper parsing.
- Updated documentation to guide users towards agent-friendly, async usage.
- Marked blocking commands (pp parse, pp all) with warnings about potential timeouts.
- Documented enhanced workspace structure, including async task state files.
- Installation instructions now specify version 0.1.3.
v0.1.2
- Added explicit skill metadata: version, author, homepage, and config file requirements.
- Introduced a prominent data privacy and security section highlighting external data processing and user control.
- Updated formatting with emojis for readability and clearer section headings.
- Clarified the need for a MinerU API token for parsing functionality.
- No changes to functionality or core commands.
v0.1.1
- Added initial documentation in SKILL.md for paper-parser-skill version 0.1.1.
- Describes CLI tool capabilities: searching, downloading, and parsing arXiv papers into Markdown using the MinerU API.
- Provides setup instructions, CLI command usage, and configuration details.
- Outlines workspace structure and required dependencies.
- Introduces command aliases and quickstart workflow.
Metadata
Frequently Asked Questions
What is paper-parser-skill?
CLI tool to search, download, and parse academic papers from arXiv into AI-friendly Markdown using MinerU API. It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install paper-parser-skill?
Run "/install paper-parser-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is paper-parser-skill free?
Yes, paper-parser-skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does paper-parser-skill support?
paper-parser-skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created paper-parser-skill?
It is built and maintained by KaiHangYang (@kaihangyang); the current version is v0.1.4.
More Skills