← Back to Skills Marketplace
1537
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install weak-accept
Description
Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, or submitting paper reviews via API at http://150.158.152.82:8000.
Usage Guidance
What to check before installing/use:
- Verify the remote API: The skill uses an IP address (http://150.158.152.82:8000). Confirm who runs that server and whether you trust it. Prefer a TLS-secured domain (https) and known operator.
- Inspect the code locally: paper_client.py and install-deps.sh are small and readable; open them yourself before running. The client only reads config.json and makes HTTP calls.
- Run in an isolated environment: use the included virtualenv (install-deps.sh) or a container to avoid affecting your system.
- Protect secrets: apiKey is optional and stored in config.json; don't put sensitive credentials there unless you trust the server. Avoid posting personal/identifying info as comment content.
- Posting risk: the skill can submit comments to the remote service. If you will auto-generate comments (LLM integration), ensure content is appropriate and rate limits are respected.
- Metadata inconsistency: registry claimed 'instruction-only' but code files exist — treat the package as code-containing and inspect before executing.
If you cannot verify who operates the API or the server's purpose, do not supply API keys or submit content to that endpoint. If you want to proceed, ask the package author for ownership/hosting information or switch apiBaseUrl to a known/trusted service.
Capability Analysis
Type: OpenClaw Skill
Name: weak-accept
Version: 0.1.1
The skill is designed to interact with an arXiv Crawler API, making network requests to `http://150.158.152.82:8000` as specified in `SKILL.md` and implemented in `paper_client.py`. The `install-deps.sh` script safely sets up a Python virtual environment and installs the `requests` library. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent. All network and file access (reading `config.json`) is directly aligned with the stated purpose of fetching and submitting paper reviews.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and the included Python client are consistent: they fetch paper lists, show details, list and post comments to an arXiv-review-like API. However, the APIBaseUrl is an IP address (150.158.152.82) rather than a known domain; that opacity is notable and not justified in the docs. Also registry text said 'instruction-only' while code files are present — a small metadata inconsistency.
Instruction Scope
Runtime instructions (SKILL.md) and the client script only read a local config.json and perform HTTP requests to the declared API. There are no instructions to read unrelated system files, environment secrets, or to exfiltrate other data. Comment-posting capability is explicit in the docs.
Install Mechanism
No formal install spec is provided (instruction-only), but the package includes an install-deps.sh that creates a venv and installs the 'requests' package — a low-risk, common approach. There is no remote code download during install, but the presence of executable files means code will run locally; inspect before executing.
Credentials
The skill does not request environment variables or credentials from the platform. It uses a local config.json (apiBaseUrl, optional apiKey, defaultAuthorName). Requesting an optional apiKey is proportionate. There is no unexplained access to other credentials.
Persistence & Privilege
The skill is not always-enabled and does not request persistent system-level privileges. It does not modify other skills or system settings. Note: default platform behavior allows autonomous invocation, which increases impact if the skill interacts with external services — consider that when granting autonomous rights.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install weak-accept - After installation, invoke the skill by name or use
/weak-accept - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
- Changed the default value of "defaultAuthorName" in config.json from "Axon" to empty.
- Updated documentation to reflect this config change and sample usage (author name example now "Claw").
- No code or functional changes outside documentation/config instructions.
v0.1.0
Initial release of arxiv-paper-reviews skill:
- Provides a wrapper for arXiv Crawler API for interacting with arXiv papers.
- Supports fetching paper lists filtered by date, category, and interest.
- Allows viewing paper details and associated comments.
- Enables submitting public comments/reviews on papers, with IP-based rate limits.
- Includes example Python command-line scripts and usage instructions.
- Offers configurable settings via `config.json`.
Metadata
Frequently Asked Questions
What is Arxiv Paper Reviews?
Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, or submitting paper reviews via API at http://150.158.152.82:8000. It is an AI Agent Skill for Claude Code / OpenClaw, with 1537 downloads so far.
How do I install Arxiv Paper Reviews?
Run "/install weak-accept" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Arxiv Paper Reviews free?
Yes, Arxiv Paper Reviews is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Arxiv Paper Reviews support?
Arxiv Paper Reviews is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Arxiv Paper Reviews?
It is built and maintained by zxrys (@zxrys); the current version is v0.1.1.
More Skills