← 返回 Skills 市场
308
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install openreview-review-analyzer
功能描述
Fetch and analyze peer reviews from OpenReview for any academic paper. Use this skill when the user mentions OpenReview, asks about reviews for a paper, want...
安全使用建议
This skill appears to do what it claims: it will make network requests to OpenReview (api2.openreview.net / api.openreview.net) and write a JSON file to /tmp/openreview_<forum_id>.json, then produce a synthesis using the bundled template. It does not request credentials. Before installing, you may want to: (1) review the full fetch_reviews.py file yourself (it runs as your user with Python), (2) confirm your environment allows outgoing HTTPS to api2.openreview.net, and (3) be aware that fallbacks include web searches or web_fetch calls that will query other websites for cached review content. If your environment forbids outbound network access or you must avoid writing files to /tmp, do not install or run the skill.
功能分析
Type: OpenClaw Skill
Name: openreview-review-analyzer
Version: 1.0.1
The skill is a legitimate tool designed to fetch and analyze academic peer reviews from OpenReview. It uses a Python script (scripts/fetch_reviews.py) to interact with the official OpenReview API (v1 and v2) and generates a structured report based on a provided template (references/report-template.md). The script correctly handles API communication using standard libraries and includes fallback mechanisms (web_fetch/web_search) in the instructions (SKILL.md) to ensure reliability. No malicious behavior, data exfiltration, or exploitable vulnerabilities were identified.
能力评估
Purpose & Capability
Name/description match the actual behavior: the included Python script and SKILL.md fetch review notes from OpenReview APIs and synthesize them. Required binary (python3) is appropriate and no unrelated services or credentials are requested.
Instruction Scope
Runtime instructions are focused on extracting a forum ID, running the included script, and generating a report from the fetched JSON. The fallback instructions include web_fetch and web_search for additional retrieval, which stays within the goal but means the agent may perform broader web queries if the API fails.
Install Mechanism
There is no install spec (instruction-only skill with an included script). That minimizes install risk; the script uses only standard libraries or requests (if present). No downloads or external installers are performed.
Credentials
The skill declares no environment variables, no credentials, and no config paths. The functionality (reading public OpenReview data) does not require secrets, so the requested privileges are proportionate.
Persistence & Privilege
The skill is user-invocable and not always-enabled. It does not request persistent agent-wide privileges or modify other skills/config; autonomy defaults are unchanged.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openreview-review-analyzer - 安装完成后，直接呼叫该 Skill 的名称或使用
/openreview-review-analyzer触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
No user-facing changes in this version; documentation and functionality remain the same.
v1.0.0
OpenReview Review Analyzer 1.0.0 – Initial Release
- Fetches all public peer reviews, metadata, and comments for academic papers on OpenReview.
- Automatically triggers on OpenReview URLs, forum IDs, or user requests related to summarizing or analyzing reviews.
- Runs a Python script (no external dependencies) to collect and organize review, rating, comment, and meta-data.
- Includes robust fallback methods if review fetching fails, such as direct API calls, web searches, or notifying the user if content isn’t public.
- Generates structured synthesis reports with reviewer ratings, consensus, disagreements, key issues, author responses, and meta-review summaries.
- Adapts the output language to match the user’s input language.
元数据
常见问题
openreview-review-analyzer 是什么？
Fetch and analyze peer reviews from OpenReview for any academic paper. Use this skill when the user mentions OpenReview, asks about reviews for a paper, want... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 308 次。
如何安装 openreview-review-analyzer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openreview-review-analyzer」即可一键安装，无需额外配置。
openreview-review-analyzer 是免费的吗？
是的，openreview-review-analyzer 完全免费（开源免费），可自由下载、安装和使用。
openreview-review-analyzer 支持哪些平台？
openreview-review-analyzer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 openreview-review-analyzer？
由 Vector（@vectorsss）开发并维护，当前版本 v1.0.1。
推荐 Skills