← 返回 Skills 市场
196
总下载
2
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install paper-parser
功能描述
Parse academic papers and research documents from PDF using MinerU. Extracts structured content including title, abstract, sections, figures, tables, formula...
安全使用建议
This skill appears coherent for parsing academic PDFs with MinerU. Before installing, verify the npm package name and the GitHub repo (https://github.com/opendatalab/MinerU-Ecosystem) match the vendor/site (https://mineru.net), inspect the repo or package code if possible, and limit the MINERU_TOKEN scope (create a dedicated token). Install the CLI in a controlled environment, and avoid supplying unrelated or high-privilege credentials. If you rely on sensitive documents, consider testing on non-sensitive PDFs first to confirm outputs and behavior.
功能分析
Type: OpenClaw Skill
Name: paper-parser
Version: 0.4.0
The paper-parser skill is a legitimate tool designed to extract structured content from academic PDFs using the MinerU API (mineru.net). It provides instructions for the agent to use the 'mineru-open-api' CLI tool, requiring a user-provided API token (MINERU_TOKEN). The skill's behavior, installation steps via npm/Go, and metadata are consistent with its stated purpose of document processing, and no malicious patterns or prompt-injection attacks were detected in SKILL.md.
能力评估
Purpose & Capability
The name/description (paper parsing via MinerU) matches the declared binary (mineru-open-api), the declared primary env var (MINERU_TOKEN), and the documented CLI commands.
Instruction Scope
SKILL.md only instructs use of the mineru-open-api CLI (extract/auth/crawl) on PDFs and URLs; it does not direct the agent to read unrelated files, secrets, or system config.
Install Mechanism
Install options are standard: npm package and a Go install from a GitHub repo. No downloads from untrusted URLs, no archives/extract steps are present in the spec.
Credentials
Only one credential (MINERU_TOKEN) is required and is appropriate for an authenticated API/CLI. No unrelated secrets, config paths, or broad credential requests are present.
Persistence & Privilege
The skill is not forced-always, does not modify other skills, and its runtime behavior is limited to invoking the mineru-open-api CLI; autonomous invocation is allowed but is the platform default.
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 paper-parser - 安装完成后，直接呼叫该 Skill 的名称或使用
/paper-parser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
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
Minor update
v1.0.0
Initial release
元数据
常见问题
Paper Parser 是什么？
Parse academic papers and research documents from PDF using MinerU. Extracts structured content including title, abstract, sections, figures, tables, formula... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 196 次。
如何安装 Paper Parser？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install paper-parser」即可一键安装，无需额外配置。
Paper Parser 是免费的吗？
是的，Paper Parser 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Paper Parser 支持哪些平台？
Paper Parser 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 Paper Parser？
由 mzlzyCA（@mzlzyca）开发并维护，当前版本 v0.4.0。
推荐 Skills