Token导航 LogoToken导航TokenDH.com
研究检索执行命令clawhub未标认证来源可访问clear审计通过

paperzillapaperzilla 命令行

Agent Skill

paperzilla 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

23,562

周安装

944

GitHub Stars

2

下载量

7,628
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:paperzilla(paperzilla 命令行)
来源仓库:https://github.com/pors/paperzilla
安装命令:
openclaw skills install paperzilla
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install paperzilla

简介

使用 Paperzilla CLI 浏览研究项目和论文提要。

  • 支持规范论文检查、反馈留下和 JSON 导出功能。
  • 提供研究项目管理和协作工具。paperzilla 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 需确认 CLI 工具安装和配置文件访问权限。
  • 建议了解命令语法和输出格式规范。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
paperzilla
description
Use the Paperzilla CLI (pz) to browse research projects and feeds, inspect canonical papers and project recommendations, leave feedback, export JSON, and generate Atom feed URLs. Trigger when users ask to check Paperzilla feeds, list projects, inspect paper details, tune recommendations, or automate feed workflows.
version
0.3.1
homepage
https://docs.paperzilla.ai/guides/cli
metadata
{ "openclaw": { "requires": { "bins": ["pz"] }, "homepage": "https://docs.paperzilla.ai/guides/cli" } }

Paperzilla CLI (pz) 🦖

Use pz to read canonical papers, browse project recommendations, inspect projects, leave recommendation feedback, and automate Paperzilla workflows from the terminal.

Prefer --json whenever an agent needs structured output.

Install

macOS

brew install paperzilla-ai/tap/pz

Windows (Scoop)

scoop bucket add paperzilla-ai https://github.com/paperzilla-ai/scoop-bucket
scoop install pz

Linux

curl -sL https://github.com/paperzilla-ai/pz/releases/latest/download/pz_linux_amd64.tar.gz | tar xz
sudo mv pz /usr/local/bin/

Build from source (Go 1.23+)

git clone https://github.com/paperzilla-ai/pz.git
cd pz
go build -o pz .
mv pz /usr/local/bin/

Update

First check the currently installed version:

pz --version

Then ask pz how it should be upgraded:

pz update

pz update detects common install methods and prints the right upgrade instructions for:

  • Homebrew
  • Scoop
  • GitHub release binaries
  • source builds

If detection is ambiguous, override it explicitly:

pz update --install-method homebrew
pz update --install-method scoop
pz update --install-method release
pz update --install-method source

Common upgrade paths:

macOS

brew update
brew upgrade pz

Windows

scoop update pz

Linux / Releases

curl -sL https://github.com/paperzilla-ai/pz/releases/latest/download/pz_linux_amd64.tar.gz | tar xz
sudo mv pz /usr/local/bin/

Source install

git pull
go build -o pz .
sudo mv pz /usr/local/bin/

Authentication

pz login

You need login for project-oriented commands like project, feed, rec, and feedback.

Core model: canonical papers vs project recommendations

This distinction matters:

  • pz paper <paper-ref> works with a canonical Paperzilla paper
  • pz rec <project-paper-ref> works with a recommendation inside one project

A canonical paper is shared globally. A recommendation is that paper as it appears in one specific project, with project-specific relevance and feedback.

Core commands

Check for updates

pz update

List projects

pz project list

Show one project

pz project <project-id>

Browse project feed

pz feed <project-id>

Useful flags:

  • --must-read
  • --since YYYY-MM-DD
  • --limit N
  • --json
  • --atom

Examples:

pz feed <project-id> --must-read --since 2026-03-01 --limit 5
pz feed <project-id> --json
pz feed <project-id> --atom

Inspect a canonical paper

pz paper <paper-id-or-short-id>
pz paper <paper-id-or-short-id> --json
pz paper <paper-id-or-short-id> --markdown

Use pz paper --project <project-id> when you want to resolve that canonical paper inside one of your projects and see recommendation context.

Example:

pz paper <paper-id> --project <project-id>

Inspect a project recommendation

pz rec <project-paper-id-or-short-id>
pz rec <project-paper-id-or-short-id> --json
pz rec <project-paper-id-or-short-id> --markdown

Use pz rec when the identifier came from pz feed --json.

Leave recommendation feedback

pz feedback <project-paper-id> upvote
pz feedback <project-paper-id> star
pz feedback <project-paper-id> downvote --reason not_relevant
pz feedback <project-paper-id> downvote --reason low_quality
pz feedback clear <project-paper-id>

Feedback is project-specific. The same canonical paper can have different feedback in different projects.

Output and automation

  • Prefer --json for machine parsing.
  • Use recommendation IDs from pz feed --json with pz rec and pz feedback.
  • Use canonical paper IDs with pz paper.
  • --atom returns a personal feed URL for feed readers.
  • pz rec --markdown may queue markdown generation if needed.
  • Anonymous pz paper --markdown only prints markdown when it is already available.

Agent usage guidance

  • If the user asks to inspect a paper from a project feed, prefer pz rec first.
  • If the user asks about the paper as a global/canonical object, use pz paper.
  • For scripting, fetch feeds with --json and then pass IDs into pz rec, pz feedback, or pz paper as appropriate.

Configuration

export PZ_API_URL="https://paperzilla.ai"

References

  • Docs: https://docs.paperzilla.ai/guides/cli
  • Quickstart: https://docs.paperzilla.ai/guides/cli-getting-started
  • Repo: https://github.com/paperzilla-ai/pz

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

83.51%
按下载量换算6,370

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install paperzilla 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills