paperzilla

Use the Paperzilla CLI (pz) to search, filter, and browse high-signal academic papers. Trigger when the user wants to check research feeds, list projects, inspect must-read papers, export JSON results, or generate Atom feed links from Paperzilla. Requires a Paperzilla account and pz login.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "paperzilla" with this command: npx skills add pors/paperzilla

Paperzilla CLI (pz) 🦖

A command-line tool for Paperzilla, an AI-powered scientific paper discovery platform.

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/

Authentication

Log in with your Paperzilla account before doing anything else:

pz login

Core Commands

List Projects

Lists your available projects and their IDs.

pz project list

Browse Feed

Fetches the papers for a given project ID.

pz feed <project-id>

Filter & Export Flags:

  • --must-read : Filter only for must-read papers.
  • --limit 5 : Limit the number of returned results.
  • --since YYYY-MM-DD : Filter papers published after a specific date.
  • --json : Output in JSON format (excellent for parsing with other tools or piping into Claude/Gemini).

Example:

pz feed 12345 --must-read --limit 5 --json

Feed Reader Integration (RSS/Atom)

Get an Atom feed URL you can add to any feed reader (Vienna RSS, NetNewsWire, Feedly, etc.):

pz feed <project-id> --atom

This prints a URL with an embedded feed token. Running --atom again after revoking will generate a new token.

API Configuration

By default, it connects to https://paperzilla.ai. To override, set PZ_API_URL.

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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Agent Dev Workflow

Orchestrate coding agents (Claude Code, Codex, etc.) to implement coding tasks through a structured workflow. Use when the user gives a coding requirement, f...

Registry SourceRecently Updated
Coding

Cortex Engine

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and...

Registry SourceRecently Updated
Coding

Skill Blocker - 安全守卫

Blocks execution of dangerous commands and risky operations like destructive deletions, credential theft, code injection, and unauthorized system changes to...

Registry SourceRecently Updated
014
Profile unavailable