← Back to Skills Marketplace
Paperzilla Monitor
by
Mark Pors 🦖
· GitHub ↗
· v1.1.4
· MIT-0
241
Downloads
1
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install paperzilla-research-monitor
Description
Monitor and discuss research papers from one Paperzilla project using the `pz` CLI inside OpenClaw. Use when users want recent papers, metadata, markdown-bas...
Usage Guidance
This skill appears coherent and limited: it will run your local 'pz' CLI (so it will act with whatever Paperzilla identity you already logged in with) and may persist a list of previously suggested paper IDs in the agent/profile memory to avoid repeats. Before enabling: (1) confirm the 'pz' binary on the host is the official CLI and that you’ve authenticated it intentionally; (2) ask where the per-project history will be stored and how long it is retained if you care about privacy; (3) confirm the host's OpenClaw message routing (Telegram) is trusted before allowing scheduled external deliveries. No credentials or installs are requested by the skill itself.
Capability Analysis
Type: OpenClaw Skill
Name: paperzilla-research-monitor
Version: 1.1.4
The skill is a research paper monitoring tool designed to interact with the Paperzilla CLI (`pz`) to fetch, summarize, and discuss academic papers. It defines clear workflows for on-demand discussions and scheduled weekday briefs delivered via the `message` tool (e.g., to Telegram). The instructions in SKILL.md and AGENT.md are well-scoped, focusing exclusively on Paperzilla-related commands and maintaining a local history of processed paper IDs to avoid duplicates, with no evidence of data exfiltration, malicious execution, or unauthorized system access.
Capability Assessment
Purpose & Capability
Name/description match the required artifacts: the skill requires the 'pz' CLI and explicitly uses it for project/ feed/ paper operations. No unrelated binaries, credentials, or unexpected system access are requested.
Instruction Scope
SKILL.md is narrowly scoped to running pz CLI commands (exec) and delivering output via message only when profile-approved or user-requested. It explicitly forbids reading arbitrary files or unrelated environment variables. It does direct the agent to persist a per-project history of proposed Paperzilla IDs across runs (profile-owned state), which is within scope for a recurring brief workflow.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low risk and consistent with relying on a preinstalled 'pz' binary.
Credentials
The skill requires no environment variables or credentials and assumes the human has already run 'pz login'. There are no requests for unrelated secrets or external service credentials.
Persistence & Privilege
always:false and normal autonomous invocation. The skill asks to store a per-project history of Paperzilla IDs in scheduling job state or profile-owned memory to avoid repeat suggestions; this is reasonable for recurring briefs but you should confirm where that storage lives and retention/purging rules.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paperzilla-research-monitor - After installation, invoke the skill by name or use
/paperzilla-research-monitor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.4
Split OpenClaw profile into SKILL.md + AGENT.md, keep explicit rec vs paper handling, feedback commands, and safer delivery rules.
v1.1.3
Clarify that messaging is user-requested only, declare tool/config requirements more explicitly, and tighten markdown/polling behavior for Paperzilla-first deep dives.
v1.1.2
Prefer pz markdown for deep dives, poll/retry when markdown is still generating, and avoid falling back to arXiv links by default.
v1.1.1
Metadata cleanup: align embedded version with published version, add homepage, and normalize OpenClaw dependency metadata for pz.
v1.1.0
Sync with newer pz workflows: add rec/feedback handling, canonical vs recommendation guidance, improved triage flow, and explicit OpenClaw metadata.
v1.0.0
**Introduces Paperzilla research paper feed monitoring and triage workflows.**
- Paperzilla high-level workflow skill built on top of Paperzilla access. It is for repeated feed triage, digest generation, and optional delivery to tools like Slack or Telegram in supported profiles. Focus on research triage and digest workflows over pure CLI usage.
- Step-by-step workflow for monitoring, triaging, and summarizing project feeds.
- Relevance classification (🟢/🟡/🔴) for feed items and concise digest formatting.
- Supports both pz-CLI and MCP data access methods.
- Introduces agent-specific delivery rules and external reporting via `AGENT.md`.
- Clarifies edge cases like feed size, missing markdown, and empty results.
Metadata
Frequently Asked Questions
What is Paperzilla Monitor?
Monitor and discuss research papers from one Paperzilla project using the `pz` CLI inside OpenClaw. Use when users want recent papers, metadata, markdown-bas... It is an AI Agent Skill for Claude Code / OpenClaw, with 241 downloads so far.
How do I install Paperzilla Monitor?
Run "/install paperzilla-research-monitor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Paperzilla Monitor free?
Yes, Paperzilla Monitor is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Paperzilla Monitor support?
Paperzilla Monitor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Paperzilla Monitor?
It is built and maintained by Mark Pors 🦖 (@pors); the current version is v1.1.4.
More Skills