mcpField
P
paperzilla

paperzilla

github.com/kalarislabsProductivity7746 installsUpdated 4d ago
Repository

About paperzilla

A skill that lets an agent access Paperzilla projects, recommendations, feeds, and canonical papers through the `pz` CLI. It supports reading and exporting research material, explaining relevance, and submitting recommendation feedback without prescribing a larger workflow.

Key features

  1. 01Browse project feeds
  2. 02Read recommendations and papers
  3. 03Retrieve papers as Markdown
  4. 04Export data as JSON
  5. 05Submit recommendation feedback

Use cases

  1. 01Review recent recommendations for a project
  2. 02Understand a recommendation's relevance
  3. 03Summarize a retrieved canonical paper
  4. 04Export a feed or paper for processing

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kalarislabs/research-agent-skills --skill paperzilla

After installing, type/paperzillain Claude Code to confirm it loaded.

Details

From the project README

Paperzilla

Use this skill when you want to chat with your agent about projects, recommendations, and canonical papers in Paperzilla.

What you can ask

  • "Give me the latest recommendations from project X."
  • "Open recommendation Y and explain why it matters."
  • "Fetch canonical paper Z as markdown and summarize it."
  • "Tell me how this paper is relevant to my research."
  • "Show me the feed for project X."
  • "Leave feedback on a recommendation."
  • "Export this paper, recommendation, or feed as JSON."

This is the core Paperzilla skill. It gives your agent direct access to Paperzilla data, but it does not impose a workflow or external delivery integration.

Access method

Most current profiles in this repo use the pz CLI.

If the current profile ships extra agent-specific instructions, follow those as well.

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

Use the official Linux install guide:

Build from source (Go 1.23+)

See the CLI repository for source builds:

Update

Check whether your CLI is up to date and get install-specific upgrade steps:

pz update

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

Supported values are auto, homebrew, scoop, release, and source.

Authentication

pz login

CLI reference

If the current profile uses pz, these are the core commands.

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

Feed output can include existing recommendation feedback markers:

  • [↑] upvote
  • [↓] downvote
  • [★] star
Read a canonical paper
pz paper <paper-id>
pz paper <paper-id> --json
pz paper <paper-id> --markdown
pz paper <paper-id> --project <project-id>
Open a recommendation from one of your projects
pz rec <project-paper-id>
pz rec <project-paper-id> --json
pz rec <project-paper-id> --markdown
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 clear <project-paper-id>

Output and automation

  • Prefer --json for machine parsing.
  • pz paper --markdown only returns markdown when it is already prepared.
  • pz rec --markdown can queue markdown generation and prints a friendly retry message while it is still being prepared.
  • --atom returns a personal feed URL for feed readers.

Configuration

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

References

Agent operating procedure

  1. Check the environment. Confirm the research question, databases, date range and inclusion criteria.
  2. Pin down the inputs. Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.
  3. Run a small version first. Run the search on one database with a narrow query and check that the results are relevant.
  4. Execute the full task using the instructions and references above.
  5. Validate the result. Every reference is retrieved from a real record with a resolvable identifier; counts and search strings are recorded.
  6. Report. State what was run (versions, commands, parameters), what was checked, and what is still uncertain.
If this happensDo this
An API rate-limits or returns errorsBack off and retry, reduce the batch size, or switch database, and report the gap.
A function, flag or endpoint in these instructions is missing in the installed versionCheck the installed version's own documentation (help(), --help, official docs), adapt, and tell the user. Never invent an API.
A required input, identifier or parameter is ambiguousAsk the user, or state the assumption explicitly before running.

Integrity rules

  • Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.
  • Never summarize a paper you have not retrieved; never cite from memory.
  • Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.
  • Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.

Comments

Markdown supported