Chat with your agent about projects, recommendations

Paperzilla

by K-Dense-AI · MIT license · ★ 45,977 on GitHub · updated Sep 21

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or…

---
name: paperzilla
description: Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.
license: MIT
metadata:
  version: "1.0"
  skill-author: Paperzilla Inc
---

# 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."

Overview

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

What you get

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 mess
--atom returns a personal feed URL for feed readers.

Manual install (npx, ZIP)

Claude Codenpx skills add K-Dense-AI/scientific-agent-skills --skill paperzilla -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/K-Dense-AI/scientific-agent-skills/tar.gz/49c6e97775ea \
  | tar -xz -C ~/.claude/skills --strip-components=2 scientific-agent-skills-49c6e97775ea/skills/paperzilla

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/e65ce5d987128e5f1f7e/paperzilla.zip" -OutFile "$env:TEMP\paperzilla.zip"; Expand-Archive "$env:TEMP\paperzilla.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.7 KB

Read the files here

K-Dense-AI/49c6e971 file

SKILL.md3.7 KB

SKILL.md

Show the full text160 lines

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:

https://docs.paperzilla.ai/guides/cli-getting-started

Build from source (Go 1.23+)

See the CLI repository for source builds:

https://github.com/paperzilla-ai/pz

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

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

1	---
2	name: paperzilla
3	description: Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.
4	license: MIT
5	metadata:
6	version: "1.0"
7	skill-author: Paperzilla Inc
8	---
9
10	# Paperzilla
11
12	Use this skill when you want to chat with your agent about projects, recommendations, and canonical papers in Paperzilla.
13
14	## What you can ask
15
16	- "Give me the latest recommendations from project X."
17	- "Open recommendation Y and explain why it matters."
18	- "Fetch canonical paper Z as markdown and summarize it."
19	- "Tell me how this paper is relevant to my research."
20	- "Show me the feed for project X."
21	- "Leave feedback on a recommendation."
22	- "Export this paper, recommendation, or feed as JSON."
23
24	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.
25
26	## Access method
27
28	Most current profiles in this repo use the `pz` CLI.
29
30	If the current profile ships extra agent-specific instructions, follow those as well.
31
32	## Install
33
34	### macOS
35	```bash
36	brew install paperzilla-ai/tap/pz
37	```
38
39	### Windows (Scoop)
40	```bash
41	scoop bucket add paperzilla-ai https://github.com/paperzilla-ai/scoop-bucket
42	scoop install pz
43	```
44
45	### Linux
46	Use the official Linux install guide:
47
48	- https://docs.paperzilla.ai/guides/cli-getting-started
49
50	### Build from source (Go 1.23+)
51	See the CLI repository for source builds:
52
53	- https://github.com/paperzilla-ai/pz
54
55	## Update
56
57	Check whether your CLI is up to date and get install-specific upgrade steps:
58
59	```bash
60	pz update
61	```
62
63	If detection is ambiguous, override it explicitly:
64
65	```bash
66	pz update --install-method homebrew
67	pz update --install-method scoop
68	pz update --install-method release
69	pz update --install-method source
70	```
71
72	Supported values are `auto`, `homebrew`, `scoop`, `release`, and `source`.
73
74	## Authentication
75
76	```bash
77	pz login
78	```
79
80	## CLI reference
81
82	If the current profile uses `pz`, these are the core commands.
83
84	### List projects
85	```bash
86	pz project list
87	```
88
89	### Show one project
90	```bash
91	pz project <project-id>
92	```
93
94	### Browse project feed
95	```bash
96	pz feed <project-id>
97	```
98
99	Useful flags:
100	- `--must-read`
101	- `--since YYYY-MM-DD`
102	- `--limit N`
103	- `--json`
104	- `--atom`
105
106	Examples:
107	```bash
108	pz feed <project-id> --must-read --since 2026-03-01 --limit 5
109	pz feed <project-id> --json
110	pz feed <project-id> --atom
111	```
112
113	Feed output can include existing recommendation feedback markers:
114
115	- `[↑]` upvote
116	- `[↓]` downvote
117	- `[★]` star
118
119	### Read a canonical paper
120	```bash
121	pz paper <paper-id>
122	pz paper <paper-id> --json
123	pz paper <paper-id> --markdown
124	pz paper <paper-id> --project <project-id>
125	```
126
127	### Open a recommendation from one of your projects
128	```bash
129	pz rec <project-paper-id>
130	pz rec <project-paper-id> --json
131	pz rec <project-paper-id> --markdown
132	```
133
134	### Leave recommendation feedback
135	```bash
136	pz feedback <project-paper-id> upvote
137	pz feedback <project-paper-id> star
138	pz feedback <project-paper-id> downvote --reason not_relevant
139	pz feedback clear <project-paper-id>
140	```
141
142	## Output and automation
143
144	- Prefer `--json` for machine parsing.
145	- `pz paper --markdown` only returns markdown when it is already prepared.
146	- `pz rec --markdown` can queue markdown generation and prints a friendly retry message while it is still being prepared.
147	- `--atom` returns a personal feed URL for feed readers.
148
149	## Configuration
150
151	```bash
152	export PZ_API_URL="https://paperzilla.ai"
153	```
154
155	## References
156
157	- Docs: https://docs.paperzilla.ai/guides/cli
158	- Quickstart: https://docs.paperzilla.ai/guides/cli-getting-started
159	- Repo: https://github.com/paperzilla-ai/pz
160