← Back to Skills Marketplace
102
Downloads
1
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install paper2diagram
Description
论文 PDF → 方法/结构抽取 → 学术评审式总结 → 多张论文风格配图（依托 Gemini + nano_banana 网关）。
Usage Guidance
This skill is an instruction-only wrapper that expects you to host or clone the actual workflow repository and to supply Gemini and Banana API keys. Before using it: (1) inspect and clone the referenced repo locally and review its code; (2) run it in an isolated environment (virtualenv/container); (3) only point GEMINI_BASE_URL / BANANA_PRO_BASE_URL to gateways you control or trust — the skill will send PDFs to whatever gateway you configure; (4) prefer local outputs/ copies of generated images rather than relying only on external temporary URLs; (5) limit API key permissions and rotate keys if you test with sensitive data. The skill appears coherent with its purpose, but you should verify the external repo and gateway behavior before running on confidential PDFs.
Capability Assessment
Purpose & Capability
Name/description match what the skill requests: it needs a Gemini API key and a Banana/nano_banana key to call LLM/image gateways and python3 to run a local workflow. Those credentials are proportional to producing summaries and images.
Instruction Scope
SKILL.md instructs the agent to read a local PDF and run a local Python module (python -m app.openclaw_main ...). That stays within the stated purpose, but the skill is instruction-only and expects you to clone a separate repo containing app.openclaw_main; without that repo the command will fail. The doc also suggests sending the PDF to the configured gateway(s) — you must trust those gateways before uploading sensitive PDFs.
Install Mechanism
No install spec (instruction-only) — nothing will be written by the skill itself. The README instructs you to clone an external repository and install dependencies locally; that is an explicit user action rather than an automated install.
Credentials
Declared required env vars are GEMINI_API_KEY and BANANA_PRO_API_KEY, which align with the stated integrations. SKILL.md additionally documents several optional env vars (GEMINI_BASE_URL, GEMINI_MODEL, BANANA_PRO_BASE_URL, BANANA_MODEL, ENABLE_BANANA) that are not listed in requires.env — a mild inconsistency. No unrelated credentials or config paths are requested.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges. It does instruct running local Python code and writing images to an outputs/ directory, which is expected and limited to its own scope.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paper2diagram - After installation, invoke the skill by name or use
/paper2diagram - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Chinese docs + safer metadata (declare BANANA_PRO_API_KEY).
v1.0.1
Add quick usage example to SKILL.md.
v1.0.0
Initial release of paper2diagram.
- Reads local paper PDFs, extracts Method/Architecture sections, and summarizes content like a senior reviewer.
- Generates publication-style academic figures covering background, architecture, innovations, experiments, and limitations using Gemini + nano_banana.
- Saves all generated diagrams to a local outputs/ directory.
- Requires Python 3, internet access, and API keys for Gemini and nano_banana.
- Designed for integration with OpenClaw; includes setup and usage instructions.
Metadata
Frequently Asked Questions
What is Paper2diagram?
论文 PDF → 方法/结构抽取 → 学术评审式总结 → 多张论文风格配图（依托 Gemini + nano_banana 网关）。 It is an AI Agent Skill for Claude Code / OpenClaw, with 102 downloads so far.
How do I install Paper2diagram?
Run "/install paper2diagram" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Paper2diagram free?
Yes, Paper2diagram is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Paper2diagram support?
Paper2diagram is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Paper2diagram?
It is built and maintained by QBC-OIO (@qbc-oio); the current version is v1.0.2.
More Skills