By PinkGranite
AI-powered academic paper generation plugin for Claude Code. Generate LaTeX papers from metadata interactively.
Interactively build EasyPaper PaperMetaData from a research-materials folder, using Claude Code's own file-investigation tools and other installed skills (`paperhub-*`, `pdf`, `exa-search`, `sequential-thinking`, `deep-research`). Output is a JSON file consumable by `/paper-from-metadata`.
Generate a paper directly from metadata using EasyPaper Python SDK.
Generate or revise a single paper section through EasyPaper.
Set up EasyPaper environment including Python dependencies and LaTeX toolchain.
Run the EasyPaper end-to-end paper generation workflow with guided setup and metadata collection.
Enforce academic writing and LaTeX drafting conventions for EasyPaper outputs.
Interactively build EasyPaper PaperMetaData from a research-materials folder using Claude Code's own file-investigation tools and other installed skills. Output is a JSON file consumable by the `paper-from-metadata` skill.
Generate a full academic paper from metadata using EasyPaper Python SDK. Collects metadata interactively if not provided, then generates the paper directly.
Automatically set up EasyPaper environment including Python dependencies and LaTeX toolchain in an isolated environment.
Apply venue-specific constraints for EasyPaper generation.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
EasyPaper is a multi-agent academic paper generation system. It turns a small set of metadata (title, idea, method, data, experiments, references) into a structured LaTeX paper and optionally compiles it into a PDF through a typesetting agent.
EasyPaper can be used in two modes:
pip install -e . and call from Python directly (no server needed)pip install -e ".[server]" and run as a FastAPI servicefrom easypaper import EasyPaper)generate_stream() (SDK) or SSE (server)pdflatex + bibtex) for PDF compilationpdf2image for PDF-to-image conversion
brew install popplerapt install poppler-utilspip install -e .
cp examples/config.example.yaml configs/dev.yaml
# Edit configs/dev.yaml — replace YOUR_API_KEY with real keys
.env file):export AGENT_CONFIG_PATH=./configs/dev.yaml
import asyncio
from easypaper import EasyPaper, PaperMetaData
async def main():
ep = EasyPaper(config_path="configs/dev.yaml")
result = await ep.generate(PaperMetaData(
title="My Paper",
idea_hypothesis="...",
method="...",
data="...",
experiments="...",
))
print(f"Status: {result.status}, Words: {result.total_word_count}")
asyncio.run(main())
async for event in ep.generate_stream(metadata):
print(f"{event.get('phase', '')}: {event.get('message', '')}")
See examples/sdk_demo.py for a complete working example.
To run as a FastAPI service (for external integrations):
pip install -e ".[server]"
uvicorn src.main:app --reload --port 8000
curl http://localhost:8000/healthz
curl -X POST http://localhost:8000/metadata/generate \
-H "Content-Type: application/json" \
-d @economist_example/metadata.json
python scripts/generate_paper.py --input economist_example/metadata.json
pip install -e ".[dev]" # pytest, ipython, etc.
pip install -e ".[vlm]" # Claude VLM review support
pip install -e ".[server]" # FastAPI + uvicorn
The application loads configuration from AGENT_CONFIG_PATH (defaults to ./configs/dev.yaml).
You can also set this variable in a .env file at the project root.
See configs/example.yaml for a fully commented configuration template. Each agent entry defines
its model and optional agent-specific settings.
Key fields per agent:
model_name — LLM model identifierapi_key — API key for the model providerbase_url — API endpoint URLAdditional top-level sections:
skills — skills system toggle and active skill listtools — ReAct tool configuration (citation validation, paper search, etc.)vlm_service — shared VLM provider for visual review (supports OpenAI-compatible and Claude)GET /healthz — health checkGET /config — current app configGET /list_agents — list registered agents and endpoints/agent/* and /metadata/*npx claudepluginhub pinkgranite/easypaper --plugin easypaperComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
TypeScript/JavaScript full-stack development with NestJS, React, and React Native
Give your AI a memory — mine projects and conversations into a searchable palace. 33 MCP tools, auto-save hooks, and guided setup.