PaperOrchestra skill
A skills pack for writing a research paper: a multi-agent pipeline from outline and plots to literature review and refinement, with no LLM keys
- 700 ★ on the repository
- Last commit
Extended access
Why this level
- Runs helper Python scripts and reaches web search
- Writes paper materials to disk
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/paperorchestraDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs helper Python scripts and reaches web search
- Writes paper materials to disk
This is third-party code. Review the repository files before installing.
What it does
PaperOrchestra is a pluggable skills pack that lets any coding agent run the multi-agent research-paper writing pipeline from the paper of the same name. The pipeline is split into five steps: outline, plotting, literature review, section writing and content refinement, plus benchmark and autorater skills. The skills reproduce the exact prompts for each agent from the paper's appendix and turn unstructured materials into a submission-ready LaTeX paper. The pipeline needs no LLM keys: it runs on top of an agent that has a native web search tool.
Who it is for. For researchers and authors who want a reproducible research-paper writing process through an agent.
Good fit when
- You need to turn research materials into a LaTeX paper via a pipeline
- You need a literature review with citation checks through an agent
- You need a reproducible multi-agent writing process
Not a fit when
- You need one-off help with a paragraph rather than the whole pipeline
- Your agent has no native web search for the literature review
Example request
Run my materials through PaperOrchestra: build the outline, literature review and sections into a LaTeX paperLimitations
The pipeline assumes an agent with a native web search tool and no LLM keys. The deterministic helper scripts need Python and the requirements.txt dependencies. The skills reproduce the paper's method, but the result's quality depends on the source materials and the model's work. The license is non-standard, so check the terms before use.
How to disable. Remove the skill symlinks from the agent's directory and delete the cloned paper-orchestra folder.
FAQ
Are LLM keys needed?
No. The pipeline runs on an agent with native web search and no keys; two optional integrations only improve coverage.
What is the pipeline made of?
Five agents: outline, plotting, literature review, section writing and refinement, plus benchmark and autorater skills.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill set for research papers: from research assets to a LaTeX draft with evidence checks and a review simulation.
The paper-spine skill takes a topic, materials and data through a scientific paper: literature, text, figures, review and Word, LaTeX and PDF files
Eight skills draft a CS, AI or ML paper section by section and halt any section that lacks supporting evidence.
A skill set for academic papers: deep method analysis, visual slides and a coherent write-up from a paper PDF
Two skills for academic papers: a strategist for planning and a composer for writing, with quality checkpoints at each stage
Eight skills for LaTeX research papers, from topic to compiled PDF, with verified BibTeX citations and gated steps
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| PaperOrchestra (this card) | no | 700 | ||
| CCFA-Skills | no | 3,532 | a family of 17 skills for a research paper | |
| PaperSpine5 | no | 6,272 | the paper-spine skill takes a topic | |
| ClaudeR | no | not required | 372 | MCP server that connects Claude Code and Codex to an open R or Python |
README in short
The README presents PaperOrchestra as a pluggable skills pack that reproduces the multi-agent research-paper writing pipeline from the paper of the same name. Its five agents (outline, plotting, literature review, sections, refinement) reportedly beat single-agent and tree-search baselines on the PaperWritingBench benchmark. The skills use the exact prompts from the paper's appendix. Install is via git clone and pip install of dependencies, then symlinking the skills into the agent's directory. The pipeline needs no LLM keys under a host with native web search, with optional integrations.