ResearchCommunity

multi-agent-academic-paper-workflow

A multi-agent academic paper workflow for structured writing, iterative polishing, fact-checking and rule-based academic compliance optimization. Suitable for 0–30 pages course papers and seminar theses.

thefoolimanAdded Oct 3, 2026

Catalog skill by thefooliman: A multi-agent academic paper workflow for structured writing, iterative polishing, fact-checking and rule-based academic compliance optimization. Suitable for 0–30 pages course papers and seminar theses. Install into Cursor, Claude, Codex, or VS Code from this page or review the source for multi-agent-academic-paper-workflow.

Add to Cursor Add to VS Code Add to Claude Add to Codex View source

Ads

Installation

git clone https://github.com/thefooliman/multi-agent-academic-paper-workflow

Install guides: Cursor skills, Claude Code skills, Codex skills, or VS Code Copilot skills.

Skill body

Paper-Agent-Workflow

A multi-agent academic writing workflow for Claude Code: structured chapter generation, iterative polishing, double review (self-review + blind fact-check), guard rule enforcement, human-in-the-loop confirmation, and breakpoint resume.

Commands

/paper-write: generate a new paper chapter by chapter (write mode)
/paper-check: polish an existing .md / .tex / .docx manuscript (check mode)
/paper-radical: aggressive de-AIGC humanization (radical mode)
/paper-stop: save state and stop
/paper-reset: clear state and start fresh

Modes

Standard (write/check): fix the must-fix AI-tell patterns plus sentence rhythm, keep the natural academic voice.
Radical: apply the full pattern catalog, the six-step loop, the five-dimension score (pass ≥ 42), and section-by-section rewrite: for passing Turnitin AI, GPTZero, 知网, 万方.

Resume

State is saved to state.json + workflow-log.json in your working directory after every step. After /paper-stop (or an interrupt), run /paper-write or /paper-check again; it will offer to resume exactly where you left off.

Agents

The coordinator (this session) dispatches worker sub-agents: writer, polishing, self-review, blind-fact-check, guard, io-worker. All agent-to-agent communication is JSON, following schemas/.

multi-agent-academic-paper-workflow

Installation

Skill body

Paper-Agent-Workflow

Commands

Modes

Resume

Agents

Related skills

Skill body

Skill body

Paper-Agent-Workflow

Commands

Modes

Resume

Agents

Related skills