By xuxiguo
Multi-agent academic research factory: data extraction, analysis, paper writing, revision, and presentation — conductors as slash commands, workers as subagents, with backbone-file project memory, guard hooks, and research skills.
Orchestrates analysis: sample construction → regressions → tables
Orchestrates data extraction: plan → pull → process → validate
Three-pillar research idea brainstorming and ranking
Bootstrap a research project for the Research Paper Factory: folder structure, backbone files, project CLAUDE.md contract
Deep reading discussion partner for academic finance papers
Cleans, transforms, merges extracted data into analysis variables
Manages references, verifies citations, formats bibliographies
Builds LaTeX PDFs, diagnoses compilation errors
Drafts publication-quality paper sections in academic tone
Prepares journal submission packages with formatting compliance
Safely update backbone files (_STATE.md, _STATE.md, _INDEX.md, _LESSONS.md). Use when modifying project state tracking files. Always read current content before writing.
Session recovery after context compression or new session start. Use at the beginning of every session to restore working state from _STATE.md and git log.
Critical-review and auto-proceed mode handling, with fix-in-loop until APPROVED before next phase
Data quality validation and completeness checks. Use when verifying processed datasets, checking merge quality, or validating sample construction results.
Track regression experiments in _EXPERIMENTS.md. Use after every regression run to log specification, results, and sign consistency. Prevents losing track of which specification produced which result.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
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.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
A multi-agent system for empirical academic research (finance/economics oriented, adaptable to any field). One install gives you, in any project, on any Claude Code surface (CLI, VS Code extension):
/research-factory:strategist, idea-lab, paper-lab,
de-conductor, da-conductor, pw-editor, rev-strategist, presenter,
plus /research-factory:init-project/plugin marketplace add xuxiguo/research-factory-claude
/plugin install research-factory@research-factory-claude
/reload-plugins
Requires Claude Code v2+ and python on PATH (for hooks and pipeline scripts).
In a fresh project: /research-factory:init-project My Project — creates the folder
structure, backbone files, and project CLAUDE.md contract. Then
/research-factory:strategist to plan your research design.
Everything works out of the box (web search uses Claude Code's built-in WebSearch — no API key needed). Optional extras:
| Feature | Requirement | Without it |
|---|---|---|
| SS-Imager (AI slide images) | OPENAI_API_KEY env var | Slides build without AI images |
| Stata regressions | Stata + a local stata-mcp server | DA-Executor falls back to Python |
{YOUR_OBSIDIAN_VAULT} placeholders in idea-lab / paper-lab | Edit to your notes folder | Literature-notes integration skipped |
| SLURM skills | A SLURM cluster (partition names are examples from one university cluster — adapt) | Local execution path used |
Placeholders like {YOUR_OBSIDIAN_VAULT}, {YOUR_CONTACTS_PROJECT} mark spots to
personalize; agents skip those steps if the paths don't exist.
Generated from a private research workflow repository; sanitized for public use. Issues and PRs welcome.
npx claudepluginhub xuxiguo/research-factory-claude --plugin research-factoryComplete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
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.
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
Comprehensive 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.