research-workflow-orchestrator

Coordinates multi-stage thesis and research workflows across specialized research skills.

2|Updated May 22, 2026
One-click install
npx skills add https://github.com/CDUTAKL/research-workflow-kit --skill research-workflow-orchestrator-cdutakl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-workflow-orchestrator
Source: https://github.com/CDUTAKL/research-workflow-kit/tree/main/skills/research-workflow-orchestrator
Command: npx skills add https://github.com/CDUTAKL/research-workflow-kit --skill research-workflow-orchestrator-cdutakl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Managing a full thesis or research paper project involves juggling literature review, experiments, figures, writing, and audits; this Skill turns broad research requests into staged workflows with clear skill routing, artifacts, and next actions. ## Core Features & Use Cases - Skill Routing: Maps each research stage to the right specialized skill, such as literature review, experiment engineering, results analysis, figure planning, paper writing, and final audit. - Twelve-Stage Workflow: Provides a structured stage model from topic intake through literature discovery, experiments, figure planning, writing, Mac document production, and Windows compatibility review. - Project Console: Defines a docs/thesis evidence console with files for experiment registries, claim-evidence maps, citation provenance, and final audit records. - Use Case: A graduate student starting a thesis asks what to do next; the Skill inspects the project console, identifies the current stage, and recommends the exact skill sequence, artifacts, and concrete actions. ## Quick Start Use the research-workflow-orchestrator to assess my current thesis project state and plan the next research steps.

Frequently Asked Questions about research-workflow-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan a thesis workflow from start to finish?

Use the twelve-stage model covering planning, literature review, experiment design, implementation, runs, analysis, figures, writing, document production, and final audit. Each stage maps to a specialized skill and produces traceable artifacts in the docs/thesis console.

What skills does the research workflow orchestrator coordinate?

It routes to research-paper-plan, research-literature-review, semanticscholar-skill, research-experiment-engineering, research-results-analysis, research-paper-figures, research-paper-writing, research-data-availability, and research-final-audit, plus tools like Zotero, Scite, and draw.io.

How do I track experiments and evidence for a research paper?

Record experiments in experiment-registry.md, link claims to results in claim-evidence-map.md, and maintain citation provenance and data availability files. The console keeps every claim traceable to experiments, figures, and verified citations.

Does this workflow support remote GPU training?

Yes, it defines execution targets: local_mac for CPU smoke tests, remote_desktop_4060 as the primary GPU target, and cloud_autodl as a fallback with auto-save and auto-shutdown. Run commands, checksums, and artifact recovery are recorded in the runbook.

When should I not use this orchestrator skill?

Skip it for single isolated tasks like reading one PDF or drafting one section; use the specialized skill directly. It is designed for multi-stage projects where coordinating skills, artifacts, and evidence across stages matters.