research-paper-plan

Plan research papers and theses by mapping claims to experiments, figures, and citations.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Turning an advisor-given title or rough research idea into a concrete, evidence-grounded paper plan is hard: claims get written before experiments exist, sections lack purpose, and missing materials surface too late. This Skill converts a topic, codebase, or experiment set into a decision-oriented research blueprint with explicit claim-evidence links. ## Core Features & Use Cases - Topic Intake to Research Blueprint: Decompose an advisor-provided title into research object, task, keywords, technical routes, risks, and advisor-confirmation questions, with a helper script that scaffolds docs/thesis/ console files. - Claim-Evidence Mapping: Build a table linking every major claim to required experiments, figures/tables, and citations, marking each as ready, weak, or missing. - Outline and Figure Planning: Produce section-level thesis or paper outlines where every section has a purpose, plus a figure/table plan tied to specific claims. - Use Case: A graduate student receives the thesis title "Deep Learning for Spectral Classification" and uses this Skill to generate a topic intake record, a chapter outline, an experiment-to-claim map, and a prioritized list of questions for their advisor. ## Quick Start Use the research-paper-plan skill to turn my advisor's thesis title into a research blueprint with an outline, claim-evidence map, and next-action list.

Frequently Asked Questions about research-paper-plan

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

FAQPage Schema
How do I plan a research paper from an advisor-given title?

Run Topic Intake first: decompose the title into research object, task, keywords, and technical routes, then build a claim-evidence map and section outline. The included generate_topic_intake.py script scaffolds topic-intake.md and related thesis console files automatically.

How to map paper claims to experiments and figures?

Use the claim-evidence map table: each claim lists required evidence, current evidence status, the supporting figure or table, and citation needs. Claims are marked ready, weak, or missing so unsupported conclusions are never drafted as fact.

Can I use this for a graduation thesis as well as a journal paper?

Yes. The workflow supports graduation theses, dissertations, journal manuscripts, conference papers, and reports. For theses it adds school-facing sections such as abstract, related work, method, experiments, appendix, and defense preparation.

Does the topic intake script support Chinese thesis titles?

Yes. The generate_topic_intake.py script accepts non-ASCII titles and detects tasks like classification, prediction, and detection from Chinese keywords. For uncertain shell encoding, pass the title via a UTF-8 file using --title-file.

What are the limitations of this paper planning approach?

It does not invent experiments, citations, datasets, or results; insufficient evidence is marked missing rather than smoothed over. Experiment implementation, code architecture, and reproducibility work are routed to a separate experiment-engineering skill.