
Research Proposal
Generates academic research proposals for PhD applications with a structured five-phase workflow: requirements gathering, literature collection, outline generation, content writing, and review. It pulls from WebSearch for open access materials and integrates with Zotero MCP to leverage your existing library of closed-access papers. Outputs 2,000-4,000 word proposals following Nature Reviews academic conventions, supporting both STEM and humanities fields in English or Chinese. The workflow is methodical, asking for approval on the outline before generating content, and emphasizes prose-based writing over bullet points. If you're applying to doctoral programs and need a proper research proposal that references real literature rather than hallucinated citations, this handles the structure and academic voice while you focus on your actual research ideas.
- skills.sh installs
- 935
- GitHub stars
- 885
- last updated
- Aug 21, 2026
Install
$ npx -y skills add luwill/research-skills --skill research-proposal --agent claude-codeInstalls into .claude/skills of the current project.
Files
Research Proposal Generator
Generate a forward-looking academic research proposal — a plan for research not yet done — following flagship academic writing conventions, in English or Chinese.
This skill produces the first draft correctly, not a template to be fixed later. Its single most important discipline is citation integrity: a proposal with a fabricated reference is an academic-integrity problem, not a style problem. Read references/CITATION_INTEGRITY.md before Phase 2.
Core Principles
Prose first. Proposals read as flowing, connected paragraphs — not bulleted lists. Reserve lists for a focused set of research questions/objectives (2–4 items) and timeline milestones. Never enumerate contributions, methodology, background, or significance as bullets; narrate them. Full rules and examples: references/WRITING_STYLE_GUIDE.md.
Sponsors
Details
- Repository
- github.com/luwill/research-skills
- Categories
- Git & Pull Requests, Code Review & Quality, Data Science & ML, Productivity & Planning
- First seen
- Jun 3, 2026