WenyuChiou/ai-research-skills

83 stars · Last commit 2026-05-31

Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.

README preview

# AI Research Skills

> A skill catalog that won't let you spend 6 months on a research gap
> that's already closed, isn't a real contribution, or isn't feasible.
> Every candidate thesis topic goes through a 3-gate decision dossier
> first — and the rest of the pipeline (literature → design → build
> → run → write → submit) only flows from candidates that pass.

Languages: [English](README.md) | [繁中](README.zh-TW.md) ·
[Pipeline](docs/pipeline.md) ·
[Examples](docs/examples.md) ·
[Runtime contract](docs/runtime-contract.md) ·
[Glossary](docs/glossary.md)

**What this is.** A catalog of 15 Claude Code skills built around one
stubborn question most research-AI tools dodge: *is this research gap
actually worth doing?* The pipeline opens with a structured decision
dossier — three gates: open / contribution / feasibility — and
downstream stages (research design, manuscript drafting, reviewer
response) only fire on a candidate that clears all three. Built for graduate students, PhDs, postdocs, and

View full repository on GitHub →