Updated 6mo ago
by sunnnybala
Rstack
Research automation skills for Claude Code. Idea to submittable paper in one session.
69 GitHub stars (69)
Steady at 69 stars — no new stars in the 16 days since Sep 30.
- 9 skills (9 skills found in its SKILL.md files)
- 10 forks (10 forks)
- 6mo ago last update (Last updated 6mo ago)
Install
Skills CLI
npx skills add sunnnybala/Rstack
Asks which skills and agents to install. Just one: npx skills add sunnnybala/Rstack --skill rstack — add -g for every project.
Claude Code
git clone https://github.com/sunnnybala/Rstackcp -r "Rstack" ~/.claude/skills/Rstack
Copies the rstack skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add sunnnybala/Rstack
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
rstack
Research automation skills for Claude Code. Full pipeline from idea to submittable paper. Skills: /lit-review, /novelty-check, /experiment, /analyze-results, /write-paper, /research (orchestrator), /setup.
SKILL.md on GitHub (opens in a new tab) -
analyze-results
Turn raw experiment outputs into publication-ready figures, tables, and statistical analysis. Use when asked to "analyze results", "make figures", "create tables", or "visualize experiments". Proactively invoke after /experiment produces results.
analyze-results/SKILL.md on GitHub (opens in a new tab) -
experiment
Design and run ML experiments on cloud GPUs. Generates experiment code, runs on Modal, tracks results in JSONL. Use when asked to "run experiments", "train a model", "test this hypothesis", or "benchmark this approach". Proactively invoke when the user has a refined research idea and needs to validate it experimentally.
experiment/SKILL.md on GitHub (opens in a new tab) -
lit-review
Find relevant papers across major indices, structured summary, gap analysis. Use when asked to "find papers", "literature review", "what's been done", "related work", or "survey the field". Proactively invoke when the user describes a research idea and needs to understand existing work.
lit-review/SKILL.md on GitHub (opens in a new tab) -
novelty-check
Compare your research idea against existing literature, assess novelty, and refine the hypothesis. Produces refined-idea.md that downstream skills consume. Use when asked to "check novelty", "is this novel", "compare against existing work", or "refine my idea". Proactively invoke after /lit-review completes.
novelty-check/SKILL.md on GitHub (opens in a new tab) -
research
Full research pipeline: idea to submittable paper in one session. Orchestrates /lit-review, /novelty-check, /experiment, /analyze-results, and /write-paper with human checkpoints at every phase boundary. Use when asked to "do research", "write a paper", "full pipeline", or "idea to paper". This is the flagship skill — chains all other skills together.
research/SKILL.md on GitHub (opens in a new tab) -
rstack-upgrade
Upgrade RStack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade rstack", "update rstack", or "get latest version".
rstack-upgrade/SKILL.md on GitHub (opens in a new tab) -
setup
Configure compute providers and research tools for RStack. Use when asked to "setup rstack", "configure modal", "install tectonic", or when any skill prints NEEDS_SETUP. Run this once after installation, or again to reconfigure providers.
setup-skill/SKILL.md on GitHub (opens in a new tab) -
write-paper
Generate venue-formatted LaTeX paper with real results and citations. Use when asked to "write the paper", "draft the paper", "format for arXiv", or "generate LaTeX". Proactively invoke when the user has experiment results and wants to write them up.
write-paper/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs…
-
cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.