Updated 4mo ago
by WUBING2023
ReproRun
🔬 A skill that automatically reproduces the numerical claims of academic papers — read paper → find code → build env → run → compare against the paper. 1 orchestrator + 6 specialized agents.
50 GitHub stars (50)
- 1 skill (1 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 4mo ago last update (Last updated 4mo ago)
Install
Skills CLI
npx skills add WUBING2023/ReproRun
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/WUBING2023/ReproRuncp -r "ReproRun/paper-reproduction" ~/.claude/skills/
Copies the paper-reproduction skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add WUBING2023/ReproRun
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.
-
paper-reproduction
Use whenever the user wants to reproduce, replicate, or verify results from an academic paper — especially ML/CV/NLP papers with public GitHub repos and Python codebases. Triggers on: 复现, reproduce, replicate, 复现论文, 跑论文代码, verify results, paper reproduction, 验证实验结果, 论文复现, check if a paper's results are real, run this paper's code, reproduce table X from paper Y. Handles the full pipeline: read pa…
paper-reproduction/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.