Light Experiment Coding
Light0305/Light-skills
Builds the code for a frozen research experiment test-first, with leakage controls, seed handling and saved evidence so results can be rerun and audited.
Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report.
SKILL.md written in Chinese; this summary is our English description.
Install Academic Paper Reproduction Methodology
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xjtulyc/MedgeClaw paper-reproduce --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paper-reproduce .claude/skills/paper-reproduce && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .claude/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xjtulyc/MedgeClaw paper-reproduce --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paper-reproduce .agents/skills/paper-reproduce && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .agents/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xjtulyc/MedgeClaw paper-reproduce --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paper-reproduce .cursor/skills/paper-reproduce && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .cursor/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xjtulyc/MedgeClaw.git --path skills/paper-reproduce--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xjtulyc/MedgeClaw paper-reproduce --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paper-reproduce .gemini/skills/paper-reproduce && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .gemini/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xjtulyc/MedgeClaw paper-reproduceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paper-reproduce .github/skills/paper-reproduce && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .github/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xjtulyc/MedgeClaw paper-reproduce --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paper-reproduce .opencode/skills/paper-reproduce && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "paper-reproduce" agent skill from https://github.com/xjtulyc/MedgeClaw/tree/main/skills/paper-reproduce into .opencode/skills/paper-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-reproduce", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
paper-reproduce- GitHub stars
- 617
- Used in
- 1 other repo
- Token cost
- ~1.3k tokens
- SKILL.md length
- 220 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- None found
At a glance
Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report.
- Works in 6 steps: 任务理解 + 数据探索 → 变量构建 + 验证 → 样本筛选 → …
- Reproducing the tables and statistics from a published observational study
- SKILL.md covers 核心原则, 复现流程（6 阶段）, 输出目录结构 and 常见陷阱, plus 1 more section
- Calls docker
What it does
The method rests on four principles: explore the data before modeling anything, since variable names and codings should never be assumed; check the sample size against the paper at every filtering step; expect and record differences between a harmonized dataset and the original rather than pretending they do not exist; and report intermediate results as each phase finishes instead of waiting for the whole pipeline to run.
Phase one reads the paper or task document to extract sample filtering steps, variable definitions and expected table values, then explores the data's actual shape and columns. Finding the right variable uses four checks in order: an exact name match, a semantic keyword search, a check that the value range matches what the paper describes, and cross-validation against a known relationship such as a total equaling the sum of its parts, because harmonized datasets often rename variables completely.
Later phases build and validate each variable immediately after constructing it, filter the sample step by step while comparing the remaining count to the paper's reported number at each step, then run descriptive statistics and regression analysis, standardizing variables before building interaction terms and re-standardizing within each subgroup for stratified analysis. A deviation of more than 10 percent at any filtering step is a signal to stop and investigate rather than continue.
When your agent uses it
- Reproducing the tables and statistics from a published observational study
- Mapping harmonized dataset variables back to the names used in a paper
- Explaining a sample-size or statistic mismatch against a paper's reported numbers
Example prompts
- “Reproduce Table 2 from this paper using the harmonized dataset in data.dta.”
- “Map the cognition variables in our data to the ones named in this paper.”
- “Our sample size is off by 15% at the exclusion step, help me find why.”
Requirements
- The published paper plus its underlying data file
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- 任务理解 + 数据探索
- 变量构建 + 验证
- 样本筛选
- 统计分析
- 结果对比 + 偏差分析
- 输出文档
What it can do on your machine
Read from SKILL.md and the folder at commit fef51d3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
docker
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Academic Paper Reproduction Methodology loads about 1.3k tokens when it runs. Until then it costs about 148 tokens; SKILL.md has 220 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 220 words (~1,319 tokens).
- name
- paper-reproduce
Files
Just SKILL.md in skills/paper-reproduce of xjtulyc/MedgeClaw.
Open the folder on GitHubat commit fef51d3
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in xjtulyc/MedgeClaw, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Academic Paper Reproduction Methodology next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Academic Paper Reproduction Methodology this skillxjtulyc/MedgeClaw | 617 | 1 repos | ~1.3k | Automated safety check: Pass | None | |
| Light Experiment CodingLight0305/Light-skills | 640 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Fcr Revision And Rebuttalfranklee16/academic-research-skills | 223 | 1 repos | ~1.1k | Automated safety check: Pass | None | |
| Aistats Writing Stylebrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~865 | Automated safety check: Pass | MIT | |
| Icml Experimentsbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~843 | Automated safety check: Pass | MIT | |
| Peer ReviewK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.1k | Automated safety check: Notes | MIT |
Similar skills
Fcr Revision And Rebuttal
franklee16/academic-research-skills
A skill your agent uses when writing the response to a Field Crops Research (FCR) revision decision (major or minor) and revising the manuscript.
Aistats Writing Style
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when revising an AISTATS paper for concise AI-statistics framing, theorem-and-experiment clarity, 8-page two-column compression, double-blind wording, reproducibility…
Icml Experiments
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when stress-testing ICML experimental evidence before submission or rebuttal, including strong tuned baselines, mechanism-isolating ablations, seed variance and confidence…
Peer Review
K-Dense-AI/claude-scientific-writer
Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
Experiment Agent
Imbad0202/experiment-agent
Experiment executor and monitor for academic research. An agent skill from Imbad0202/experiment-agent.
More from xjtulyc/MedgeClaw
CHARLS Paper Reproduction Guide
xjtulyc/MedgeClaw
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
Feishu Rich Card Sender
xjtulyc/MedgeClaw
Sends interactive Feishu group-chat cards that mix markdown text with uploaded chart or diagram images, for progress updates and analysis results.
Biomedical Analysis Dispatch
xjtulyc/MedgeClaw
Routes bioinformatics, drug discovery, clinical and multi-omics tasks from a chat interface to Claude Code sessions running K-Dense scientific skills, with a live dashboard per task.
CJK Font Setup for Plots
xjtulyc/MedgeClaw
Detects a usable Chinese, Japanese or Korean font and configures matplotlib so chart labels, titles and legends render instead of showing empty boxes.
SVG UI Templates
xjtulyc/MedgeClaw
Generate professional SVG UI panels for structured information display.
Related
Works with
Categories
Questions about Academic Paper Reproduction Methodology
What does Academic Paper Reproduction Methodology do?
Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report. The method rests on four principles: explore the data before modeling anything, since variable names and codings should never be assumed; check the sample size against the paper at every filtering step; expect and record differences between a harmonized dataset and the original rather than pretending they do not exist; and report intermediate results as each phase finishes instead of waiting for the whole pipeline to run.
When should I use Academic Paper Reproduction Methodology?
Academic Paper Reproduction Methodology fits situations like: reproducing the tables and statistics from a published observational study; mapping harmonized dataset variables back to the names used in a paper; explaining a sample-size or statistic mismatch against a paper's reported numbers.
How do I install Academic Paper Reproduction Methodology in Claude Code?
Run `npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a claude-code`. Or copy the skill folder (skills/paper-reproduce in xjtulyc/MedgeClaw) into .claude/skills/paper-reproduce in your project. Claude Code loads it when a task matches its description.
How do I install Academic Paper Reproduction Methodology in Codex?
Run `npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a codex`. Or copy the skill folder (skills/paper-reproduce in xjtulyc/MedgeClaw) into .agents/skills/paper-reproduce in your project. Codex loads it when a task matches its description.
Can I use Academic Paper Reproduction Methodology in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xjtulyc/MedgeClaw --skill paper-reproduce -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-reproduce, .gemini/skills/paper-reproduce, .github/skills/paper-reproduce and .opencode/skills/paper-reproduce in your project.
What does Academic Paper Reproduction Methodology need to run?
Going by SKILL.md and its folder, Academic Paper Reproduction Methodology needs the command-line tools its instructions call (docker). Our summary lists: The published paper plus its underlying data file.
Does Academic Paper Reproduction Methodology access the network?
SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Academic Paper Reproduction Methodology safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Academic Paper Reproduction Methodology use?
No licence was found for Academic Paper Reproduction Methodology or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Academic Paper Reproduction Methodology use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Academic Paper Reproduction Methodology?
Skills that share tags, products or a category with Academic Paper Reproduction Methodology: Light Experiment Coding (Light0305/Light-skills, 640 stars), Fcr Revision And Rebuttal (franklee16/academic-research-skills, 223 stars), Aistats Writing Style (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars) and Icml Experiments (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Academic Paper Reproduction Methodology?
xjtulyc (a GitHub user) maintains it in xjtulyc/MedgeClaw, which has 617 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 12, 2026.
Source: xjtulyc/MedgeClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.