New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

CHARLS Paper Reproduction Guide

by xjtulyc in 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.

No licenceAuto-check passedResearch & Science

SKILL.md written in Chinese; this summary is our English description.

Install CHARLS Paper Reproduction Guide

skills CLI
$ npx skills add xjtulyc/MedgeClaw --skill charls-reproduce -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xjtulyc/MedgeClaw charls-reproduce --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xjtulyc/MedgeClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/charls-reproduce .claude/skills/charls-reproduce && rm -rf skills-src

Use ~/.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/

Facts

Skill name
charls-reproduce
GitHub stars
617
Used in
1 other repo
Token cost
~1.8k tokens
SKILL.md length
562 words
Files
2 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
None found

At a glance

Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.

  • Works in 4 steps: 检查各变量缺失贡献: 哪个变量排除了最多人？ → 尝试不同的 MS 定义 → 检查婚姻编码: "已婚但不住在一起"算已婚还是未婚？ → …
  • Reproducing a published paper that uses CHARLS data
  • SKILL.md covers CHARLS 概览, Harmonized 数据集 vs 原始数据, 核心变量映射表 and 日期定向子变量, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill is a reference guide for working with CHARLS, the China Health and Retirement Longitudinal Study, and it is written mainly in Chinese. It explains how to tell a harmonized dataset (all survey waves stacked, variables cleaned and renamed) from the raw questionnaire modules, and why variable names, missing-value patterns and codings differ between the two.

A variable dictionary maps the names used in papers to raw and harmonized variables for cognition (immediate and delayed recall, serial 7s, orientation, drawing), CESD-10 depression scoring and a four-part social isolation index covering marital status, contact with children, rural residence and social activity. It also gives practical advice, for example checking missing serial 7 answers when a rebuilt mental status sample is much smaller than the paper reports.

When your agent uses it

  • Reproducing a published paper that uses CHARLS data
  • Mapping harmonized CHARLS variables to raw questionnaire items
  • Scoring cognitive function, CESD-10 depression or social isolation
  • Cleaning CHARLS data or selecting a study cohort

Example prompts

  • “Reproduce the main regression table of this CHARLS paper using the raw wave files in ./charls/.”
  • “Build a CESD-10 depression score from the harmonized CHARLS file and flag scores of 10 or more.”
  • “My mental status sample is far smaller than the paper's, so check whether serial 7 missingness is the cause.”

Requirements

  • CHARLS data files in Stata (.dta) format

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 检查各变量缺失贡献: 哪个变量排除了最多人？
  2. 尝试不同的 MS 定义
  3. 检查婚姻编码: "已婚但不住在一起"算已婚还是未婚？
  4. 检查 BMI 异常值: 原始 BMI 有 >100 的值，是否被论文保留？

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • charls.pku.edu.cn

    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

CHARLS Paper Reproduction Guide loads about 1.8k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 562 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

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 562 words (~1,835 tokens).

“大多数 CHARLS 论文使用原始问卷模块数据，变量名以 CHARLS 问卷编号命名（如 dc009s1）。但很多用户拿到的是 harmonized 数据集（合并所有波次，变量已清洗重命名）。”

— opening of SKILL.md by xjtulyc
name
charls-reproduce

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in skills/charls-reproduce of xjtulyc/MedgeClaw.

  • SKILL.md
  • references/variable_dictionary.md

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

CHARLS Paper Reproduction Guide 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.

CHARLS Paper Reproduction Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CHARLS Paper Reproduction Guide this skillxjtulyc/MedgeClaw6171 repos~1.8kAutomated safety check: PassNone
Bio Outlier Splicing DetectionGPTomics/bioSkills1.2k2 repos~5.1kAutomated safety check: PassMIT
PacsomaticK-Dense-AI/scientific-agent-skills48k1 repos~1.6kAutomated safety check: PassMIT
Bio Workflows Merip PipelineGPTomics/bioSkills1.2k1 repos~4.8kAutomated safety check: PassMIT
Inclusion Exclusion Criteria Builderaipoch/medical-research-skills1.9k—~4.2kAutomated safety check: PassMIT
Jhe Replication Packagebrycewang-stanford/Awesome-Journal-Skills1.2k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Bio Outlier Splicing Detection

    GPTomics/bioSkills

    Detects aberrant splicing in single rare-disease patients vs a control panel using FRASER 2.0 (Bioconductor; Beta-binomial autoencoder on Intron Jaccard Index, default delta cutoff 0.1, q…

    1.2k GitHub starsUsed in 2 repos~5.1k tokens
    Research & ScienceAuto-check passed

  • Pacsomatic

    K-Dense-AI/scientific-agent-skills

    Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs.

    48k GitHub starsUsed in 1 repo~1.6k tokens
    Research & ScienceAuto-check passed

  • Bio Workflows Merip Pipeline

    GPTomics/bioSkills

    Orchestrates an end-to-end MeRIP-seq / m6A-seq analysis from raw FASTQ to differential m6A peak calls and metagene plots, chaining fastp adapter trimming, STAR splice-aware alignment (NO…

    1.2k GitHub starsUsed in 1 repo~4.8k tokens
    Research & ScienceAuto-check passed

  • Inclusion Exclusion Criteria Builder

    aipoch/medical-research-skills

    Builds clear, executable, and auditable inclusion and exclusion criteria for biomedical and clinical research protocols.

    1.9k GitHub stars~4.2k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed

  • Jhe Replication Package

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when assembling the data, code, and access documentation for a Journal of Health Economics (JHE) manuscript — where much health data is restricted (claims, administrative…

    1.2k GitHub stars~1.9k tokensUpdated 14 days ago
    Research & ScienceAuto-check passed

  • Radiology

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when targeting Radiology (RSNA) or deciding whether a medical-imaging study fits this venue.

    1.2k GitHub stars~1.7k tokensUpdated 14 days ago
    Research & ScienceAuto-check passed

More from xjtulyc/MedgeClaw

  • 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.

    617 GitHub starsUsed in 1 repo~734 tokens
    Auto-check: notes

  • 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.

    617 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • 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.

    617 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Academic Paper Reproduction Methodology

    xjtulyc/MedgeClaw

    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.

    617 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • SVG UI Templates

    xjtulyc/MedgeClaw

    Generate professional SVG UI panels for structured information display.

    617 GitHub starsUsed in 1 repo~522 tokens
    Auto-check passed

Categories

Questions about CHARLS Paper Reproduction Guide

What does CHARLS Paper Reproduction Guide do?

Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores. This skill is a reference guide for working with CHARLS, the China Health and Retirement Longitudinal Study, and it is written mainly in Chinese. It explains how to tell a harmonized dataset (all survey waves stacked, variables cleaned and renamed) from the raw questionnaire modules, and why variable names, missing-value patterns and codings differ between the two.

When should I use CHARLS Paper Reproduction Guide?

CHARLS Paper Reproduction Guide fits situations like: reproducing a published paper that uses CHARLS data; mapping harmonized CHARLS variables to raw questionnaire items; scoring cognitive function, CESD-10 depression or social isolation; cleaning CHARLS data or selecting a study cohort.

How do I install CHARLS Paper Reproduction Guide in Claude Code?

Run `npx skills add xjtulyc/MedgeClaw --skill charls-reproduce -a claude-code`. Or copy the skill folder (skills/charls-reproduce in xjtulyc/MedgeClaw) into .claude/skills/charls-reproduce in your project. Claude Code loads it when a task matches its description.

How do I install CHARLS Paper Reproduction Guide in Codex?

Run `npx skills add xjtulyc/MedgeClaw --skill charls-reproduce -a codex`. Or copy the skill folder (skills/charls-reproduce in xjtulyc/MedgeClaw) into .agents/skills/charls-reproduce in your project. Codex loads it when a task matches its description.

Can I use CHARLS Paper Reproduction Guide 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 charls-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/charls-reproduce, .gemini/skills/charls-reproduce, .github/skills/charls-reproduce and .opencode/skills/charls-reproduce in your project.

What does CHARLS Paper Reproduction Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: CHARLS Paper Reproduction Guide is instructions for the agent only. Our summary lists: CHARLS data files in Stata (.dta) format.

Does CHARLS Paper Reproduction Guide access the network?

SKILL.md names 1 domain. As links in the text: charls.pku.edu.cn. This is read from the text; nothing was executed.

Is CHARLS Paper Reproduction Guide 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 CHARLS Paper Reproduction Guide use?

No licence was found for CHARLS Paper Reproduction Guide or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does CHARLS Paper Reproduction Guide use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to CHARLS Paper Reproduction Guide?

Skills that share tags, products or a category with CHARLS Paper Reproduction Guide: Bio Outlier Splicing Detection (GPTomics/bioSkills, 1.2k stars), Pacsomatic (K-Dense-AI/scientific-agent-skills, 48k stars), Bio Workflows Merip Pipeline (GPTomics/bioSkills, 1.2k stars) and Inclusion Exclusion Criteria Builder (aipoch/medical-research-skills, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CHARLS Paper Reproduction Guide?

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.