reproducible-research
可重复性研究助手,帮助科研人员构建可重复的计算工作流。支持Jupyter notebooks最佳实践、Docker/Singularity容器化、工作流管理(Snakemake/Nextflow)、代码和数据版本控制、环境管理(conda/venv)。当用户需要:(1) 确保研究的可重复性、(2)…
Skill by Hollis36
Chalk Labs
Need help deploying reproducible-research?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hollis36-reproducible-research
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, research, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/reproducible-research
What's inside
- Skill name
reproducible-research- Description
- 可重复性研究助手,帮助科研人员构建可重复的计算工作流。支持Jupyter notebooks最佳实践、Docker/Singularity容器化、工作流管理(Snakemake/Nextflow)、代码和数据版本控制、环境管理(conda/venv)。当用户需要:(1) 确保研究的可重复性、(2) 创建可复现的分析流程、(3) 容器化计算环境、(4) 版本控制代码和数据时触发。关键词:可重复性、reproducibility、Jupyter、Docker、容器化、workflow、Snakemake。
- License
- Apache-2.0
- Instructions
- 898 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- body: 898 lines (spec recommends under 500)
- body: contains an absolute path from the author's machine
Files (2)
- LICENSE.txt
- SKILL.md
SKILL.md (first lines)
# 可重复性研究助手
帮助科研人员构建可重复、可复现的计算研究工作流,确保研究结果的可验证性和可信度。
## 核心原则
### 可重复性研究的三个支柱
1. **代码版本控制**:使用Git追踪所有分析代码的变更
2. **环境管理**:明确记录计算环境(软件版本、依赖项)
3. **工作流自动化**:自动化数据处理和分析流程
## 1. Jupyter Notebooks 最佳实践
### 基本原则
```python
# Jupyter Notebook 最佳实践模板
# Cell 1: 文档说明
"""
# 数据分析: [项目名称]
**作者**: [姓名]
**日期**: 2026-04-06
**目的**: [简要描述分析目的]
## 环境要求
- Python 3.11
- pandas 2.0.0
- numpy 1.24.0
- matplotlib 3.7.0
"""
# Cell 2: 导入库(按类别组织)
# 标准库
import os
import sys
from pathlib import Path
# 第三方库 - 数据处理
import numpy as np
import pandas as pd
# 第三方库 - 可视化
import matplotlib.pyplot as plt
import seaborn as sns
# 第三方库 - 统计分析
from scipy import stats
# 设置
%matplotlib inline
%load_ext autoreload
%autoreload 2
# 可视化配置
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")
# 显示设置
pd.set_option('display.max_columns', 50)
pd.set_option('display.max_rows', 100)
# Cell 3: 设置随机种子(确保可重复性)
RANDOM_SEED = 42
np.random.seed(RANDOM_SEED)
# Cell 4: 定义路径
PROJECT_ROOT = Path.cwd().parent
DATA_DIR = PROJECT_ROOT / "data"
RAW_DATA_DIR = DATA_DIR / "raw"
PROCESSED_DATA_DIR = DATA_DIR / "processed"
RESULTS_DIR = PROJECT_ROOT / "results"
FIGURES_DIR = RESULTS_DIR / "figures"
# 创建目录
RESULTS_DIR.mkdir(parents=True, exist_ok=True)
FIGURES_DIR.mkdir(parents=True, exist_ok=True)
# Cell 5: 定义函数(将复杂逻辑封装为函数)
def load_data(file_path):
"""加载数据文件
Args:
file_path: 数据文件路径
Returns:
DataFrame: 加载的数据
"""
df = pd.read_csv(file_path)
print(f"加载数据: {df.shape[0]} 行, {df.shape[1]} 列")
return df
def preprocess_data(df):
"""数据预处理
Args:
df: 原始数据
Returns:
DataFrame: 处理后的数据
"""
# 处理缺失值
df = df.dropna()
# 数据转换
# ...
return df
# Cell 6+: 分析步骤(每个cell一个逻辑步骤)
# 每个分析步骤包含:
# 1. Markdown说明
# 2. 代码实现
# 3. 结果展示
```
### Jupyter配置文件(推荐设置)From Hollis36/claude-skill, Apache-2.0.
More from Hollis36/claude-skill
- 0.462score
grill-me
Hollis36
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 1Claude Code +9 - 0.425score
review-paper-writing
Hollis36
Comprehensive guide to writing literature review / survey papers using Claude Code skills, MCP bio-research tools, scientific writing plugins, and 2025-2026…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
graphical-abstract
Hollis36
学术论文摘要结构图(Graphical Abstract/TOC图)创建助手。支持多种工具:Python (matplotlib/PIL/drawsvg)、HTML/CSS/SVG、TikZ/LaTeX、Figma MCP、Banana Pro…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
scientific-plotting
Hollis36
科研绘图助手,用于创建高质量的学术论文图表。支持统计图表(柱状图、折线图、散点图、箱线图、小提琴图)、科学示意图(流程图、机制图)、数据可视化(热力图、网络图)、高级图表(雷达图、Sankey图、分面图)。集成SciencePlots…
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
experiment-tracking
Hollis36
实验追踪与管理助手,帮助科研人员记录、组织和管理实验数据。支持电子实验记录本(ELN)最佳实践、实验版本控制、数据溯源、FAIR数据原则。当用户需要:(1) 记录实验流程和参数、(2) 管理实验数据和结果、(3) 追踪实验版本和变更、(4) 确保实验可重复性时触发。关键词:实验记录、lab…
SkillDFreshness: D★ 1Claude Code +9 - 0.416score
code-review
Hollis36
科研代码审查助手,专注于确保科研代码的正确性、可重复性和可维护性。支持代码质量检查、安全漏洞扫描、可重复性验证、数据完整性检查、最佳实践验证。当用户需要:(1) 审查科研代码质量、(2) 确保实验代码可重复、(3) 检查数据分析脚本、(4) 验证统计分析代码、(5) 准备代码发布或提交论文时触发。关键词:code…
SkillDFreshness: D★ 1Claude Code +9 - 0.407score
mcp-builder
Hollis36
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
canvas-design
Hollis36
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
doc-coauthoring
Hollis36
Guide users through a structured workflow for co-authoring documentation.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
frontend-design
Hollis36
Create distinctive, production-grade frontend interfaces with high design quality.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
brand-guidelines
Hollis36
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
algorithmic-art
Hollis36
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 6, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Hollis36/claude-skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Hollis36
- 0.462score
grill-me
Hollis36
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 1Claude Code +9 - 0.425score
review-paper-writing
Hollis36
Comprehensive guide to writing literature review / survey papers using Claude Code skills, MCP bio-research tools, scientific writing plugins, and 2025-2026…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
graphical-abstract
Hollis36
学术论文摘要结构图(Graphical Abstract/TOC图)创建助手。支持多种工具:Python (matplotlib/PIL/drawsvg)、HTML/CSS/SVG、TikZ/LaTeX、Figma MCP、Banana Pro…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
scientific-plotting
Hollis36
科研绘图助手,用于创建高质量的学术论文图表。支持统计图表(柱状图、折线图、散点图、箱线图、小提琴图)、科学示意图(流程图、机制图)、数据可视化(热力图、网络图)、高级图表(雷达图、Sankey图、分面图)。集成SciencePlots…
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
experiment-tracking
Hollis36
实验追踪与管理助手,帮助科研人员记录、组织和管理实验数据。支持电子实验记录本(ELN)最佳实践、实验版本控制、数据溯源、FAIR数据原则。当用户需要:(1) 记录实验流程和参数、(2) 管理实验数据和结果、(3) 追踪实验版本和变更、(4) 确保实验可重复性时触发。关键词:实验记录、lab…
SkillDFreshness: D★ 1Claude Code +9 - 0.416score
code-review
Hollis36
科研代码审查助手,专注于确保科研代码的正确性、可重复性和可维护性。支持代码质量检查、安全漏洞扫描、可重复性验证、数据完整性检查、最佳实践验证。当用户需要:(1) 审查科研代码质量、(2) 确保实验代码可重复、(3) 检查数据分析脚本、(4) 验证统计分析代码、(5) 准备代码发布或提交论文时触发。关键词:code…
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get reproducible-research running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
reproducible-research skill. Agent Mart. https://agentmart.dev/skills/hollis36-reproducible-research (last updated 2026-10-24)