Plugin
oh-my-claudecode
For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI. Liked OmC but found it a bit overkill? Try gajae-code.
48 skills11 hooks1 MCP+4+3+3+3+2+2+2+2+240k
@yeachan-heoData Science
Plugin
gyoshu
gyoshu is a Claude Code plugin with 3 hand-picked skills, indexed on Flowy in the Data Science category.
Plugin Signal47/100Fair
maintained11
capable53
documented100
adopted51
Install on Claude Code
> /plugin marketplace add Yeachan-Heo/My-Jogyo> /plugin install gyoshu@gyoshu
Stats
242
Stars
62
Forks
Quiet
Maintenance
TypeScript
Language
8mo ago
Last commit
10mo ago
Created
9d ago
Added
What's inside
Skill(3 skills)
Agent(6 agents)
Command(2 commands)
MCP(1 mcp)
README
🎓 Gyoshu & Jogyo
"Every great professor needs a great teaching assistant."
Gyoshu (교수, Professor) orchestrates. Jogyo (조교, Teaching Assistant) executes.
Together, they form an end-to-end research automation system for OpenCode that turns your research goals into reproducible Jupyter notebooks—complete with hypotheses, experiments, findings, and publication-ready reports.
🎭 The Cast
| Agent | Role | Korean | What They Do |
|---|---|---|---|
| Gyoshu | 🎩 Professor | 교수 | Plans research, orchestrates workflow, manages sessions |
| Jogyo | 📚 Teaching Assistant | 조교 | Executes Python code, runs experiments, generates outputs |
| Baksa | 🔍 PhD Reviewer | 박사 | Adversarial verifier — challenges claims, calculates trust scores |
| Jogyo Paper Writer | ✍️ Grad Student | 조교 | Transforms raw findings into narrative research reports |
Think of it like a research lab:
- The Professor (Gyoshu) sets the research direction and reviews progress
- The TA (Jogyo) does the actual experiments and analysis
- The PhD Reviewer (Baksa) plays devil's advocate, questioning every claim
- When it's time to publish, a Grad Student writes up the findings beautifully
✨ Features
- 🔬 Hypothesis-Driven Research — Structure your work with
[OBJECTIVE],[HYPOTHESIS],[FINDING]markers - 🐍 Persistent Python REPL — Variables survive across sessions, just like a real Jupyter kernel
- 📓 Auto-Generated Notebooks — Every experiment is captured as a reproducible
.ipynb - 🤖 Autonomous Mode — Set a goal, walk away, come back to results
- 🔍 Adversarial Verification — PhD reviewer challenges every claim before acceptance
- 🎯 Two-Gate Completion — SUCCESS requires both evidence quality (Trust Gate) AND goal achievement (Goal Gate)
- 📝 AI-Powered Reports — Turn messy outputs into polished research narratives
- 🔄 Session Management — Continue, replay, or branch your research anytime
🚀 Installation
Option 1: Claude Code (MCP Server)
Gyoshu works with Claude Code via the Model Context Protocol (MCP). Install in one command:
# Clone and build the MCP server
git clone https://github.com/Yeachan-Heo/My-Jogyo.git
cd My-Jogyo/src/mcp
npm install && npm run build
# Register with Claude Code
claude mcp add gyoshu-mcp "$(pwd)/build/index.cjs"
Verify installation:
claude mcp list
# Should show: gyoshu-mcp: ✓ Connected
Available MCP Tools:
| Tool | Purpose |
|---|---|
python_repl | Execute Python code with marker detection |
research_manager | Create/manage research sessions |
gyoshu_snapshot | Capture research state snapshots |
checkpoint_manager | Save/restore research checkpoints |
notebook_writer | Jupyter notebook operations |
notebook_search | Search across notebooks |
Note: The MCP server exposes 12 research tools. See src/mcp/ for details.
Option 2: OpenCode Plugin
Add Gyoshu to your opencode.json:
{
"plugin": ["gyoshu"]
}
That's it! OpenCode will auto-install Gyoshu from npm on next startup.
Option 3: CLI Installer
# Using bunx (no global install needed)
bunx gyoshu install
# Or install globally first
npm install -g gyoshu
gyoshu install
The CLI automatically adds Gyoshu to your opencode.json.
Clone & link locally:
git clone https://github.com/Yeachan-Heo/My-Jogyo.git
cd My-Jogyo && bun install
Then in your opencode.json:
{
"plugin": ["file:///path/to/My-Jogyo"]
}
Verify installation:
# Check status via CLI
bunx gyoshu check
# Or in OpenCode
opencode
/gyoshu doctor
🤖 Installation for LLMs
Using Claude Code, OpenCode, or another AI coding assistant? This section is for you.
For Claude Code: Install the MCP server (Option 1 above). The tools are automatically available.
For OpenCode: Run bunx gyoshu install or add "gyoshu" to your plugin array. Then give your LLM the context it needs:
-
Point your LLM to the guide:
"Read
AGENTS.mdin the Gyoshu directory for full context on how to use the research tools." -
Or paste this quick start prompt:
I've installed Gyoshu. Read AGENTS.md and help me run /gyoshu to analyze my data.
Key commands your LLM should know:
| Command | What It Does |
|---|---|
/gyoshu | Start interactive research |
/gyoshu-auto <goal> | Autonomous research (hands-off) |
/gyoshu doctor | Check system health and diagnose issues |
Tip: AGENTS.md contains everything an LLM needs — agents, commands, markers, troubleshooting, and more.
🏃 Quick Start
# Start OpenCode
opencode
# 👋 Say hi to the Professor
/gyoshu
# 🎯 Start a new research project
/gyoshu analyze customer churn patterns in the telecom dataset
# 🤖 Or let it run autonomously (hands-off!)
/gyoshu-auto classify iris species using random forest
# 📊 Generate a report
/gyoshu report
# 🔄 Continue where you left off
/gyoshu continue
📚 Examples
Binance Futures Comprehensive EDA
Real-world example: Comprehensive exploratory data analysis of Binance USD-M futures data with multi-dimensional visualizations.
What it shows:
- 3D volume-price-time analysis
- Correlation heatmaps with dendrograms
- Rolling statistics and volatility surfaces
- Cross-pair scatter density plots
- Performance radar charts and candlestick analysis
Try It Yourself
# Binance futures analysis (API or local data)
/gyoshu-auto perform comprehensive EDA on binance futures data
# Titanic classification (classic ML workflow)
/gyoshu-auto analyze Titanic survival data and build classification model
# Iris clustering (no download needed - sklearn built-in)
/gyoshu-auto cluster iris dataset and visualize results
📖 Commands
The Professor's Commands (/gyoshu)
| Command | What It Does |
|---|---|
/gyoshu | Show status and what to do next |
/gyoshu <goal> | Start interactive research |
/gyoshu-auto <goal> | Autonomous mode (set it and forget it!) |
/gyoshu plan <goal> | Just create a plan, don't execute |
/gyoshu continue | Pick up where you left off |
/gyoshu report | Generate research report |
/gyoshu list | See all your research projects |
/gyoshu search <query> | Find stuff across all notebooks |
/gyoshu doctor | Check system health and diagnose issues |
Research Modes
| Mode | Best For | Command |
|---|---|---|
| 🎓 Interactive | Learning, exploring, iterating | /gyoshu <goal> |
| 🤖 Autonomous | Clear goals, hands-off execution | /gyoshu-auto <goal> |
| 🔧 REPL | Quick exploration, debugging | /gyoshu repl <query> |
🔬 How Research Works
1. You Set a Goal
/gyoshu analyze wine quality factors and build a predictive model
2. The Professor Plans
Gyoshu creates a structured research plan with clear objectives and hypotheses.
3. The TA Executes
Jogyo runs Python code, using structured markers to organize output:
print("[OBJECTIVE] Predict wine quality from physicochemical properties")
print("[HYPOTHESIS] Alcohol content is the strongest predictor")
# ... analysis code ...
print(f"[METRIC:accuracy] {accuracy:.3f}")
print("[FINDING] Alcohol shows r=0.47 correlation with quality")
print("[CONCLUSION] Hypothesis supported - alcohol is key predictor")
4. Auto-Generated Notebook
Everything is captured in notebooks/wine-quality.ipynb with full reproducibility.
5. AI-Written Report
The Paper Writer agent transforms markers into a narrative report:
"Our analysis of 1,599 wine samples revealed that alcohol content emerges as the dominant predictor of quality ratings (r = 0.47). The final Random Forest model achieved 87% accuracy..."
📁 Project Structure
your-project/
├── notebooks/ # 📓 Research notebooks
│ ├── wine-quality.ipynb
│ └── customer-churn.ipynb
├── reports/ # 📝 Generated reports
│ └── wine-quality/
│ ├── report.md # AI-written narrative report
│ ├── figures/ # Saved plots
│ └── models/ # Saved models
├── data/ # 📊 Your datasets
└── .venv/ # 🐍 Python environment
Runtime files (sockets, locks) go to OS temp directories—not your project! 🧹
What Gyoshu Creates
When you run research, Gyoshu creates these artifacts in your project:
your-project/
├── notebooks/
│ └── your-research.ipynb ← Research notebook (source of truth)
├── reports/
│ └── your-research/
│ ├── figures/ ← Saved plots (.png, .svg)
│ ├── models/ ← Trained models (.pkl, .joblib)
│ └── report.md ← Generated research report
└── (your existing files untouched!)
Note: Gyoshu never modifies your
.venv/,data/, or other existing project files.
🎯 Output Markers
The TA uses structured markers to organize research output:
Core Markers
| Marker | Purpose | Example |
|---|---|---|
[OBJECTIVE] | Research goal | [OBJECTIVE] Classify iris species |
[HYPOTHESIS] | What you're testing | [HYPOTHESIS] H0: no difference; H1: petal length predicts species |
[DATA] | Dataset info | [DATA] Loaded 150 samples |
[FINDING] | Key discovery | [FINDING] Setosa is linearly separable (d=2.1, p<0.001) |
[CONCLUSION] | Final verdict | [CONCLUSION] Hypothesis confirmed with large effect |
Statistical Evidence Markers (Required for Verified Findings)
| Marker | Purpose | Example |
|---|---|---|
[STAT:ci] | Confidence interval | [STAT:ci] 95% CI [0.82, 0.94] |
[STAT:effect_size] | Effect magnitude | [STAT:effect_size] Cohen's d = 0.75 (medium) |
[STAT:p_value] | Statistical significance | [STAT:p_value] p = 0.003 |
[SO_WHAT] | Practical significance | [SO_WHAT] This means 15% cost reduction |
[LIMITATION] | Threats to validity | [LIMITATION] Small sample size (n=50) |
ML Pipeline Markers
| Marker | Purpose | Example |
|---|---|---|
[METRIC:baseline_*] | Dummy model benchmark | [METRIC:baseline_accuracy] 0.33 |
[METRIC:cv_*] | Cross-validation scores | [METRIC:cv_accuracy_mean] 0.95 |
Quality Gate: Findings without
[STAT:ci]and[STAT:effect_size]are marked as "Exploratory" in reports.
🔬 Research Quality
Gyoshu enforces senior data scientist level quality through automated quality gates. Every claim requires statistical evidence.
The Finding Gating Rule
⚠️ No
[FINDING]is accepted without:
[STAT:ci]— Confidence interval (within 10 lines before)[STAT:effect_size]— Effect magnitude (within 10 lines before)
Findings that fail these checks are downgraded to "Exploratory Observations" in reports.
Quality Standards
| Requirement | Penalty if Missing | Why It Matters |
|---|---|---|
| CI for findings | -30 trust | Point estimates without uncertainty are misleading |
| Effect size for findings | -30 trust | Statistical significance ≠ practical significance |
| Baseline for ML | -20 trust | Can't claim improvement without a reference point |
File tree
More plugins by @yeachan-heo.
View @yeachan-heo’s profile@yeachan-heoFAQ
gyoshu is a Claude Code plugin with 3 hand-picked skills, indexed on Flowy in the Data Science category. Install it with the command on its page. It includes data-analysis, experiment-design, ml-rigor. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is gyoshu?
- gyoshu is a Claude Code plugin with 3 hand-picked skills, indexed on Flowy in the Data Science category. By yeachan-heo. 242 GitHub stars, updated Feb 2026.
- How do I install gyoshu?
- Run these in Claude Code: /plugin marketplace add Yeachan-Heo/My-Jogyo then /plugin install gyoshu@gyoshu. Then prompt normally.
- Does gyoshu auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is gyoshu free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it