jupyter-live-kernel

Name: jupyter-live-kernel
Author: AlexAI-MCP

132stars24forks

How to install jupyter-live-kernel?

alexai-mcp/hermes-ccc/jupyter-live-kernel

$npx -y skills add AlexAI-MCP/hermes-CCC --skill jupyter-live-kernel

Installs into the current project.

Summary

Jupyter notebook and kernel operations — start kernels, execute cells programmatically, export, and data analysis patterns.

Files · 1

View on GitHub

SKILL.md

1	# Jupyter Live Kernel
2
3	Run notebooks, execute cells programmatically, and manage Jupyter kernels.
4
5	## Setup
6
7	```bash
8	pip install jupyter jupyterlab nbformat nbconvert ipykernel
9	python -m ipykernel install --user --name myenv --display-name "My Env"
10	```
11
12	---
13
14	## Start Jupyter
15
16	```bash
17	# JupyterLab (recommended)
18	jupyter lab --no-browser --port 8888
19
20	# Classic notebook
21	jupyter notebook --no-browser --port 8888
22
23	# Allow remote access (careful with security)
24	jupyter lab --ip 0.0.0.0 --no-browser
25
26	# Start with specific directory
27	jupyter lab /path/to/project
28	```
29
30	---
31
32	## Execute Notebooks Programmatically
33
34	```bash
35	# Execute and save output
36	jupyter nbconvert --to notebook --execute input.ipynb --output output.ipynb
37
38	# With timeout
39	jupyter nbconvert --to notebook --execute --ExecutePreprocessor.timeout=300 input.ipynb
40
41	# Export to HTML
42	jupyter nbconvert --to html notebook.ipynb
43
44	# Export to Python script
45	jupyter nbconvert --to script notebook.ipynb
46
47	# Export to PDF (requires LaTeX)
48	jupyter nbconvert --to pdf notebook.ipynb
49	```
50
51	---
52
53	## Create Notebooks with nbformat
54
55	```python
56	import nbformat
57
58	nb = nbformat.v4.new_notebook()
59
60	# Add markdown cell
61	nb.cells.append(nbformat.v4.new_markdown_cell("# My Analysis"))
62
63	# Add code cell
64	nb.cells.append(nbformat.v4.new_code_cell("""
65	import pandas as pd
66	import matplotlib.pyplot as plt
67
68	df = pd.read_csv('data.csv')
69	df.head()
70	"""))
71
72	# Save
73	with open("analysis.ipynb", "w") as f:
74	nbformat.write(nb, f)
75	```
76
77	---
78
79	## Execute Cells Programmatically with nbclient
80
81	```python
82	import nbformat
83	from nbclient import NotebookClient
84
85	with open("analysis.ipynb") as f:
86	nb = nbformat.read(f, as_version=4)
87
88	client = NotebookClient(nb, timeout=600, kernel_name="python3")
89	client.execute()
90
91	with open("analysis_output.ipynb", "w") as f:
92	nbformat.write(nb, f)
93	```
94
95	---
96
97	## Papermill — Parameterized Notebooks
98
99	```bash
100	pip install papermill
101
102	# Run with parameters
103	papermill input.ipynb output.ipynb -p learning_rate 0.001 -p epochs 10
104
105	# Pass dict parameter
106	papermill input.ipynb output.ipynb -y "{'config': {'lr': 0.001}}"
107	```
108
109	Mark parameter cell with tag `parameters` in the notebook.
110
111	---
112
113	## Kernel Management
114
115	```bash
116	# List running kernels
117	jupyter kernel list
118
119	# List available kernel specs
120	jupyter kernelspec list
121
122	# Install a kernel from venv
123	source myenv/bin/activate
124	pip install ipykernel
125	python -m ipykernel install --user --name myenv
126
127	# Remove kernel
128	jupyter kernelspec remove myenv
129	```
130
131	---
132
133	## Magic Commands (in notebooks)
134
135	```python
136	# Time a single line
137	%timeit [i**2 for i in range(1000)]
138
139	# Time a cell
140	%%timeit
141	result = [i**2 for i in range(1000)]
142
143	# Run shell command
144	!pip install pandas
145	!ls -la
146
147	# Show matplotlib inline
148	%matplotlib inline
149
150	# Load external script
151	%load script.py
152
153	# Auto-reload modules
154	%load_ext autoreload
155	%autoreload 2
156
157	# Run bash cell
158	%%bash
159	echo "Hello from bash"
160	ls
161	```
162
163	---
164
165	## Common Data Analysis Pattern
166
167	```python
168	import pandas as pd
169	import matplotlib.pyplot as plt
170	import numpy as np
171
172	# Load data
173	df = pd.read_csv("data.csv")
174
175	# Quick overview
176	print(df.shape)
177	df.info()
178	df.describe()
179	df.isnull().sum()
180
181	# Plot
182	fig, axes = plt.subplots(1, 2, figsize=(12, 4))
183	df["column"].hist(ax=axes[0])
184	df.plot.scatter(x="col1", y="col2", ax=axes[1])
185	plt.tight_layout()
186	plt.savefig("plot.png", dpi=150)
187	plt.show()
188	```
189
190	---
191
192	## VS Code Integration
193
194	- Install "Jupyter" extension
195	- Open `.ipynb` files directly
196	- Select kernel from top-right dropdown
197	- Run cells with `Shift+Enter`
198	- Variables panel: View → Variables

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

jupyter-live-kernel

132stars24forks

View on GitHub

How to install jupyter-live-kernel?

alexai-mcp/hermes-ccc/jupyter-live-kernel

$npx -y skills add AlexAI-MCP/hermes-CCC --skill jupyter-live-kernel

Installs into the current project.

Summary

Jupyter notebook and kernel operations — start kernels, execute cells programmatically, export, and data analysis patterns.

Files · 1

View on GitHub

SKILL.md

1	# Jupyter Live Kernel
2
3	Run notebooks, execute cells programmatically, and manage Jupyter kernels.
4
5	## Setup
6
7	```bash
8	pip install jupyter jupyterlab nbformat nbconvert ipykernel
9	python -m ipykernel install --user --name myenv --display-name "My Env"
10	```
11
12	---
13
14	## Start Jupyter
15
16	```bash
17	# JupyterLab (recommended)
18	jupyter lab --no-browser --port 8888
19
20	# Classic notebook
21	jupyter notebook --no-browser --port 8888
22
23	# Allow remote access (careful with security)
24	jupyter lab --ip 0.0.0.0 --no-browser
25
26	# Start with specific directory
27	jupyter lab /path/to/project
28	```
29
30	---
31
32	## Execute Notebooks Programmatically
33
34	```bash
35	# Execute and save output
36	jupyter nbconvert --to notebook --execute input.ipynb --output output.ipynb
37
38	# With timeout
39	jupyter nbconvert --to notebook --execute --ExecutePreprocessor.timeout=300 input.ipynb
40
41	# Export to HTML
42	jupyter nbconvert --to html notebook.ipynb
43
44	# Export to Python script
45	jupyter nbconvert --to script notebook.ipynb
46
47	# Export to PDF (requires LaTeX)
48	jupyter nbconvert --to pdf notebook.ipynb
49	```
50
51	---
52
53	## Create Notebooks with nbformat
54
55	```python
56	import nbformat
57
58	nb = nbformat.v4.new_notebook()
59
60	# Add markdown cell
61	nb.cells.append(nbformat.v4.new_markdown_cell("# My Analysis"))
62
63	# Add code cell
64	nb.cells.append(nbformat.v4.new_code_cell("""
65	import pandas as pd
66	import matplotlib.pyplot as plt
67
68	df = pd.read_csv('data.csv')
69	df.head()
70	"""))
71
72	# Save
73	with open("analysis.ipynb", "w") as f:
74	nbformat.write(nb, f)
75	```
76
77	---
78
79	## Execute Cells Programmatically with nbclient
80
81	```python
82	import nbformat
83	from nbclient import NotebookClient
84
85	with open("analysis.ipynb") as f:
86	nb = nbformat.read(f, as_version=4)
87
88	client = NotebookClient(nb, timeout=600, kernel_name="python3")
89	client.execute()
90
91	with open("analysis_output.ipynb", "w") as f:
92	nbformat.write(nb, f)
93	```
94
95	---
96
97	## Papermill — Parameterized Notebooks
98
99	```bash
100	pip install papermill
101
102	# Run with parameters
103	papermill input.ipynb output.ipynb -p learning_rate 0.001 -p epochs 10
104
105	# Pass dict parameter
106	papermill input.ipynb output.ipynb -y "{'config': {'lr': 0.001}}"
107	```
108
109	Mark parameter cell with tag `parameters` in the notebook.
110
111	---
112
113	## Kernel Management
114
115	```bash
116	# List running kernels
117	jupyter kernel list
118
119	# List available kernel specs
120	jupyter kernelspec list
121
122	# Install a kernel from venv
123	source myenv/bin/activate
124	pip install ipykernel
125	python -m ipykernel install --user --name myenv
126
127	# Remove kernel
128	jupyter kernelspec remove myenv
129	```
130
131	---
132
133	## Magic Commands (in notebooks)
134
135	```python
136	# Time a single line
137	%timeit [i**2 for i in range(1000)]
138
139	# Time a cell
140	%%timeit
141	result = [i**2 for i in range(1000)]
142
143	# Run shell command
144	!pip install pandas
145	!ls -la
146
147	# Show matplotlib inline
148	%matplotlib inline
149
150	# Load external script
151	%load script.py
152
153	# Auto-reload modules
154	%load_ext autoreload
155	%autoreload 2
156
157	# Run bash cell
158	%%bash
159	echo "Hello from bash"
160	ls
161	```
162
163	---
164
165	## Common Data Analysis Pattern
166
167	```python
168	import pandas as pd
169	import matplotlib.pyplot as plt
170	import numpy as np
171
172	# Load data
173	df = pd.read_csv("data.csv")
174
175	# Quick overview
176	print(df.shape)
177	df.info()
178	df.describe()
179	df.isnull().sum()
180
181	# Plot
182	fig, axes = plt.subplots(1, 2, figsize=(12, 4))
183	df["column"].hist(ax=axes[0])
184	df.plot.scatter(x="col1", y="col2", ax=axes[1])
185	plt.tight_layout()
186	plt.savefig("plot.png", dpi=150)
187	plt.show()
188	```
189
190	---
191
192	## VS Code Integration
193
194	- Install "Jupyter" extension
195	- Open `.ipynb` files directly
196	- Select kernel from top-right dropdown
197	- Run cells with `Shift+Enter`
198	- Variables panel: View → Variables

People who liked this also viewed

6 picks

Type