SkillAgentSearch skills...

jupyter-live-kernel

Stateful Jupyter kernel — variables persist across cells (hamelnb)

Install / Use

npx skills add taracodlabs/aiden --skill jupyter-live-kernel

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

Universal

Our assessment of jupyter-live-kernel

jupyter-live-kernel scores 85/100 on our quality scale, 463rd of 608 Data & Analytics skills we index.

Its SKILL.md is 3.7 KB long, well organised into 18 sections with 5 code examples: a solid amount of guidance for an agent.

It has 843 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so jupyter-live-kernel is actively maintained.
  • Our last check on 2026-11-05 found the source still online.
  • It is released under AGPL-3.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

jupyter-live-kernel compared with similar skills

All 4 of these similar skills score higher than jupyter-live-kernel; compare them before choosing.

SkillScoreStarsUpdatedFormat
jupyter-live-kernel (this skill)by taracodlabs858432mo agoSKILL.md
Agent-Reachby Panniantong100112.7k9d agoCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md
Scraplingby D4Vinci100103.9ktodayMCP Server
crawl4aiby unclecode10087.5ktodayMCP Server

Frequently asked questions

How do I install jupyter-live-kernel?
Run npx skills add taracodlabs/aiden --skill jupyter-live-kernel. The install tabs above show the steps for each supported agent.
Which AI agents does jupyter-live-kernel work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is jupyter-live-kernel safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is AGPL-3.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is jupyter-live-kernel still maintained?
The repository was last updated about 2 months ago, so jupyter-live-kernel is actively maintained.

name: jupyter-live-kernel description: Stateful Jupyter kernel — variables persist across cells (hamelnb) category: developer version: 1.0.0 origin: aiden license: Apache-2.0 tags: jupyter, notebook, kernel, python, data-science, ipython, stateful, cells, pandas

Jupyter Live Kernel Execution

Run Python code in a persistent Jupyter kernel so that variables, imports, and state carry over between executions — exactly like working in a notebook, but from the CLI.

When to Use

  • User wants to run data analysis across multiple code cells with shared state
  • User wants to explore a dataset step by step
  • User wants to run ML training and inspect intermediate results
  • User wants to execute a .ipynb notebook file from the command line
  • User wants to maintain a REPL-like Python session with persistent variables

How to Use

1. Install hamelnb (stateful kernel CLI)

pip install hamelnb
# or use jupyter directly
pip install jupyter

2. Start a kernel and run cells (hamelnb)

# Start a persistent kernel session (keeps running between calls)
hamelnb start --name datasession

# Execute a code snippet in the named session
hamelnb run datasession "import pandas as pd; df = pd.read_csv('data.csv'); print(df.shape)"

# Execute next cell — df variable is still available
hamelnb run datasession "print(df.describe())"

# Stop session when done
hamelnb stop datasession

3. Execute a notebook file

# Run all cells in a notebook and save output
jupyter nbconvert --to notebook --execute analysis.ipynb --output analysis_out.ipynb

# Run and convert output to HTML for viewing
jupyter nbconvert --to html --execute analysis.ipynb --output report.html

4. Run Python code in a Jupyter kernel via Python API

import jupyter_client, queue

km = jupyter_client.KernelManager(kernel_name="python3")
km.start_kernel()
kc = km.client()
kc.start_channels()
kc.wait_for_ready(timeout=30)

def run_cell(code):
  kc.execute(code)
  outputs = []
  while True:
    try:
      msg = kc.get_iopub_msg(timeout=10)
      if msg["msg_type"] == "stream":
        outputs.append(msg["content"]["text"])
      elif msg["msg_type"] == "execute_result":
        outputs.append(msg["content"]["data"].get("text/plain",""))
      elif msg["msg_type"] == "status" and msg["content"]["execution_state"] == "idle":
        break
    except queue.Empty:
      break
  return "".join(outputs)

print(run_cell("import pandas as pd; df = pd.read_csv('data.csv'); df.shape"))
print(run_cell("df.describe()"))   # df is still in scope!
km.shutdown_kernel()

5. Inject variables into a running kernel

# Use run_cell from step 4 to inject values
run_cell("x = 42; y = [1, 2, 3]")
result = run_cell("print(x * 2, sum(y))")

Examples

"Load sales.csv and show the top 10 rows, then plot revenue by month" → Use step 4: run cell 1 to load and preview the CSV, run cell 2 to group by month and show results — df persists between calls.

"Execute my analysis.ipynb notebook and give me the output" → Use step 3 with jupyter nbconvert --to notebook --execute.

"Explore the wine quality dataset — check correlations step by step" → Use hamelnb (step 2) to build up analysis iteratively with named session.

Cautions

  • Kernel sessions consume memory for as long as they run — always km.shutdown_kernel() when done
  • Long-running cells (ML training) will block until complete — set reasonable timeouts
  • nbconvert --execute re-runs all cells from scratch — it does not resume a previous state
  • hamelnb is a third-party tool — verify it is installed with pip show hamelnb before use
  • Never pass user secrets as inline code strings — use environment variables or config files instead

Related Skills

View on GitHub
GitHub Stars843
CategoryData
Updated2mo ago
Forks147

Languages

TypeScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions