Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Create New Notebook — measured AI agent skill | DecimalAI

brycewang-stanford/new-notebook

SkillScore73Maintained

Creates a Jupyter notebook with Jupytext pairing and registers it in _quarto.yml. Use when adding a new notebook.

Documentationby brycewang-stanford

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull brycewang-stanford-new-notebook

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/brycewang-stanford-new-notebook/SKILL.md

Raw file: /s/brycewang-stanford-new-notebook/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-new-notebook.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9h ago

—-36% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	-51%	0%
case-10	✗→✓	▲ Improved	-68%	0%
case-11	✗→✓	▲ Improved	-57%	0%
case-12	✗→✓	▲ Improved	-37%	0%
case-18	✗→✓	▲ Improved	15%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/29-quarcs-lab-project20XXy/dot-claude/skills/new-notebook/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

Skill contents

SKILL.md

Create New Notebook

Create a new Jupyter notebook with Jupytext pairing and register it in the manuscript.

Arguments

$ARGUMENTS — the notebook name and title (e.g., "notebook-02 Regression Analysis")

Steps

Parse the name and title from the arguments. Follow the naming convention: notebook-NN.ipynb (sequential numbering)
Check notebooks/ for existing notebooks to determine the next number
Create the .ipynb file in notebooks/ with:

The correct kernel (ask user: Python, R, or Stata)
A first code cell with the setup appropriate for the chosen kernel:
Python: import sys; sys.path.insert(0, ".."); from config import set_seeds, DATA_DIR; set_seeds()
R: source("../config.R"); set_seeds()
Stata: clear all followed by set seed 42
A markdown cell with the notebook title

Create the Jupytext .md pair by running: uv run jupytext --set-formats ipynb,md:myst notebooks/<name>.ipynb
Register the notebook in _quarto.yml under manuscript.notebooks:

yaml

notebook: notebooks/<name>.ipynb

title: "N<number>: <title>"

Confirm the notebook renders: quarto render notebooks/<name>.ipynb

Want to see if brycewang-stanford/new-notebook would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.