メニュー
Reference for notebook manipulation scripts (notebook_helpers.py, notebook_tools.py). Use when working with Jupyter notebooks, analyzing structure, executing cells, or manipulating notebook content.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/jsboige/CoursIA --skill notebook-helpersコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
SOC 職業分類に基づく
| name | notebook-helpers |
| description | Reference for notebook manipulation scripts (notebook_helpers.py, notebook_tools.py). Use when working with Jupyter notebooks, analyzing structure, executing cells, or manipulating notebook content. |
from scripts.notebook_helpers import NotebookHelper, CellIterator, NotebookExecutor
# Read and analyze
helper = NotebookHelper("path/to/notebook.ipynb")
helper.list_cells() # List all cells with type, preview
helper.get_cell_source(5) # Source code of cell 5
helper.set_cell_source(5, "new code") # Modify cell content
helper.find_cells_with_pattern("import") # Search by regex
helper.find_cells_with_errors() # Cells with error outputs
helper.find_consecutive_code_cells() # Code cells without markdown between
helper.save() # Save modifications
# Iterative correction
iterator = CellIterator(
notebook_path="notebook.ipynb",
cell_index=5,
objective="Output should contain 'SUCCESS'",
max_iterations=5
)
# List cells (verbose shows source preview)
python scripts/notebook_tools/notebook_helpers.py list notebook.ipynb --verbose
# Execute a specific cell
python scripts/notebook_tools/notebook_helpers.py execute notebook.ipynb --cell 5 --timeout 60
# Execute entire notebook cell-by-cell
python scripts/notebook_tools/notebook_helpers.py execute notebook.ipynb --verbose
# Detect kernel type
python scripts/notebook_tools/notebook_helpers.py detect-kernel notebook.ipynb
# Get cell source or output
python scripts/notebook_tools/notebook_helpers.py get-source notebook.ipynb 5
python scripts/notebook_tools/notebook_helpers.py get-output notebook.ipynb 5
# Validate structure (quick) or full (with execution)
python scripts/notebook_tools/notebook_tools.py validate Sudoku --quick
python scripts/notebook_tools/notebook_tools.py validate MyIA.AI.Notebooks/Sudoku/Sudoku-1.ipynb
# Extract skeleton for README generation
python scripts/notebook_tools/notebook_tools.py skeleton MyIA.AI.Notebooks/Tweety --output markdown
# Analyze notebook structure
python scripts/notebook_tools/notebook_tools.py analyze MyIA.AI.Notebooks/SymbolicAI
# Check environment requirements
python scripts/notebook_tools/notebook_tools.py check-env Lean
# Execute notebook
python scripts/notebook_tools/notebook_tools.py execute GameTheory --timeout 120 --cell-by-cell
# Quick summary
python scripts/notebook_tools/extract_notebook_skeleton.py MyIA.AI.Notebooks/Sudoku
# Markdown table for README
python scripts/notebook_tools/extract_notebook_skeleton.py MyIA.AI.Notebooks/Sudoku --output markdown
# Detailed with code previews
python scripts/notebook_tools/extract_notebook_skeleton.py MyIA.AI.Notebooks/Sudoku --output detailed --code-preview
# JSON for programmatic use
python scripts/notebook_tools/extract_notebook_skeleton.py MyIA.AI.Notebooks/Sudoku --output json
| Script | Description |
|---|---|
validate_stack.py | Full ComfyUI stack validation |
validate_notebooks.py | Papermill execution of GenAI notebooks |
check_vram.py | GPU/VRAM availability check |
list_models.py | List available ComfyUI models |
list_nodes.py | List ComfyUI nodes |
docker_manager.py | Docker service management |
notebook_helpers.py list is the fastest way to understand a notebook's structurenotebook_tools.py validate --quick for rapid structural validationvalidate_stack.py firstCycle de coordination ai-01 (coordinateur UNIQUEMENT — jamais sur un worker). Lit memoire + dashboards + inbox + GitHub, merge les PRs pretes, tranche les design-gates, dispatche des grains par lane, reporte. Arguments: [--dispatch] [--focus <topic>]
Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH|MED|LOW] [--json]
Iterate on a GenAI notebook against the self-hosted stack via the genai-stack CLI (config dirs, auth, subdomains, quantization, GPU/VRAM). Arguments: <notebook|service> [--service comfyui|forge|vllm] [--quant int4|fp8] [--validate] [--bg]