一键导入
enrich-notebooks
Enrich Jupyter notebooks with pedagogical markdown content. Arguments: [target] [--execute] [--fix-errors] [--strict] [--consecutive] [--iterate]
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Enrich Jupyter notebooks with pedagogical markdown content. Arguments: [target] [--execute] [--fix-errors] [--strict] [--consecutive] [--iterate]
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH|MED|LOW] [--json]
Resume multi-agent coordination session. Reads memory, RooSync inbox, GitHub issues, and produces a situational briefing with recommended actions. Arguments: [--dispatch] [--focus <topic>] [--reply-all]
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]
Train an ML model in the QuantConnect ML-Training-Pipeline with thermal-safe GPU usage and rigorous validation. Arguments: <architecture|script> [--dry-run] [--seeds 0,1,7,42,99] [--folds 5] [--bg]
Execute iterative improvement workflow for QuantConnect strategies. Arguments: [strategy|issue#] [--iterations=N] [--no-backtest] [--commit]
Review and merge student exercise PRs during TP sessions. Arguments: <repo-url> [--class <class-id>] [--timeslot <HH:MM-HH:MM>] [--dry-run]
| name | enrich-notebooks |
| description | Enrich Jupyter notebooks with pedagogical markdown content. Arguments: [target] [--execute] [--fix-errors] [--strict] [--consecutive] [--iterate] |
Add pedagogical markdown content to Jupyter notebooks.
Target: $ARGUMENTS
target: Notebook path, family name (Infer, Sudoku, Tweety, Lean, GenAI, etc.), or all--execute: Run notebooks and capture outputs before enriching--fix-errors: Correct code errors found during execution--strict: Require interpretation after EVERY code cell--consecutive: Focus on consecutive code cells without markdown--iterate: Use cell-iterator for iterative correctionParse target - Discover notebooks to enrich
For each notebook, launch a background agent:
.claude/agents/notebook-enricher.md)python scripts/notebook_tools/notebook_helpers.py list {path} --verbosefrom scripts.notebook_helpers import NotebookHelper
helper = NotebookHelper(path)
gaps = helper.find_cells_needing_enrichment() # Cells missing interpretation
consecutive = helper.find_consecutive_code_cells() # Code cells without markdown between
helper.validate_enrichment_context(cell_index) returns what's neededhelper.get_cell_sequence(start, end) after each insertionIf --execute: Execute notebooks first to capture outputs for interpretation
If --fix-errors: Analyze errors, propose corrections, re-execute
If --consecutive: Prioritize fixing consecutive code cells
If --iterate: Use notebook-cell-iterator agent for targeted cell fixes
Use model: sonnet for enrichment agents (good balance of speed and quality).
For complex domains (Probas, Lean), consider model: inherit for better reasoning.
Task(
subagent_type="general-purpose",
model="sonnet",
prompt="Tu es un agent notebook-enricher. Lis .claude/agents/notebook-enricher.md. Enrichis: {path}",
description=f"Enrich {name}",
run_in_background=True
)
| Type | Placement | Tense |
|---|---|---|
| Section intro | BEFORE code | Future: "This code will..." |
| Code explanation | BETWEEN code cells | Present: "This function..." |
| Result interpretation | AFTER code output | Past: "The results show..." |
| Transition | Between sections | "After seeing X, let's explore Y..." |
| Conclusion | End of section | Summary table |
git diff (expect more insertions than deletions)/cleanup-notebooks to fix any positioning issues