tianzhenyu516-alt/ai-agent-skills-toolkit / data-science/jupyter-notebook
jupyter-notebook
VerifiedCreate, edit, and validate self-contained Jupyter notebooks for experiments or tutorials without external templates.
Jupyter notebook
Use this skill to create or revise .ipynb files for an experiment, analysis, or tutorial. No bundled assets or helper scripts are required.
Plan the notebook
- Identify the audience, question, available data, kernel, and dependencies. For private data, use a documented local path or a synthetic sample rather than committing the data.
- Choose an experiment structure (question, setup, method, results, limitations) or tutorial structure (goal, prerequisites, short steps, exercises, recap).
Build or edit
- Use the notebook format supported by the environment; prefer
nbformatwhen installed. Give each section a concise Markdown heading and keep code cells small enough to inspect independently. - Place imports and configuration near the top. Use reproducible random seeds when randomness affects results. Avoid absolute personal paths, credentials, and network-dependent examples unless essential.
- Make units, expected shapes, and assumptions explicit. Separate source data from derived output. Do not embed private data, huge outputs, or hidden state.
- When editing an existing notebook, preserve useful metadata and intentional outputs. Remove only stale or sensitive outputs.
Validate
- Parse the final notebook as valid
.ipynb. Execute it from a clean kernel when dependencies and safe data are available. - Check cell order, missing variables, broken relative paths, unexpectedly large outputs, and nonportable configuration.
- Report execution status and any dependencies or private inputs needed to reproduce results.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |