Skip to content

gpsaggese/helpers / .claude/skills/notebook.brainstorm_outline

notebook.brainstorm_outline

Verified

Create a set of ideas for Jupyter notebooks to explore ideas and concepts

Goal

  • Given technical material, come up with 5 ideas for interactive Jupyter notebooks that teach its concepts through visualization, interaction, and exploration

  • When possible, use "famous" examples, data, experiments, and problems related to the material

  • Output notebook_ideas.<TAG>.md, a markdown file that describes the ideas

  • State in the output how it was generated, with this line right after the title:

    - Generated by `.claude/skills/notebook.brainstorm_outline/SKILL.md`
    

Template

  • For each idea, use a template like
    ## 1. <Title>
    
    ### Goal
    Students gain intuitive understanding of ... by building and analyzing ... and
    exploring the relationship between ...
    
    ### Learning Objectives
    - Understand ...
    - Visualize ...
    
    ### Core Concepts
    - ...
    
    ### Key Packages
    - **package**: ...
    
    (Do not cite the standard packages like pandas, scipy, numpy, matplotlib)
    
    ### Learning Activities
    - Build ...
    - Generate ...
    - Test ...
    - Explore ...
    - Measure ...
    - Interactive ...
    

Example

  • For a query like "Explain propositional logic":
    ## 1. Interactive Logic Explorer
    
    ### Goal
    - Students will:
      - Gain intuitive understanding of propositional logic by building and analyzing
        logical formulas, truth tables, and inference rules
      - Explore the relationship between syntax, semantics, and computation.
    
    ### Learning Objectives
    - Construct propositional formulas and evaluate truth values
    - Enumerate all models and check entailment
    - Understand SAT solving and computational complexity
    - Visualize how expressiveness and tractability trade off
    
    ### Core Concepts
    - Propositional logic syntax (operators: not, and, or, implies, iff)
    - Semantics via truth tables and model interpretation
    - Inference rules (Modus Ponens, Modus Tollens, Resolution)
    - Model checking algorithm (sound and complete)
    - Satisfiability and NP-completeness
    
    ### Key Packages
    - **sympy**: symbolic logic, propositional formula manipulation
    - **python-sat**: SAT solver backends
    
    ### Learning Activities
    - Build formulas interactively: `(Rain and Cold) or Sunny`
    - Generate and display truth tables for arbitrary formulas
    - Test entailment between two formulas: does KB entail alpha?
    - Explore inference rules (modus ponens, resolution)
    - Measure SAT solver complexity as # variables increases
    - Interactive "Wumpus World" knowledge base reasoning
    

Conventions

  • When writing markdown text follow
    • .claude/skills/markdown.rules.md: Markdown formatting rules
    • .claude/skills/text.rules.md: Bullet point conventions

Lint

  • After generating the file notebook_ideas.<TAG>.md
    > lint_text.py -i `notebook_ideas.<TAG>.md`
    

Verification

  • The output file says that it was generated by .claude/skills/notebook.brainstorm_outline/SKILL.md
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: 118kUpdated Claude CodeCodexVerifiedInstall
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: 118kUpdated Claude CodeCodexVerifiedInstall
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: 117kUpdated Claude CodeCodexVerifiedInstall
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: 117kUpdated Claude CodeCodexVerifiedInstall