Skip to content

gpsaggese/helpers / .claude/skills/text.extract_ideas

text.extract_ideas

Verified

Extract the most interesting ideas from the text

Goal

  • You are an expert reader and critical thinker
  • Print each step before executing it

Workflow

Read the Given Text

  • Extract the most thought-provoking, surprising, and intellectually interesting ideas from the text below
  • Focus on:
    • Ideas that challenge common assumptions or conventional wisdom
    • Counterintuitive, paradoxical, or unexpected concepts
    • Insights with deep implications (philosophical, scientific, social, or psychological)
    • Elegant, novel, or powerful ways of explaining something
    • Hidden patterns, connections, or underlying themes

Extract Ideas

  • For each idea, write bullets following .claude/skills/markdown.rules.md and .claude/skills/text.rules.md

  • Create a header 1 with a short summary

    # <ID>. Creative Destruction as Generative Force
    
  • State the idea clearly and concisely

    **Idea**: ...
    
  • Explain why it is interesting, surprising, or important

    **Why it is interesting**: ...
    
  • (Optional) Add a short reflection or question that deepens the insight

    **Reflections**: ...
    
  • E.g.,

    # 1. Pre-training as "Crappy Evolution"
    - **Idea**
      - ...
      - ...
    - **Why it's interesting**:
      - Pre-training LLMs on internet data creates a practical shortcut to
        biological evolution: encoding vast human knowledge into neural weights
      - Not true evolution (doesn't run on biology), but achieves similar
        bootstrapping in weeks instead of millions of years
      - Reframes AI development from "mimicking nature" to "using human cultural
        artifacts as evolutionary substitute"
      - Suggests evolution was finding an algorithm; pre-training is compressing
        knowledge
    - **Reflection**
      - If pre-training is evolution's shortcut, what breaks down in the analogy?
      - Is intelligence from knowledge compression equivalent to intelligence from
        algorithmic discovery?
    
  • Prioritize quality over quantity: select only the most compelling ideas

Save the Output

  • Save the output in <FILE>.ideas.md
  • Run lint_text.py -i to format <FILE>.ideas.md

Verification

  • Confirm <FILE>.ideas.md was created
  • Confirm lint_text.py -i ran without errors
  • Confirm each idea includes Idea, Why it is interesting, and (optional) Reflections
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 193kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 193kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 193kUpdated Claude CodeCodexVerifiedInstall