メニュー
Extract unique insights and perspectives from personal content (conversations, transcripts, notes). Spawns insight-extractor subagent.
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。
SOC 職業分類に基づく
| name | extract-insights |
| description | Extract unique insights and perspectives from personal content (conversations, transcripts, notes). Spawns insight-extractor subagent. |
| allowed-tools | ["Task"] |
| user-invocable | true |
| arg-description | <file path or content description> |
Extract unique insights, original thinking, and distinctive perspectives from YOUR content.
User-invocable wrapper that spawns the insight-extractor subagent to:
Brain/AI Extracted Notes/NOT for external research - use /extract-document-insights for papers, books, articles.
/extract-insights /path/to/transcript.md
/extract-insights "the conversation above about dopamine"
Task(
subagent_type="insight-extractor",
prompt="Extract insights from: [source]. Follow your mandatory workflow - contextualize, search for duplicates, extract, create notes, update changelog."
)
Brain/AI Extracted Notes/Brain/05-Meta/Changelogs/Autonomous AI crystallization - synthesizes converged thinking topics into ai-inferred notes in a dedicated folder. Never touches the human-curated permanent knowledge base and never changes a topic's status, so manual crystallization stays available to the user.
Analyze knowledge base structure and update the knowledge-base-analysis.md report
Discover non-obvious cross-domain connections through random sampling and pattern analysis
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative
Create long-form articles from knowledge base insights. Use when writing articles, blog posts, Substack content, or synthesizing knowledge into publishable content. Includes tone of voice, structure templates, and knowledge base integration.