Story Explanation - Narrative Summary with Creative Analysis

🎯 Load Full PAI Context

Before starting any task with this skill, load complete PAI context:

read ${PAI_DIR}/skills/CORE/SKILL.md

Core Philosophy

Standard approach: Generate a generic summary of content.

This skill: Use UltraThink to analyze multiple narrative framings, then select the BEST one and present it in a compelling story format.

Based on:

• UltraThink: Deep content understanding across multiple perspectives and narrative angles
• Best framing selection: Choose the most compelling narrative angle from multiple options
• Daniel Miessler voice: First person, casual, direct, genuinely curious

The Problem This Solves:

• Generic summaries use obvious framing without exploring alternatives
• Mode collapse causes formulaic story explanations
• Best narrative angles get missed in favor of first-thought approaches
• Content needs to be explained in conversational, engaging way

When to Activate This Skill

• User requests story explanations or narrative summaries
• User says "create a story explanation" or "explain this as a story"
• User says "narrative summary", "tell as story", or "explain in narrative"
• User wants content explained in conversational, engaging format
• Need to find the most compelling narrative hook for content
• User explicitly requests this skill
• Want to present content in Daniel's voice
• Format-specific requests: "story with links", "abridged story", "5-line summary", "CSE", "CSE5"
• Slash commands: /create-story-explanation, /cse, /cse5

DO NOT use this skill when:

• User wants comprehensive extraction (use research skill with fabric)
• User wants quick technical summary
• Speed matters more than narrative quality

🔀 Workflow Routing

This skill contains multiple workflows for different story explanation formats:

Available Workflows:

1. workflows/create.md - Main 3-part narrative (default)

   • Use when: User wants standard story explanation format
   • Triggers: "create story explanation", "story explanation", default workflow
   • Output: 3-part format (opening 15-25 words → body 5-15 sentences → closing 15-25 words)

2. workflows/create-with-links.md - N-length format with inline source links

   • Use when: User wants comprehensive narrative with source attribution
   • Triggers: "story explanation with links", "narrative with sources", "with inline citations"
   • Output: N sentences (default 25) with inline links after each sentence

3. workflows/create-abridged.md - Ultra-concise 5-line format (5-12 words per line)

   • Use when: User wants abbreviated format from URL, YouTube, or text
   • Triggers: "create abridged story explanation", "5-line summary", command: /create-abridged-story-explanation
   • Output: 5 lines with strict word limits

4. workflows/cse.md - Comprehensive explanation using Foundry MCP

   • Use when: User wants detailed narrative explanation
   • Triggers: "run CSE", "explain this story", command: /cse
   • Output: Complete narrative explanation via Foundry

5. workflows/cse5.md - Clean 5-line numbered format using Foundry MCP

   • Use when: User wants scannable, numbered breakdown
   • Triggers: "explain in 5 lines", "CSE5", command: /cse5
   • Output: 5 numbered lines, one concept per line

Routing Decision Tree:

User request → Analyze intent:

├─ "with links" OR "inline sources" OR "with citations"
│  └─> workflows/create-with-links.md (N-length format with inline links)
│
├─ "abridged" OR "5-12 words per line"
│  └─> workflows/create-abridged.md
│
├─ "CSE5" OR "5 lines" OR "numbered"
│  └─> workflows/cse5.md
│
├─ "CSE" OR "comprehensive explanation"
│  └─> workflows/cse.md
│
└─ Default OR "story explanation"
   └─> workflows/create.md (3-part narrative)

Command Routing:

• /create-story-explanation → workflows/create.md
• /create-story-output-links → workflows/create-with-links.md
• /create-abridged-story-explanation → workflows/create-abridged.md
• /cse → workflows/cse.md
• /cse5 → workflows/cse5.md

📁 Scratchpad → History Pattern

Working Directory: ${PAI_DIR}/scratchpad/YYYY-MM-DD-HHMMSS_story-explanation-[topic]/

Process:

1. Scratchpad (Working Files):

   • Create timestamped directory for each story explanation project
   • Store raw content extraction (transcripts, article text, etc.)
   • Keep UltraThink analysis notes
   • Save multiple framing explorations (5+ options from deep analysis)
   • Draft iterations and refinements
   • Example: ${PAI_DIR}/scratchpad/2025-10-26-143000_story-explanation-agi-timeline/

2. History (Permanent Archive - Optional):

   • Move to ${PAI_DIR}/history/research/YYYY-MM/YYYY-MM-DD-HHMMSS_AGENT-[agent]_RESEARCH_[slug].md ONLY IF:
     • The analysis provides valuable reusable insights about narrative framing
     • The content analysis reveals patterns applicable to future work
     • The framing exploration demonstrates particularly effective techniques
     • You want to reference this analysis methodology later
   • Include: Final story explanation + UltraThink analysis notes + framing options explored
   • Most story explanations are one-off outputs and can stay in scratchpad

3. Distinction:

   • Scratchpad = All working files (content extraction, drafts, explorations)
   • History = Only valuable analytical insights (methodology learnings, exceptional framing discoveries)
   • Most story explanations are throwaway content - only archive exceptional analysis

File Structure Example:

${PAI_DIR}/scratchpad/2025-10-26-143000_story-explanation-agi-timeline/
├── raw-content.txt                    # Extracted article/transcript
├── ultrathink-analysis.md             # Deep narrative analysis notes
├── framing-explorations.md            # 5+ different narrative framings explored
├── draft-v1.md                        # First draft
├── draft-v2.md                        # Refined version
└── final-story-explanation.md         # Final output

# Only if exceptional:
${PAI_DIR}/history/research/2025-10/2025-10-26-143000_AGENT-default_RESEARCH_agi-timeline-narrative-framing-analysis.md

Guidelines:

• Always work in scratchpad first
• Only move to history if the analysis itself is valuable for future reference
• Clean up scratchpad after project completion (or leave for periodic cleanup)
• The story explanation output itself goes to the user - not necessarily to history

The Four-Step Process

Step 1: Content Extraction

For YouTube videos:

fabric -y "YOUTUBE_URL"

For URLs/articles:

WebFetch(url, "Extract full content of this article")

For other content:

• Paste text directly
• Read from files

Step 2: Activate Be Creative Skill

Load the be-creative skill for deep reasoning enhancement:

This provides access to:

• UltraThink: Deep reasoning and quality analysis
• Enhanced techniques for finding the best narrative framing

Step 3: Deep UltraThink Analysis (via Be Creative)

Before generating story explanation, engage in extended deep thinking:

UltraThink Protocol:

ULTRATHINK DEEP STORY ANALYSIS MODE:

Think deeply and extensively about this content:

1. CORE NARRATIVE - What's the fundamental story being told?
2. MULTIPLE FRAMINGS - What are 5-7 different ways to frame this story?
3. AUDIENCE ANGLES - How would different audiences understand this?
4. HOOK VARIETY - What are compelling but different entry points?
5. EMPHASIS OPTIONS - Which elements could be emphasized or de-emphasized?
6. STRUCTURAL APPROACHES - Chronological? Problem-solution? Comparison?
7. IMPACT FOCUS - What's the "wow" factor that makes this significant?
8. CONVERSATIONAL FLOW - How would Daniel explain this to a friend?
9. KEY INSIGHTS - What makes readers think "I get it now!"?
10. BEST FRA