---

name: memory-documentary version: 1.0.0 description: Generate evidence-based documentary reports by searching across all 4 memory systems (Claude-Mem, Forgetful, Serena, DeepWiki), .agents/ artifacts, and GitHub issues. Produces investigative journalism-style analysis with full citation chains. license: MIT model: claude-sonnet-4-5 metadata: timelessness: 8/10 category: analysis

Memory Documentary Skill

Generate comprehensive documentary-style reports from your memory systems with full evidence chains.

---

Quick Start

Copy/memory-documentary [topic]

Example topics:

• "recurring frustrations"
• "coding patterns not codified"
• "evolution of thinking on testing"
• "decisions I second-guessed"
• "what I complain about most"

---

Triggers

Use this skill when:

• "Search my memories for patterns about..."
• "What does my history say about..."
• "Generate a documentary on my [topic]"
• "Cross-reference all systems for..."
• "Evidence-based analysis of my [topic]"

---

Quick Reference

---

How It Works

The skill searches ALL available data sources systematically:

Memory Systems (4 MCP servers):

• Claude-Mem: Timeline observations via 3-layer workflow
• Forgetful: Semantic memory with linked entities
• Serena: Project-specific lexical memory
• DeepWiki: Documentation resources

Project Artifacts:

• .agents/retrospective/ - Learning extractions
• .agents/sessions/ - Session logs
• .agents/analysis/ - Research reports
• .agents/architecture/ - ADRs
• .agents/planning/ - Plans and PRDs

GitHub Issues:

• Open and closed issues
• Comments and related PRs

---

Commands

Copy# Standard invocation
/memory-documentary "recurring frustrations"

# With explicit time range
/memory-documentary "testing patterns" --since 2025-12-01

---

Report Structure

Executive Summary

• Key finding in one sentence
• Timeline span (earliest to most recent)
• Evidence count (memories + observations + issues + files)
• Major pattern categories

Evidence Trail

Full citation for each finding:

• Memory ID/Observation ID with retrieval command
• Source system (Forgetful/Claude-Mem/Serena)
• Timestamp/Creation date
• Direct quote from source
• Links to related evidence

Pattern Evolution

Timeline showing how thinking changed:

CopyYYYY-MM-DD: [Observation #ID] - Initial state
YYYY-MM-DD: [Memory #ID] - First iteration
YYYY-MM-DD: [Issue #NNN] - Technical response

Unexpected Patterns

Cross-system synthesis revealing:

• Frequency patterns (time clustering)
• Correlation patterns (X happens before Y)
• Avoidance patterns (conspicuous absence)
• Contradiction patterns (saying vs doing)
• Evolution patterns (recursive loops)
• Emotional patterns (frustration markers)

Synthesis

• What all systems agree on
• What's recent (Claude-Mem) vs crystallized (Forgetful)
• Actionable recommendations

---

Evidence Standards

---

Anti-Patterns

---

Output Location

Reports saved to: .agents/analysis/[topic]-documentary-[date].md

---

Related Skills

---

On Invocation

Read: references/execution-protocol.md

This contains the full 5-phase execution protocol with detailed instructions for each data source.