From nickcrew-claude-ctx-plugin
Extracts insights from multi-agent interactions, identifies patterns, codifies best practices into knowledge nuggets and playbooks, and optimizes for RAG retrieval.
npx claudepluginhub nickcrew/claude-cortexThis skill uses the workspace's default tool permissions.
Extract, organize, and distribute insights across multi-agent systems. Turns raw
Extracts patterns, templates, and preferences from completed knowledge work to store learnings and improve future tasks. Activates on reflection requests like 'what did we learn' or after high-stakes work.
Extracts patterns, quirks, and decisions from conversations; persists to Markdown files in knowledge/learnings/. Use /learn for quick or /learn --deep for thorough analysis.
Reviews AI agent sessions to extract patterns, gotchas, preferences, decisions, and TODOs. Updates MEMORY.md and daily files, commits to git. Automates nightly loops for compounding knowledge.
Share bugs, ideas, or general feedback.
Extract, organize, and distribute insights across multi-agent systems. Turns raw interaction data, logs, and outcomes into actionable knowledge through pattern recognition, best practice codification, and structured retrieval.
| Resource | Purpose | Load when |
|---|---|---|
references/synthesis-workflow.md | Pattern recognition, RAG optimization, citation methods, knowledge graphs | Starting a synthesis cycle |
Phase 1: Discovery → Mine interactions, logs, and outcomes for patterns
Phase 2: Codification → Document best practices, build knowledge graph
Phase 3: Dissemination → Surface insights to relevant agents/teams
Phase 4: Feedback → Capture adoption feedback, refine the knowledge base
Map the landscape before extracting insights:
Transform raw patterns into structured, retrievable knowledge:
## [Pattern Name]
**Context**: When does this pattern apply?
**Evidence**: What interactions/outcomes support it? [cite sources]
**Action**: What should agents do when they encounter this situation?
**Confidence**: High | Medium | Low
**Tags**: [domain], [workflow-type], [agent-role]
Surface the right insights to the right consumers:
Close the loop to keep the knowledge base accurate:
When answering questions based on the knowledge base, provide grounded responses:
[1], [2]) inlineExample:
The retry logic reduces failures by 40% in high-latency environments [1].
References: [1] "Session 2025-03-12" -- "After adding exponential backoff, error rate dropped from 12% to 7%"