session-learn
Session Learn — Continuous Knowledge Extraction
Automatically extract knowledge signals from the current session and persist them to the wiki. Inspired by ECC continuous-learning but outputs structured wiki pages instead of atomic instincts.
When to Use
- User says "extract this session" or "save what we learned"
- After completing substantive work (≥5 tool calls)
- As part of a session-end review routine
- User corrects the agent's understanding of a topic
- Auto-trigger after completing a cognitive-compile, wiki-ingest, or deep-research task
The 7 Knowledge Signals
1. New Concept
Signal: Session discussed a concept/framework/methodology not in the wiki.
More from mark393295827/third-brain-v5-skills
project-flow-ops
Operate execution flow — triage tasks, manage priorities, keep progress structured. Use when the user needs backlog control, task planning, or workflow coordination across projects.
2context-manager
Manage the LLM's context window — token budgeting, prompt assembly, truncation strategies. Use when approaching context limits or optimizing prompt costs.
2deep-research
Multi-source deep research — search, synthesize, and deliver cited reports. Use when the user wants thorough research on any topic with evidence and citations.
2verify-before-claim
Iron rule — no completion claims without fresh verification evidence. Use whenever about to claim work is done, fixed, working, or passing. Run verification commands and show output before making any success statement.
2harness-engineering
Design runtime infrastructure around AI agents — permissions, tools, feedback loops, observability. Use when deploying agents to production or designing multi-agent systems.
2wiki-lint
Health-check the knowledge wiki — find orphans, broken links, missing frontmatter, contradictions, stale content, and statistical drift. Use when the user says "lint the wiki", "health check", or periodically for maintenance.
1