Menu
Extract non-obvious session learnings into scoped AGENTS.md files
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Checkpoint episodes and create handoff packs for multi-agent session continuity
Configure, test, benchmark, and manage embedding providers for semantic search and vector operations
Create and traverse typed relationships between episodes for dependency tracking and knowledge graphs
Manage episode tags for organization, filtering, and retrieval across the memory system
Generate task playbooks and explain patterns using learned strategies from episodic memory
Record and analyze recommendation sessions and feedback to drive the self-learning loop
| name | learn |
| description | Extract non-obvious session learnings into scoped AGENTS.md files |
| category | knowledge-management |
| trigger | after non-trivial task completion |
Extract non-obvious session learnings into scoped AGENTS.md files to preserve knowledge across sessions.
Activate after completing a non-trivial task to capture insights that would otherwise be lost.
AGENTS.md and agent_docs/building_the_project.md).AGENTS.md + agent_docs/AVAILABLE_SKILLS.md when adding skills).Place learnings in the most specific AGENTS.md file:
AGENTS.md.scripts/AGENTS.md..agents/skills/<name>/AGENTS.md.Every new non-obvious insight must be recorded in two places:
LESSON-NNN entry to agent_docs/LESSONS.md with Issue/Root Cause/Solution.AGENTS.md (this is what learn automates).If agent_docs/LESSONS.md does not exist yet, create it before relying on the dual-write workflow.
AGENTS.md.MAX_LINES_AGENTS_MD=150 constraint.agent_docs/LESSONS.md - Project-wide lessons log.AGENTS.md - Root agent guidance and constraints.agent_docs/README.md - Index of workflow-impacting reference files.