Menu
Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.
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
| name | brain-learn |
| description | Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow. |
Use Agent Brain command /brain-learn.
This runtime wrapper is only an activation shortcut. The source of truth is commands/brain-learn.md and commands/registry.json.
Wrapper boundary marker: cc-source-of-truth.
Before acting:
AGENTBRAIN.md, PRINCIPLES.md, ANTI_RATIONALIZATION.md, and docs/state-machine.md.commands/brain-learn.md and follow it exactly.context-memory, learning-capture, wiki-maintenance.templates/learning-capture.md.none.If this wrapper conflicts with the command file or registry, follow the command file, report wrapper drift, and route the fix through /brain-verify.
User arguments: $ARGUMENTS
Agent Brain /brain-brief: after intake, research, and grill have enough signal.
Agent Brain /brain-build: an implementation plan has a selected task and validation method.
Agent Brain /brain-design: a product brief needs ux or interaction design before planning.
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Agent Brain /brain-plan: the brief/design is strong enough to implement.