continuous-learning

Installation
SKILL.md

Default output: return only the result, blockers, and required evidence. Omit preambles, process narration, repeated context, confidence scores, and follow-up offers. Use at most five bullets unless a required artifact or schema needs more.

Continuous Learning

Overview

Learn from sessions in two complementary ways:

  1. Instinct-based learning — extract reusable patterns, score confidence, promote high-confidence instincts into skills.
  2. Workspace memory — delegate durable preferences and facts to the agents-memory-updater subagent (orchestration only in this skill).

When to Use

  • After completing a significant feature or fix (instincts)
  • When a session revealed a non-obvious solution worth remembering
  • Before starting similar work to apply learned instincts
  • When transcript deltas may update AGENTS.md (workspace memory)

Instinct Lifecycle

Installs
1
GitHub Stars
8
First Seen
Aug 17, 2026
continuous-learning — v1truv1us/ai-eng-system