update-agent-learnings
OfficialStandardize and propagate session learnings.
Authorulpi-io
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Session learnings often remain siloed across agents, making it hard to uniformly improve behavior. This skill extracts patterns, mistakes, or insights from conversations and propagates them to the central learnings repository and the appropriate agent files based on scope (Global, Claude Code Only, or Agent-Specific).
Core Features & Use Cases
- Centralized capture and categorization of learnings into global and agent-specific sections.
- Automated propagation to
.claude/learnings/agent-learnings.mdand per-agent files to ensure alignment across subagents. - Phase-driven workflow including session analysis, learning extraction, central update, and agent file synchronization.
Quick Start
Run the update process after a challenging session to extract actionable learnings and propagate them to central and agent-specific files.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: update-agent-learnings Download link: https://github.com/ulpi-io/browse/archive/main.zip#update-agent-learnings Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.