reflect-learn

name	reflect-learn
description	Self-improvement through conversation analysis. Extracts learnings from corrections and success patterns, proposes updates to agent files or creates new skills. Philosophy: "Correct once, never again." Use when: (1) User explicitly corrects behavior ("never do X", "always Y"), (2) Session ending or context compaction, (3) User requests /reflect, (4) Successful pattern worth preserving.
zh_description	用于reflect、learn，支持检索、拆解、反思和决策。
version	2.0.0
author	Claude Code Toolkit
source	in-house
source_url
tags	["learn", "planning", "reflect", "workflow"]
created_at	2026-03-04
updated_at	2026-03-20
quality	5
complexity	intermediate
allowed-tools	null

Reflect - Self-Improvement Skill

Quick Reference

Command	Action
/reflect	Analyze conversation for learnings
/reflect on	Enable auto-reflection
/reflect off	Disable auto-reflection
/reflect status	Show state and metrics
/reflect review	Review low-confidence learnings
/reflect [agent]	Focus on specific agent

Core Philosophy

"Correct once, never again."

When users correct behavior, those corrections become permanent improvements encoded into the agent system - across all future sessions.

Workflow

Step 1: Initialize State

Check and initialize state files using the state manager:

# Check for existing state
python scripts/state_manager.py init

# State directory is configurable via REFLECT_STATE_DIR env var
# Default: ~/.reflect/ (portable) or ~/.claude/session/ (Claude Code)

State includes:

• reflect-state.yaml - Toggle state, pending reviews
• reflect-metrics.yaml - Aggregate metrics
• learnings.yaml - Log of all applied learnings

Step 2: Scan Conversation for Signals

Use the signal detector to identify learnings:

python scripts/signal_detector.py --input conversation.txt

Signal Confidence Levels

Confidence	Triggers	Examples
HIGH	Explicit corrections	"never", "always", "wrong", "stop", "the rule is"
MEDIUM	Approved approaches	"perfect", "exactly", accepted output
LOW	Observations	Patterns that worked, not validated