Reflect

haddock-development/reflect

> Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect or automatically at session end when enabled.

35k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

208

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/haddock-development/claude-reflect-system --skill reflect

What comes with it

135 282 bytes besides the instruction

.state/auto-reflection.json

.state/last-reflection.timestamp

README.md

USER_GUIDE.md

commands/reflect-meta.md

commands/reflect-promote.md

commands/reflect-stats.md

references/signal-patterns.md

scripts/extract_signals.py

scripts/hook-stop.sh

scripts/learning_ledger.py

scripts/meta_learning.py

scripts/present_review.py

scripts/promote_learning.py

scripts/reflect.py

scripts/scope_analyzer.py

scripts/semantic_detector.py

scripts/toggle-off.sh

scripts/toggle-on.sh

scripts/toggle-status.sh

scripts/update_skill.py

The instruction itself

13 sections, as written by the author

Reflect - Self-Improving Skills

Overview

This skill enables Claude Code to learn from conversations by analyzing corrections,

approvals, and patterns, then proposing updates to relevant skills. It implements

a "correct once, never again" learning system.

Usage Modes

1. Manual Reflection (/reflect)

Trigger analysis of the current conversation:

/reflect [skill-name]

Without skill-name: Analyzes all skills used in conversation
With skill-name: Focuses on specific skill

2. Automatic Reflection

When enabled via /reflect-on, runs automatically at session end via Stop hook.

3. Toggle Commands

/reflect-on - Enable automatic reflection
/reflect-off - Disable automatic reflection
/reflect-status - Show current configuration

Confidence Levels

HIGH - Explicit corrections:

User contradicts Claude's approach with specific alternative
Pattern: "Don't do X, do Y instead"
Action: Direct updates with deprecation warnings

MEDIUM - Approvals and patterns:

User approves specific approach
Pattern succeeds multiple times
Action: Add to "Best Practices" section

LOW - Observations:

User questions or suggests alternatives
Pattern: "Have you considered..." or "Why not try..."
Action: Add to "Considerations" section

Workflow

Signal Detection - Scan transcript for corrections/patterns
Context Analysis - Extract 5-message context around signals
Skill Mapping - Match signals to relevant skills
Change Proposal - Generate diff of proposed updates
User Review - Interactive approval with natural language editing
Application - Safe YAML/markdown updates with backups
Git Commit - Automatic commit with descriptive message

Scripts

Core Engine

scripts/reflect.py - Main orchestration logic
scripts/extract_signals.py - Pattern detection engine
scripts/update_skill.py - Safe skill file updates
scripts/present_review.py - Interactive review interface

Automation

scripts/hook-stop.sh - Stop hook integration
scripts/toggle-on.sh - Enable auto-reflection
scripts/toggle-off.sh - Disable auto-reflection
scripts/toggle-status.sh - Show status

Safety Features

Timestamped backups before all edits
YAML validation before writing
Lock files prevent concurrent runs
Graceful error handling with rollback
Git status checks before commits

References

See references/signal-patterns.md for detailed pattern library.

How to use it

Copy the folder

Take haddock-development/reflect from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.