Show HN：Claude Reflect - 自動將 Claude 的修正轉換為專案設定

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

License

Uh oh!

There was an error while loading. Please reload this page.

BayramAnnakov/claude-reflect

Folders and files

Latest commit

History

Repository files navigation

claude-reflect

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

What it does

When you correct Claude Code during a session ("no, use gpt-5.1 not gpt-5", "use database for caching"), these corrections are captured and can be added to your CLAUDE.md files so Claude remembers them in future sessions.

Installation

After installation, restart Claude Code (exit and reopen). Then hooks auto-configure and commands are ready.

First run? When you run /reflect for the first time, you'll be prompted to scan your past sessions for learnings.

Prerequisites

Commands

How It Works

Two-Stage Process

Stage 1: Capture (Automatic)

Hooks run automatically to detect and queue corrections:

Stage 2: Process (Manual)

Run /reflect to review and apply queued learnings to CLAUDE.md.

Pattern Detection

The capture hook detects corrections AND positive feedback:

Corrections (what went wrong):

Positive patterns (what works):

Explicit markers:

Each captured learning has a confidence score (0.60-0.95) based on pattern strength. Higher confidence = more likely to be a real learning.

Human Review

When you run /reflect, Claude presents a summary table:

You choose:

Multi-Target Sync

Approved learnings are synced to:

Run /reflect --targets to see which files will be updated.

Uninstall

File Structure

Features

Historical Scan

First time using claude-reflect? Run:

This scans all your past sessions for corrections you made, so you don't lose learnings from before installation.

Smart Filtering

Claude filters out:

Only reusable learnings are kept.

Duplicate Detection

Before adding a learning, existing CLAUDE.md content is checked. If similar content exists, you can:

Semantic Deduplication

Over time, CLAUDE.md can accumulate similar entries. Run /reflect --dedupe to:

Example:

Tips

Use explicit markers for important learnings:

Run /reflect after git commits - The hook reminds you, but make it a habit

Historical scan on new machines - When setting up a new dev environment:

Project vs Global - Model names and general patterns go global; project-specific conventions stay in project CLAUDE.md

Contributing

Pull requests welcome! Please read the contributing guidelines first.

License

MIT

About

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

Topics

Resources

License

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

  1

Packages

  0

Contributors

  2

Languages

Footer

Footer navigation