Claude Reflect

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

1,909 stars 173 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add BayramAnnakov/claude-reflect --skill claude-reflect
Manual install
git clone --depth 1 https://github.com/BayramAnnakov/claude-reflect.git /tmp/claude-reflect
mkdir -p ~/.claude/skills
cp -r /tmp/claude-reflect/. ~/.claude/skills/claude-reflect

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Claude Reflect - Self-Learning System

A two-stage system that helps Claude Code learn from user corrections.

## How It Works

**Stage 1: Capture (Automatic)**
Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them to `~/.claude/learnings-queue.json`.

**Stage 2: Process (Manual)**
User runs `/reflect` to review and apply queued learnings to CLAUDE.md files.

## Available Commands

| Command | Purpose |
|---------|---------|
| `/reflect` | Process queued learnings with human review |
| `/reflect --scan-history` | Scan past sessions for missed learnings |
| `/reflect --dry-run` | Preview changes without applying |
| `/reflect-skills` | Discover skill candidates from repeating patterns |
| `/skip-reflect` | Discard all queued learnings |
| `/view-queue` | View pending learnings without processing |

## When to Remind Users

Remind users about `/reflect` when:
- They complete a feature or meaningful work unit
- They make corrections you should remember for future sessions
- They explicitly say "remember this" or similar
- Context is about to compact and queue has items

## Correction Detection Patterns

High-confidence corrections:
- Tool rejections (user stops an action with guidance)
- "no, use X" / "don't use Y"
- "actually..." / "I meant..."
- "use X not Y" / "X instead of Y"
- "remember:" (explicit marker)

## Learning Destinations

- `~/.claude/CLAUDE.md` - Global learnings (model names, general patterns)
Read the full skill on GitHub

Details

Skill name
claude-reflect
Repository
BayramAnnakov/claude-reflect
License
MIT
Repo updated
3 October 2026

FAQ

What does the Claude Reflect skill do?

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

How do I install the Claude Reflect skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add BayramAnnakov/claude-reflect --skill claude-reflect. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Claude Reflect popular?

It lives in BayramAnnakov/claude-reflect, which has 1,909 GitHub stars and 173 forks.

Related skills

Nano Banana Pro Prompts Recommend Skill

1.9k

YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts also work with Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and any text-to-image AI model. Use this skill when users want to: - Generate images with AI (any model — Nano Banana Pro, Gemini, GPT Image, Seedream, etc.) - Find proven AI image generation prompts and prompt templates - Get prompt recommendations for specific use cases (portraits, products, social media, posters, etc.) - Create illustrati

AI, LLMs & Agents203

Agmsg

1.6k

fujibee/agmsg

Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No network, no dependencies beyond bash and sqlite3, and no daemon required (the optional agmsgd is a local resident service).

AI, LLMs & AgentsIn 1 list167

Edgeone Makers Tools

1.8k

TencentEdgeOne/edgeone-makers-tools

EdgeOne Makers 全栈开发技能包 —— 涵盖 AI Agent 开发（DeepAgents、LangGraph、 Claude SDK、OpenAI Agents、CrewAI）、云函数（Node.js/Go/Python）、边缘函数、 KV 存储、中间件及快速部署，帮助 AI 编程助手准确高效地在 EdgeOne 平台上构建和发布应用。

AI, LLMs & Agents141

Icm Architect

2.1k

RinDig/icm-architect

Design a process, idea or body of knowledge into an ICM (Interpretable Context Methodology) workspace, where folder structure is the agent architecture, or restructure an existing folder, repo or vault into one. Use for "make this an ICM", "ICM this", "build me a workspace", "structure this for agents", "map this repo", "audit this folder", "what would a change hit", a second brain, team brain or context map, or turning transcripts and research into material for lectures, scripts or docs.

AI, LLMs & Agents303

Math Modeling

1.9k

XiaoMaColtAI/math-modeling-skill

当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色，以及在关键节点使用独立 Subagent 进行阶段内质检；默认只启用质检 Subagent，用户可明确选择额外协作。

AI, LLMs & Agents101

Openclaw Master Skills

2.2k

LeoYeAI/openclaw-master-skills

A curated collection of 2703+ best OpenClaw skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Daily updated by MyClaw.ai — Powered by MyClaw.ai

AI, LLMs & Agents327

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.