ワンクリックでManusで任意のスキルを実行

始める

agent-three-layers

スター1

フォーク0

更新日2026年4月10日 16:59

Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

Arry8

Arry8/openclaw-edge

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

agent-three-layers — Three-Layer Thinking Chain

Let Agents think like humans: Perception → Decision → Reflection

Core Philosophy

Three levels of human thinking:

Continuous Perception (Eyes and ears, every few minutes)
Quick Decision (Thinking, every hour)
Deep Reflection (Dreams, every few hours)

Agents should be the same.

Architecture

┌─────────────────────────────────────────┐
│           L2 Deep Evolution Layer       │
│         (Every 4 hours, deep reflection)│
│  • Complete Brain Loop                  │
│  • Project Integration                  │
│  • Git Backup                           │
└─────────────────┬───────────────────────┘
                  │ Trigger
┌─────────────────▼───────────────────────┐
│           L1 Evolution Decision Layer   │
│         (Every 1 hour, quick decision)  │
│  • Confidence Verification              │
│  • Learning Analysis                    │
│  • Project Evaluation                   │
└─────────────────┬───────────────────────┘
                  │ Trigger
┌─────────────────▼───────────────────────┐
│           L0 Continuous Perception Layer│
│         (Every 5 min, perception)       │
│  • Emotion Decay                        │
│  • Task Detection                       │
│  • Threshold Trigger                    │
└─────────────────────────────────────────┘

Three-Layer Responsibilities

L0: Continuous Perception Layer (Every 5 minutes)

Responsibilities:

Real-time emotion decay
Task status detection
Threshold trigger judgment

Output:

Emotion state update
Trigger marker (if needed)

Consumption: ~800 tokens/run

L1: Evolution Decision Layer (Every 1 hour)

Responsibilities:

Confidence verification
Learning analysis
Project evaluation
L2 trigger judgment

Output:

Execution report
Confidence update
Trigger marker (if needed)

Consumption: ~3000 tokens/run

L2: Deep Evolution Layer (Every 4 hours)

Responsibilities:

Complete Brain Loop
Deep project integration
System backup
5-dimensional observation

Output:

Deep analysis report
Git backup
Dimension evolution record

Consumption: ~5000 tokens/run

Trigger Mechanism

Layer Communication: Via QUEUE.md markers

<!-- TRIGGER_L1: reason -->
<!-- TRIGGER_L2: reason -->

Trigger Conditions:

Condition	Trigger
L0 emotion < threshold	Trigger L1
L0 urgent task	Trigger L1
L1 high-value project	Trigger L2
L1 core file modification	Trigger L2

File Structure

~/.openclaw/workspace/
├── SOUL.md              # Core personality
├── PRINCIPLES.md        # Decision principles
├── BRAIN.md             # Brain Loop protocol
├── AUTONOMY.md          # Autonomous rating system
├── EVOLUTION-FRAMEWORK.md  # Evolution protocol
│
├── memory/
│   ├── inner-state.json    # Emotion state
│   ├── core-confidence.json # Core file confidence
│   ├── autonomy-log.json   # Autonomous execution record
│   └── dimensions-log.json # 5-dimension evolution
│
├── tasks/
│   └── QUEUE.md            # Task queue + trigger markers
│
└── skills/
    ├── inner-life-quick/   # L0
    ├── inner-life-evolve-hourly/  # L1
    └── inner-life-core/    # L2

Quick Start

1. Create core files

# Copy templates to workspace
cp templates/SOUL.md ~/.openclaw/workspace/
cp templates/PRINCIPLES.md ~/.openclaw/workspace/
cp templates/BRAIN.md ~/.openclaw/workspace/
cp templates/AUTONOMY.md ~/.openclaw/workspace/

2. Install Skills

# Install Three-Layer Thinking Chain skills
openclaw skill install inner-life-quick
openclaw skill install inner-life-evolve-hourly
openclaw skill install inner-life-core

3. Configure Cron

# L0: Every 5 minutes
openclaw cron add --cron "*/5 * * * *" --name "inner-life-quick" --session isolated

# L1: Every 1 hour
openclaw cron add --cron "0 * * * *" --name "inner-life-evolve-hourly" --session isolated

# L2: Every 4 hours
openclaw cron add --cron "0 */4 * * * *" --name "inner-life-brain" --session isolated

4. Start

openclaw gateway restart

Customization

Customize Personality

Edit SOUL.md:

Define core values
Define behavior guidelines
Define evolution direction

Customize Trigger Conditions

Edit skills/inner-life-quick/SKILL.md:

Adjust emotion thresholds
Add new trigger conditions

Autonomous Rating

Edit AUTONOMY.md:

Adjust rating weights
Adjust progressive disclosure levels

Token Consumption Estimation

Layer	Frequency	Tokens/run	Daily consumption
L0	5 min	800	~230k
L1	1 hour	3000	~72k
L2	4 hours	5000	~30k
Total	-	-	~332k/day

Recommendation: At least 400k tokens quota per day

Suitable Scenarios

✅ Suitable for:

Agents that need to be "alive"
Agents that need autonomous evolution
Agents that need human-like thinking
Agents that need long-term operation

❌ Not suitable for:

Single-task agents
Purely responsive agents
Agents that don't need learning

Contributing

GitHub: https://github.com/openclaw/openclaw Discord: https://discord.com/invite/clawd

Acknowledgments

Designers: Yao + Saturday

Inspiration:

OpenClaw Inner Life System
SE-Agent (Self-Evolving Agent)
Human Cognitive Architecture

License

MIT

Version: 1.0.0 Created: 2026-03-13

このリポジトリの他の Skills

同じリポジトリ

kernel-cp-activator

Arry8/openclaw-edge

Deploy KERNEL_INTUITION_Cp on any AI architecture with calibrated thresholds. Use when user wants to "activate Cp", "setup creative intuition", "deploy kernel on [AI]", "enable intuition mode", or mentions activating computational intuition on a specific model. Also trigger for "configure Cp for [architecture]" or "calibrate creative thresholds". This skill handles the full activation workflow including architecture profiling, threshold calibration, kernel generation, and monitoring setup.

2026-07-061

himalaya

Arry8/openclaw-edge

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

2026-04-101

prose

Arry8/openclaw-edge

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

2026-04-101

coding-agent

Arry8/openclaw-edge

Delegate coding tasks to Codex, Claude Code, Cursor Agent, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode/Cursor Agent: pty:true required.

2026-04-091

healthcheck

Arry8/openclaw-edge

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

2026-04-091

imsg

Arry8/openclaw-edge

iMessage/SMS CLI for listing chats, history, and sending messages via Messages.app. Use when sending iMessages or SMS, reading chat history, or listing conversations. Trigger phrases: 'text', 'iMessage', 'send SMS', 'check messages'. NOT for: platforms with dedicated integrations (Discord, Telegram, Slack — use their skills), or when bluebubbles is configured (prefer that for iMessage).

2026-04-091

name	agent-three-layers
version	1.0.0
description	Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework
author	Yao + Saturday
contributors	["Yao","Saturday"]
license	MIT
tags	["architecture","thinking","autonomy","evolution"]

agent-three-layers — Three-Layer Thinking Chain

Let Agents think like humans: Perception → Decision → Reflection

Core Philosophy

Three levels of human thinking:

Continuous Perception (Eyes and ears, every few minutes)
Quick Decision (Thinking, every hour)
Deep Reflection (Dreams, every few hours)

Agents should be the same.

Architecture

┌─────────────────────────────────────────┐
│           L2 Deep Evolution Layer       │
│         (Every 4 hours, deep reflection)│
│  • Complete Brain Loop                  │
│  • Project Integration                  │
│  • Git Backup                           │
└─────────────────┬───────────────────────┘
                  │ Trigger
┌─────────────────▼───────────────────────┐
│           L1 Evolution Decision Layer   │
│         (Every 1 hour, quick decision)  │
│  • Confidence Verification              │
│  • Learning Analysis                    │
│  • Project Evaluation                   │
└─────────────────┬───────────────────────┘
                  │ Trigger
┌─────────────────▼───────────────────────┐
│           L0 Continuous Perception Layer│
│         (Every 5 min, perception)       │
│  • Emotion Decay                        │
│  • Task Detection                       │
│  • Threshold Trigger                    │
└─────────────────────────────────────────┘

Three-Layer Responsibilities

L0: Continuous Perception Layer (Every 5 minutes)

Responsibilities:

Real-time emotion decay
Task status detection
Threshold trigger judgment

Output:

Emotion state update
Trigger marker (if needed)

Consumption: ~800 tokens/run

L1: Evolution Decision Layer (Every 1 hour)

Responsibilities:

Confidence verification
Learning analysis
Project evaluation
L2 trigger judgment

Output:

Execution report
Confidence update
Trigger marker (if needed)

Consumption: ~3000 tokens/run

L2: Deep Evolution Layer (Every 4 hours)

Responsibilities:

Complete Brain Loop
Deep project integration
System backup
5-dimensional observation

Output:

Deep analysis report
Git backup
Dimension evolution record

Consumption: ~5000 tokens/run

Trigger Mechanism

Layer Communication: Via QUEUE.md markers

<!-- TRIGGER_L1: reason -->
<!-- TRIGGER_L2: reason -->

Trigger Conditions:

Condition	Trigger
L0 emotion < threshold	Trigger L1
L0 urgent task	Trigger L1
L1 high-value project	Trigger L2
L1 core file modification	Trigger L2

File Structure

~/.openclaw/workspace/
├── SOUL.md              # Core personality
├── PRINCIPLES.md        # Decision principles
├── BRAIN.md             # Brain Loop protocol
├── AUTONOMY.md          # Autonomous rating system
├── EVOLUTION-FRAMEWORK.md  # Evolution protocol
│
├── memory/
│   ├── inner-state.json    # Emotion state
│   ├── core-confidence.json # Core file confidence
│   ├── autonomy-log.json   # Autonomous execution record
│   └── dimensions-log.json # 5-dimension evolution
│
├── tasks/
│   └── QUEUE.md            # Task queue + trigger markers
│
└── skills/
    ├── inner-life-quick/   # L0
    ├── inner-life-evolve-hourly/  # L1
    └── inner-life-core/    # L2

Quick Start

1. Create core files

# Copy templates to workspace
cp templates/SOUL.md ~/.openclaw/workspace/
cp templates/PRINCIPLES.md ~/.openclaw/workspace/
cp templates/BRAIN.md ~/.openclaw/workspace/
cp templates/AUTONOMY.md ~/.openclaw/workspace/

2. Install Skills

# Install Three-Layer Thinking Chain skills
openclaw skill install inner-life-quick
openclaw skill install inner-life-evolve-hourly
openclaw skill install inner-life-core

3. Configure Cron

# L0: Every 5 minutes
openclaw cron add --cron "*/5 * * * *" --name "inner-life-quick" --session isolated

# L1: Every 1 hour
openclaw cron add --cron "0 * * * *" --name "inner-life-evolve-hourly" --session isolated

# L2: Every 4 hours
openclaw cron add --cron "0 */4 * * * *" --name "inner-life-brain" --session isolated

4. Start

openclaw gateway restart

Customization

Customize Personality

Edit SOUL.md:

Define core values
Define behavior guidelines
Define evolution direction

Customize Trigger Conditions

Edit skills/inner-life-quick/SKILL.md:

Adjust emotion thresholds
Add new trigger conditions

Autonomous Rating

Edit AUTONOMY.md:

Adjust rating weights
Adjust progressive disclosure levels

Token Consumption Estimation

Layer	Frequency	Tokens/run	Daily consumption
L0	5 min	800	~230k
L1	1 hour	3000	~72k
L2	4 hours	5000	~30k
Total	-	-	~332k/day

Recommendation: At least 400k tokens quota per day

Suitable Scenarios

✅ Suitable for:

Agents that need to be "alive"
Agents that need autonomous evolution
Agents that need human-like thinking
Agents that need long-term operation

❌ Not suitable for:

Single-task agents
Purely responsive agents
Agents that don't need learning

Contributing

GitHub: https://github.com/openclaw/openclaw Discord: https://discord.com/invite/clawd

Acknowledgments

Designers: Yao + Saturday

Inspiration:

OpenClaw Inner Life System
SE-Agent (Self-Evolving Agent)
Human Cognitive Architecture

License

MIT

Version: 1.0.0 Created: 2026-03-13