dojo.md
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
three dimensional memory
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install amlyx/three-dimensional-memoryInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Three-Dimensional Memory System for AI Assistants — 人类思维方式的文件记忆管理
A memory management system that mirrors human cognition: organized by time, conversation, and topics.
Traditional file management organizes by file type (docs, images, videos). Humans don't think that way.
Humans remember:
This skill creates a three-dimensional memory space for AI assistants and their users.
memory/
├── 2026-02-21.md ← What happened today
├── 2026-02-22.md ← What happened today
└── 2026-02-23.md ← What happened today
Purpose: Daily work logs, chronological record of events
Update frequency: Daily
Content: Tasks completed, decisions made, meetings held
AI-memory-backup/
├── backup-20260221.md ← Complete conversation transcript
├── backup-20260222.md ← Complete conversation transcript
└── backup-20260223.md ← Complete conversation transcript
Purpose: Full context preservation, searchable dialogue history
Update frequency: Per conversation
Content: Every word exchanged, including user messages and AI responses
topic-memory/
├── project-product-launch/
│ ├── proposal-v1.md
│ ├── proposal-v2.md
│ └── final-version.md
│
├── decision-org-restructure/
│ ├── options-considered.md
│ ├── final-decision.md
│ └── implementation-plan.md
│
└── knowledge-market-analysis/
├── competitor-research.md
└── trend-report.md
Purpose: Project-centric information aggregation
Update frequency: As projects evolve
Content: All documents, decisions, and knowledge related to a specific topic
workspace/
│
├── memory/ ← Dim...
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
Find any file in 10 seconds. Guaranteed.
A revolutionary approach to memory management that mirrors how humans actually think and remember.
Traditional file systems:
📁 Documents/
📄 report.pdf
📄 presentation.pptx
📁 Images/
🖼️ screenshot.png
📁 Other/
❓ Where did I save that important thing?
You: "Where's that pricing strategy we discussed last week?"
Traditional: [5 minutes of searching...] "Found it in Documents/Projects/2026/Q1/Pricing/Final/"
Three-Dimensional Memory:
memory/ ← WHEN
2026-02-21.md "Product strategy meeting"
2026-02-22.md "Drafted pricing proposal"
2026-02-23.md "Finalized three-tier model"
AI-memory-backup/ ← WHAT WAS SAID
backup-20260221.md "Let's consider three tiers..."
backup-20260222.md "$29 might signal cheap..."
backup-20260223.md "Final decision: $39, $99, $299"
topic-memory/ ← WHAT IT'S ABOUT
project-product-launch/
pricing-strategy.md
timeline.md
key-decisions.md
You: "Where's that pricing strategy?"
3D Memory: "You mean the one from Wednesday's meeting? It's in topic-memory/project-product-launch/pricing-strategy.md"
Time to find: 10 seconds ⏱️
clawhub install three-dimensional-memory
# Initialize the structure
memory-init
# Create today's log
memory-daily "Shipped v2.0, fixed 3 critical bugs"
# Start a new project
memory-project "Q3-Roadmap" --status "planning"
# Search all dimensions
memory-search "pricing"
"现在的机构找文件很好找,用的很顺手"
— Early adopter, 2026
Humans remember when things happened.
Your AI writes a daily work log:
Humans remember what was said.
Complete conversation tran...
# three-dimensional-memory
**Three-Dimensional Memory System for AI Assistants** — 人类思维方式的文件记忆管理
A memory management system that mirrors human cognition: organized by time, conversation, and topics.
---
## 🎯 Why This Skill?
Traditional file management organizes by file type (docs, images, videos). Humans don't think that way.
Humans remember:
- **When** it happened (time)
- **What was said** (conversation)
- **What it was about** (topic)
This skill creates a three-dimensional memory space for AI assistants and their users.
---
## 🧠 The Three Dimensions
### Dimension 1: Timeline Memory
```
memory/
├── 2026-02-21.md ← What happened today
├── 2026-02-22.md ← What happened today
└── 2026-02-23.md ← What happened today
```
**Purpose**: Daily work logs, chronological record of events
**Update frequency**: Daily
**Content**: Tasks completed, decisions made, meetings held
---
### Dimension 2: Conversation Stream
```
AI-memory-backup/
├── backup-20260221.md ← Complete conversation transcript
├── backup-20260222.md ← Complete conversation transcript
└── backup-20260223.md ← Complete conversation transcript
```
**Purpose**: Full context preservation, searchable dialogue history
**Update frequency**: Per conversation
**Content**: Every word exchanged, including user messages and AI responses
---
### Dimension 3: Topic Network
```
topic-memory/
├── project-product-launch/
│ ├── proposal-v1.md
│ ├── proposal-v2.md
│ └── final-version.md
│
├── decision-org-restructure/
│ ├── options-considered.md
│ ├── final-decision.md
│ └── implementation-plan.md
│
└── knowledge-market-analysis/
├── competitor-research.md
└── trend-report.md
```
**Purpose**: Project-centric information aggregation
**Update frequency**: As projects evolve
**Content**: All documents, decisions, and knowledge related to a specific topic
---
## 📁 Recommended File Structure
```
workspace/
│
├── memory/ ← Dim...# Three-Dimensional Memory System
> **Find any file in 10 seconds. Guaranteed.**
A revolutionary approach to memory management that mirrors how humans actually think and remember.
## The Problem
```
Traditional file systems:
📁 Documents/
📄 report.pdf
📄 presentation.pptx
📁 Images/
🖼️ screenshot.png
📁 Other/
❓ Where did I save that important thing?
```
**You**: "Where's that pricing strategy we discussed last week?"
**Traditional**: [5 minutes of searching...] "Found it in Documents/Projects/2026/Q1/Pricing/Final/"
## The Solution
```
Three-Dimensional Memory:
memory/ ← WHEN
2026-02-21.md "Product strategy meeting"
2026-02-22.md "Drafted pricing proposal"
2026-02-23.md "Finalized three-tier model"
AI-memory-backup/ ← WHAT WAS SAID
backup-20260221.md "Let's consider three tiers..."
backup-20260222.md "$29 might signal cheap..."
backup-20260223.md "Final decision: $39, $99, $299"
topic-memory/ ← WHAT IT'S ABOUT
project-product-launch/
pricing-strategy.md
timeline.md
key-decisions.md
```
**You**: "Where's that pricing strategy?"
**3D Memory**: "You mean the one from Wednesday's meeting? It's in `topic-memory/project-product-launch/pricing-strategy.md`"
**Time to find**: 10 seconds ⏱️
## Installation
```bash
clawhub install three-dimensional-memory
```
## Quick Start
```bash
# Initialize the structure
memory-init
# Create today's log
memory-daily "Shipped v2.0, fixed 3 critical bugs"
# Start a new project
memory-project "Q3-Roadmap" --status "planning"
# Search all dimensions
memory-search "pricing"
```
## Real User Testimonials
> "现在的机构找文件很好找,用的很顺手"
> — Early adopter, 2026
## How It Works
### Dimension 1: Timeline
Humans remember **when** things happened.
Your AI writes a daily work log:
- What was done
- Decisions made
- Meetings held
### Dimension 2: Conversation
Humans remember **what was said**.
Complete conversation tran...University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
A股分析技能
A2A4B2B Skill for OpenClaw