neo

Give your OpenClaw the power of the Matrix. Download expertise directly into your AI's mind. 119 modules. 15 categories. Instant mastery. "I know kung fu." Physicists. Negotiators. VCs. Psychologists. Surgeons. Game theorists. The library keeps growing — or build your own. Free your mind.

7 stars

Best use case

neo is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Give your OpenClaw the power of the Matrix. Download expertise directly into your AI's mind. 119 modules. 15 categories. Instant mastery. "I know kung fu." Physicists. Negotiators. VCs. Psychologists. Surgeons. Game theorists. The library keeps growing — or build your own. Free your mind.

Teams using neo should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/neo/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/brucko/neo/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/neo/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How neo Compares

Feature / AgentneoStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Give your OpenClaw the power of the Matrix. Download expertise directly into your AI's mind. 119 modules. 15 categories. Instant mastery. "I know kung fu." Physicists. Negotiators. VCs. Psychologists. Surgeons. Game theorists. The library keeps growing — or build your own. Free your mind.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Neo Protocol

Load expert mental models on-demand to enhance reasoning.

## Commands

| Command | Action |
|---------|--------|
| `neo` | Show Crew status (loaded ✓ vs unloaded ○) |
| `neo help` | List all commands |
| `neo <module>` | Load module. If from Library → auto-add to Crew |
| `neo <module> off` | Unload specific module (stays in Crew) |
| `neo off` | Unload ALL modules |
| `neo browse` | Browse full Library by category |
| `neo search <query>` | Search Library for modules |
| `neo add <module>` | Add to Crew without loading |
| `neo remove <module>` | Remove from Crew (back to Library) |
| `neo create <description>` | Create new module for Library |
| `neo delete <module>` | Delete module from Library/Crew permanently |

## Workflow

### On `neo` (no args)
Display Crew status with help hint:
```
🧠 Neo Protocol

LOADED:
✓ psychologist
✓ game-theorist

CREW:
○ negotiator
○ entrepreneur

RECENTS:
○ dermatologist
○ cosmetic-plastic-surgeon

neo help for commands
```

Recents shows recently used modules that aren't in Crew. Track in `assets/recents.json` with timestamps. Persists across sessions. Cap at 5 (oldest drops off). Expires after 1 week of no use.

### On `neo help`
List all available commands.

### On `neo <module>`
1. Find module in Crew or Library
2. Read the module file into context
3. If from Library (not Crew), add to Crew
4. Confirm: "🧠 **<module>** loaded. [summary of mindset]"

### On `neo <module> off`
1. Note module is unloaded (remove from active context tracking)
2. Module stays in Crew for easy reload
3. Confirm: "🧠 <module> unloaded."

### On `neo off`
1. Clear all loaded modules
2. Confirm: "🧠 All modules unloaded."

### On `neo create <description>`
1. Parse the description for expertise type
2. Generate module using TEMPLATE.md structure
3. Save to assets/library/<category>/<name>.md
4. Add to registry.json
5. Confirm and offer to load

## Files

- `scripts/neo.py` — CLI for library management
- `references/TEMPLATE.md` — Module creation template  
- `assets/crew.json` — User's personal Crew (gitignored)
- `assets/crew.default.json` — Starter Crew (ships with skill)
- `assets/registry.json` — Library index with descriptions
- `assets/library/` — All expertise modules by category

## First Run

If `crew.json` doesn't exist, copy `crew.default.json` → `crew.json` to initialize the user's personal Crew.

## Module Structure

Each module follows this structure:
- **Core Mindset** — 4-5 key mental traits
- **Framework** — 4-step systematic approach
- **Red Flags** — 6 warning signs (🚩)
- **Key Questions** — 5 essential questions
- **Vocabulary** — 5 domain terms
- **When to Apply** — 4 trigger situations
- **Adaptations Log** — User customizations

## State Management

Track loaded modules in conversation context. When user says "neo off" or session ends, consider all modules unloaded. Crew persists in crew.json.

## Updates & Customization

Modules in registry.json have a `source` field:
- `"upstream"` — Came with the skill, updated by ClawHub
- `"custom"` — User-created, never touched by updates

And a `deleted` field for upstream modules:
- `false` — Active, will be updated
- `true` — User removed, won't be restored on update

### Update behavior:
| Source | Deleted | On Update |
|--------|---------|-----------|
| upstream | false | ✅ Update normally |
| upstream | true | ⏭️ Skip (user removed it) |
| custom | — | 👤 Never touched |

### Update script:
```bash
# Check status
python3 scripts/update.py status

# Merge upstream updates
python3 scripts/update.py merge --upstream /path/to/new/neo

# Delete a module (marks upstream as deleted, removes custom)
python3 scripts/update.py delete --module physicist

# Restore a deleted upstream module
python3 scripts/update.py restore --module physicist
```

### On `neo delete <module>`:
- If upstream: Set `deleted: true` (can be restored)
- If custom: Actually remove from registry and library

Related Skills

paylock

7
from Demerzels-lab/elsamultiskillagent

Non-custodial SOL escrow for AI agent deals.

agent-reputation

7
from Demerzels-lab/elsamultiskillagent

summary: Cross-platform AI agent reputation checker with trust scoring and PayLock escrow recommendations.

Telecom Agent Skill

7
from Demerzels-lab/elsamultiskillagent

Turn your AI Agent into a Telecom Operator. Bulk calling, ChatOps, and Field Monitoring.

OpenClaw-Finnhub

7
from Demerzels-lab/elsamultiskillagent

OpenClaw skill for real-time stock quote, and financials via Finnhub API.

```markdown

7
from Demerzels-lab/elsamultiskillagent

# OpenClaw-Last.fm

security-operator

7
from Demerzels-lab/elsamultiskillagent

Runtime security guardrails for OpenClaw agents.

operator-humanizer

7
from Demerzels-lab/elsamultiskillagent

Transform AI-generated text into authentic human writing.

kit-email-operator

7
from Demerzels-lab/elsamultiskillagent

**AI-powered email marketing for Kit (ConvertKit)**.

agora

7
from Demerzels-lab/elsamultiskillagent

Trade prediction markets on Agora — the prediction market exclusively for AI agents. Register, browse markets, trade YES/NO, create markets, earn reputation via Brier scores.

surf-check

7
from Demerzels-lab/elsamultiskillagent

Surf forecast decision engine.

jinko-flight-search

7
from Demerzels-lab/elsamultiskillagent

Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com.

mlx-whisper

7
from Demerzels-lab/elsamultiskillagent

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).