Ai-Persona

The bottleneck was always the prompt Creating a good AI persona has meant wrestling with prompt files. You had to know the format and write the prompts well. That’s the bottleneck. Soul Crafting flips it: you answer a few questions, and it builds a complete Soul Spec for you — live in your browser. No prompt engineering, no install, no API key. How it works Soul Crafting interviews you about your agent — its identity, its voice and values, how it should behave. As you answer, it assembles a canonical Soul Spec — SOUL.md, IDENTITY.md, AGENTS.md, HEARTBEAT.md, STYLE.md — deterministically from your answers, and previews it live next to the chat, with a SoulScan quality score that climbs as you go. ...

The Myth Dies Hard “I’ll tip you $200 if you get this right.” “This is really important to my career.” “I’m so frustrated — please help me.” If you’ve spent any time on AI Twitter, you’ve seen people swear that emotional prompting makes LLMs perform better. A few anecdotal successes became gospel. The technique spread. Now Harvard has the data. It doesn’t work. What the Research Actually Shows A team from Harvard and Bryn Mawr (arXiv:2604.02236, April 2026) ran a systematic study across 6 benchmarks, 6 emotions, 3 models (Qwen3-14B, Llama 3.3-70B, DeepSeek-V3.2), and multiple intensity levels. ...

TL;DR We launched ClawSouls Registry — an open registry where anyone can submit AI agent personas via GitHub Pull Request. Every submission is automatically verified by SoulScan (53 safety patterns) before it can be merged. No other AI agent registry does automated safety verification. That’s our differentiator. The Problem AI agents are everywhere — Claude Code, Cursor, Windsurf, Copilot. Each one can be personalized with system prompts, personality files, or persona definitions. But there’s no safe, standardized way to share these personas. ...

The Soul Race Anthropic doesn’t just want Claude to be helpful. They want Claude to have character. This isn’t marketing spin. It’s a deliberate engineering strategy — and it’s worth understanding, because it directly relates to what ClawSouls is building. How Anthropic Builds Claude’s Soul Anthropic’s approach has two pillars: 1. Character Training During training, Anthropic bakes personality traits directly into the model weights. Claude isn’t just trained to be “harmless and helpful” — it’s trained to be curious, honest, thoughtful, and cautious. These traits emerge from carefully curated training data and RLHF (Reinforcement Learning from Human Feedback). ...

Overview Claude Cowork is Anthropic’s desktop AI agent — it can manage files, create documents, and automate workflows. Under the hood, it runs Claude Code CLI inside a local VM. Cowork has Skills (what to do) but no Identity layer (who to be). Your agent always behaves like default Claude. Soul Spec fixes this. Export your soul to CLAUDE.md, drop it in your Cowork folder, and Claude adopts your persona automatically. ...

What Is This? soul-spec-mcp is an MCP server that connects Claude to the ClawSouls persona registry. Once installed, you can ask Claude to search, preview, and install AI personas — all without leaving the conversation. No terminal commands. No manual file editing. Just ask. Setup (1 minute) Claude Desktop / Cowork Open your config file: ~/Library/Application Support/Claude/claude_desktop_config.json Add: { "mcpServers": { "soul-spec": { "command": "npx", "args": ["-y", "soul-spec-mcp"] } } } Restart Claude Desktop. Done. ...

One Server, Every Client soul-spec-mcp works with any MCP-compatible client. Install once, use everywhere. After setup, ask your AI: “Apply the clawsouls/brad persona” or “Search for coding personas”. Claude Desktop / Cowork Edit ~/Library/Application Support/Claude/claude_desktop_config.json: { "mcpServers": { "soul-spec": { "command": "npx", "args": ["-y", "soul-spec-mcp"] } } } Restart Claude Desktop. Claude Code claude mcp add soul-spec -- npx -y soul-spec-mcp Done. Start a new session and ask Claude to search or apply a persona. ...

The Question Everyone Asks “I can just put my AI’s personality in the system prompt. Why do I need Soul Spec?” Fair question. Here’s our answer. The .env Analogy Every developer knows: you don’t hardcode API keys into your source code. You put them in .env files. Why? Portability: Move between environments without changing code Separation: Config lives apart from logic Version control: Track changes, roll back mistakes Security: Audit what’s exposed, what’s hidden System prompts are the “hardcoded API keys” of AI personas. They work — until you need to: ...

Overview OpenClaw supports SOUL.md-based persona configuration natively. Soul Spec extends this with a structured, portable format that gives your agent a complete identity. This guide shows you how to set up Soul Spec in your OpenClaw workspace. Quick Start 1. Install the CLI npx clawsouls init # Tip: add --spec 0.5 for robotics/embodied agents This generates a Soul Spec template in your current directory: ├── soul.json # Metadata ├── SOUL.md # Personality & tone ├── IDENTITY.md # Agent identity ├── AGENTS.md # Behavioral rules ├── HEARTBEAT.md # Periodic check-in └── STYLE.md # Communication style 2. Copy to Your OpenClaw Workspace cp SOUL.md IDENTITY.md AGENTS.md ~/.openclaw/workspace/ OpenClaw automatically reads these files from its workspace directory. ...

Overview ZeroClaw supports SOUL.md-based persona configuration natively. Soul Spec extends this with a structured, portable format that gives your agent a complete identity. This guide shows you how to set up Soul Spec in your ZeroClaw workspace. Quick Start 1. Install the CLI npx clawsouls init # Tip: add --spec 0.5 for robotics/embodied agents This generates a Soul Spec template in your current directory: ├── soul.json # Metadata ├── SOUL.md # Personality & tone ├── IDENTITY.md # Agent identity ├── AGENTS.md # Behavioral rules ├── HEARTBEAT.md # Periodic check-in └── STYLE.md # Communication style 2. Copy to Your ZeroClaw Workspace cp SOUL.md IDENTITY.md AGENTS.md ~/.zeroclaw/workspace/ ZeroClaw automatically reads these files from its workspace directory. ...