Quick Start
Native Agent Install (Most Recommended)
The quickest way to install and configure everything is to give your AI agent (like Claude Code, Cursor, OpenCode, or OpenClaw) a single instruction. The agent will read the protocol and execute the entire setup autonomously in the background.
The simulation below uses the full POSIX implementation. On Windows, the
agent must stay within the windows-subset-v1 commands documented in the
manual-install step.
Copy this prompt and paste it into your AI Agent:
Read https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/SKILL.md and follow the instructions to set up Scoutica Protocol natively.🤖 AI Agent Simulation Log
Section titled “🤖 AI Agent Simulation Log”1. Step 1: Install CLI
- AI executes bash:
curl -fsSL https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/install.sh | bash - Terminal Output:
✅ Scoutica installed successfully.
2. Step 2: Locate files & Scan
- AI executes bash:
cd ~/CV && scoutica scan . - Terminal Output:
Creating dedicated card folder: ~/CV/john-doe-card
3. Step 3: Schema Validation
- AI executes bash:
scoutica validate - Terminal Output:
✅ All files passed.
4. Step 4: Network Registration & Publishing
- AI executes bash:
scoutica register . --type candidateandscoutica publish - Terminal Output:
✅ Successfully published to GitHub! Registered on the Scoutica Network.
Copy this prompt and paste it into your AI Agent:
Read https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/RECRUITER_SKILL.md and follow the instructions to set up the Scoutica Employer Network natively.🤖 AI Agent Simulation Log
Section titled “🤖 AI Agent Simulation Log”1. Step 1: Install CLI
- AI executes bash:
curl -fsSL https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/install.sh | bash
2. Step 2: Scaffold Organization
- AI executes bash:
scoutica org init - Terminal Output:
✅ Created recruiter_profile.json and hiring_rules.yaml.
3. Step 3: Register and Search
- AI executes bash:
scoutica org publishandscoutica jobs search - Terminal Output:
✅ Successfully published to GitHub! Found 14 matching candidates.
Manual CLI Install
If you prefer to install it yourself, run the installer:
curl -fsSL https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/install.sh | bashsource ~/.zshrc # or source ~/.bashrcirm https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/install.ps1 | iexThen, build your card manually using one of these methods:
Let AI generate your card automatically from your local documents.
scoutica scan ~/my-docs/Use a specific AI provider explicitly:
scoutica scan ~/my-docs/ --with gemini # Gemini CLIscoutica scan ~/my-docs/ --with claude # Claude Codescoutica scan ~/my-docs/ --with ollama # Ollama (offline privacy)Answer questions step-by-step to build your card:
scoutica init ./my-card/# Or get AI-guided instructionsscoutica init --aiGo to the Scoutica Protocol repo and copy GENERATE_MY_CARD.md. Paste it into ChatGPT or Claude web.
After creation, your card folder looks like this:
my-card/├── profile.json # Your skills, experience, tools├── rules.yaml # Your rules of engagement├── evidence.json # Links to your public work└── SKILL.md # Agent entry pointValidate your card
Run the schema validator to check your card for errors:
scoutica validate ./my-card/Expected output:
✅ 5 checks passedFix any validation errors before publishing.
Publish to GitHub
Push your card to your GitHub repository:
scoutica validate && scoutica publishYour card is now live and discoverable by any AI agent at your GitHub repo URL.