Skip to main content
1

Install the CLI

curl -fsSL https://raw.githubusercontent.com/traylinx/scoutica-protocol/main/install.sh | bash
Then reload your shell:
source ~/.zshrc   # or source ~/.bashrc
Verify the install:
scoutica version
Run scoutica doctor to confirm all prerequisites (Git, Python 3, AI providers) are installed correctly.
2

Create your Skill Card

Choose the method that fits you best: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 point
├── scoutica.json       # Discovery file (auto-generated)
└── rules/              # Evaluation rule templates
    ├── evaluate-fit.md
    ├── negotiate-terms.md
    ├── verify-evidence.md
    └── request-interview.md
3

Validate your card

Run the schema validator to check your card for errors:
scoutica validate ./my-card/
Expected output:
✅ 5 checks passed
Fix any validation errors before publishing.
4

Publish to GitHub

Push your card to your GitHub repository:
scoutica validate && scoutica publish
Your card is now live and discoverable by any AI agent at your GitHub repo URL.
scoutica publish only stages canonical card files (profile.json, rules.yaml, evidence.json, scoutica.json, SKILL.md). Your raw source documents are never committed.

​
What’s next

CLI Reference

Full reference for all Scoutica CLI commands and flags

Your Skill Card

Understand the 4 files that make up your Skill Card

Privacy Zones

How your three-zone privacy model works

Developer Guide

Build apps and integrations on the Scoutica Protocol