# Skill: Deploy Agent Skills Discovery Index (RFC v0.2.0)

> **Standard:** Agent Skills Discovery RFC v0.2.0
> **Category:** PROTOCOL_DISCOVERY
> **Classification:** SPECIFICATION_AND_GUIDE
> **Author:** TinyCTO Architecture Guild (https://tinycto.tv)

## Overview
Serve /.well-known/agent-skills/index.json exposing on-demand tool and workflow skills with SHA-256 integrity digests.

## Learning Objectives
1. Publish index.json listing available skills with name, description, and skill URL.
2. Include SHA-256 content hashes for tamper-evident verification.
3. Serve markdown SKILL.md files at standard sub-paths.

## Prerequisites
- Bespoke SKILL.md instruction files

## Implementation & Execution Guide

### Step 1: Publish Agent Skills Catalog
Return on-demand skill discovery JSON.

```http
{
  "version": "0.2.0",
  "skills": [
    {
      "name": "tinycto-audit",
      "description": "AEO & Agent Readiness auditor",
      "url": "https://tinycto.tv/skills/audit/SKILL.md",
      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    }
  ]
}
```

## Architectural Takeaway
On-demand skill discovery keeps LLM context windows lean by loading tool specifications only when relevant.