# Skill Catalog Builder

> Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before…

Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bodies.

- Page: https://ss33.ai/skills/rohitg00/skill-catalog-builder-77221317764
- Publisher: rohitg00
- Category: [AI & Agents](https://ss33.ai/skills/category/ai-and-agents-y6jz7i) › [Skill & prompt authoring](https://ss33.ai/skills/category/ai-and-agents-y6jz7i/skill-and-prompt-authoring-p179rh)
- License: MIT
- Source: https://github.com/rohitg00/ai-engineering-from-scratch/blob/45fa4084de6ba2f88fa96a41e69efa2166f868b3/phases/13-tools-and-protocols/24-skill-discovery-and-progressive-disclosure/outputs/skill-catalog-builder/SKILL.md

## Skill

SKILL.md: https://ss33.ai/api/v1/ss33/download/rohitg00/skill-catalog-builder-77221317764

# Skill catalog builder

Use this skill when an agent host needs deterministic discovery across more than one skill directory.

1. Read `references/discovery-contract.md`.
2. Review the example host policy in `assets/scope-policy.json`; do not assume its order is universal.
3. Run `python3 scripts/build_catalog.py project=PATH user=PATH` with scopes listed from highest to lowest precedence.
4. Inspect the JSON `collisions` and `omitted` arrays before activating a skill.
5. Load only the selected SKILL.md body. Load a direct reference only when that body names it.

Never execute a bundled script during discovery. Never choose an equal-precedence duplicate by incidental filesystem order.

Return the catalog budget, selected entries, collision resolutions, and omissions.