Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ucp Schema Authoring

ASecurity

Author custom UCP schemas and extensions — create capability schemas, extension schemas, and type definitions using JSON Schema 2020-12 composition. Use when extending UCP with custom capabilities or building domain-specific extensions.

39 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgogitapi

Works with

apimcp

Security Analysis

A100/100

Scanned 9/22/2026

$npx -y skills add OrcaQubits/agentic-commerce-skills-plugins --skill ucp-schema-authoring --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ucp Schema Authoring?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ucp Schema Authoring
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/orcaqubits-ucp-schema-authoring-agentic-commerce-skills-plugin/badge)](https://www.skillsdirectory.com/skills/orcaqubits-ucp-schema-authoring-agentic-commerce-skills-plugin)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: ucp-schema-authoring
description: >
  Author custom UCP schemas and extensions — create capability schemas,
  extension schemas, and type definitions using JSON Schema 2020-12 composition.
  Use when extending UCP with custom capabilities or building domain-specific
  extensions.
---

# UCP Schema Authoring

## Before writing code

**Fetch live spec**: Web-search `site:ucp.dev specification schema` and fetch the relevant pages for the exact schema metadata requirements, category rules, and composition patterns.

Also fetch:
- https://ucp.dev/latest/specification/reference/ — the base type schemas you will reference
- https://ucp.dev/latest/specification/overview/ — the current service/capability layout, which determines the namespaces available to extend

## Conceptual Architecture

### Schema Categories

The official 6 schema categories are:

| Category | Required Metadata | Purpose | Examples |
|----------|-------------------|---------|----------|
| **Capability** | `$schema`, `$id`, `title`, `description`, `name`, `version` | Major functional domain | checkout, order, identity_linking |
| **Service** | `$schema`, `$id`, `title`, `description` | Transport binding definition | REST, MCP, A2A |
| **Payment Handler** | `$schema`, `$id`, `title`, `description` | Payment method specification | Google Pay, Shop Pay |
| **Component** | `$schema`, `$id`, `title`, `description` | Reusable structural unit | payment, payment_data |
| **Type** | `$schema`, `$id`, `title`, `description` | Primitive data model | buyer, line_item, postal_address, total |
| **Meta** | `$schema`, `$id`, `title`, `description` | Schema about schemas | ucp.json, capability.json |

**Note on Extensions**: Extensions (e.g., fulfillment, discount, buyer_consent, ap2_mandate) are NOT a separate top-level category. They are **Capabilities with an `extends` field** that references their parent capability. An extension has the same required metadata as a Capability (`$schema`, `$id`, `title`, `description`, `name`, `version`) plus the `extends` field.

### Extension Composition via `allOf`

Extensions compose with their parent capability using JSON Schema `allOf`:

```json
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://example.com/schemas/my-extension.json",
  "title": "My Extension",
  "description": "Adds X to checkout",
  "name": "com.example.my_extension",
  "version": "<spec-dated-version>",
  "extends": "dev.ucp.shopping.checkout",
  "allOf": [
    { "$ref": "https://ucp.dev/latest/schemas/shopping/checkout.json" },
    {
      "properties": {
        "my_field": { "type": "object" }
      }
    }
  ]
}
```

### Services and the namespace tree

UCP organizes capabilities into **services** — verticals that own an API surface. The official tree is reverse-DNS under `dev.ucp`:

| Service | Namespace | Holds |
|---------|-----------|-------|
| Shopping | `dev.ucp.shopping.*` | Checkout, Cart, Catalog, Order, and shopping extensions |
| Common | `dev.ucp.common.*` | Identity Linking, Location, and cross-vertical extensions |
| Payment | `dev.ucp.payment.*` / `dev.ucp.common.payment.*` | Payment handlers and payment extensions |

Fetch the overview page for the current tree before choosing what to extend — services and capabilities are added between spec versions, and a capability you intend to extend may have moved or may not have existed when this skill was written.

### Namespace Governance

- `dev.ucp.*` — governed by ucp.dev (official standard). **Never author into this namespace.**
- `com.example.*` — governed by example.com (your organization)
- `com.shopify.*` — governed by shopify.com

Use your organization's reverse-domain name for custom extensions.

**Namespace authority binding.** Later spec versions add verification that a party actually holds authority over the reverse-DNS namespace it publishes under — you are expected to be able to demonstrate control of the domain your namespace derives from. There are also ordering and reservation rules for namespaces. Fetch the live spec for the current binding mechanism and reserve your namespace before shipping schemas that use it; retrofitting a namespace change after publication breaks every consumer.

### Schema Resolution Sequence

1. Discovery — fetch Business profile
2. Negotiation — compute capability intersection
3. Fetch base capability schema from `schema` URI
4. Fetch extension schemas for negotiated extensions
5. Compose via `allOf`
6. Validate checkout data against composed schema

### Implementation Guidance

- Use **JSON Schema 2020-12** (`https://json-schema.org/draft/2020-12/schema`)
- Host your schemas at a stable, versioned URL
- Declare extensions in your `/.well-known/ucp` profile with the `extends` field
- Test schema composition with the UCP schema validator: https://github.com/Universal-Commerce-Protocol/ucp-schema
- Fetch existing UCP schemas as reference before authoring custom ones

Attribution

OrcaQubitsOrcaQubits
View sourceSee grades on GitHubMore from OrcaQubits →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →