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 Cart

ASecurity

Implement the UCP Cart capability (`dev.ucp.shopping.cart`) — a lightweight CRUD surface for collecting line items before purchase intent exists, and its conversion into a Checkout session. Use when building pre-checkout item collection, shareable carts, or cart-recovery flows over REST, MCP, or Embedded bindings.

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

Works with

mcp

Security Analysis

A100/100

Scanned 9/22/2026

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

Installs into .claude/skills of the current project.

Are you the author of Ucp Cart?

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

Security grade badge for Ucp Cart
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/orcaqubits-ucp-cart-b385a81d/badge)](https://www.skillsdirectory.com/skills/orcaqubits-ucp-cart-b385a81d)

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-cart
description: Implement the UCP Cart capability (`dev.ucp.shopping.cart`) — a lightweight CRUD surface for collecting line items before purchase intent exists, and its conversion into a Checkout session. Use when building pre-checkout item collection, shareable carts, or cart-recovery flows over REST, MCP, or Embedded bindings.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch
---

# UCP Cart Capability

## Before writing code

**Fetch live spec**: Web-search `site:ucp.dev specification shopping cart` and fetch the page for the exact Cart schema, operation names, and binding details. Also fetch `https://ucp.dev/latest/schemas/shopping/cart.json` for the authoritative JSON Schema. Field names and required-ness change between spec versions — never write the schema from memory.

## Conceptual Architecture

### Why Cart is separate from Checkout

Checkout carries payment handler configuration, buyer commitment, and a status lifecycle. That is overhead a buyer does not need while still browsing. Cart is the lightweight half: collect items, get estimated totals, share a link — with **no payment configuration and no status machine**.

The canonical progression is:

```
cart session  →  checkout session  →  order
```

Cart handles *exploration*. Checkout enforces *commitment*.

### Operations

| Operation | Purpose |
|-----------|---------|
| Create Cart | Initialize a session with line items and optional buyer / context data |
| Get Cart | Read current state; returns `not_found` once expired or cancelled |
| Update Cart | **Full replacement** of cart contents — not a patch |
| Cancel Cart | Terminate the session |

`Update Cart` replacing rather than merging is the detail most implementations get wrong. Send the complete intended line-item set every time.

### Key data model

- `id` — cart identifier
- `line_items` — entries with quantity (in the authoritative sale basis), unit price, and line totals
- `context` — localization signals: country, region, postal code, location
- `buyer` — optional name, email, phone
- `currency` — ISO 4217
- `totals` — **estimated** subtotal, tax, fulfillment, discounts
- `messages` — validation warnings and informational notices
- `continue_url` — handoff link for session recovery
- `expires_at` — optional expiry

### State model

Carts are binary: they exist or they do not. There is no `incomplete → completed` lifecycle, and **totals stay estimates** until checkout conversion. Treat any amount read from a cart as indicative only — never as something to charge against.

### Conversion to Checkout

Create a checkout referencing `cart_id`. Two rules govern this:

1. The business **uses the cart contents and ignores overlapping payload fields**. Do not attempt to pass line items alongside a `cart_id` and expect them to merge.
2. Conversion is **idempotent** — if an incomplete checkout already exists for that cart, the business returns the existing session rather than creating a second one.

After checkout completion the business may clear the cart, driven by TTL or its own business logic. Do not depend on the cart surviving.

### Bindings

Cart is exposed over **REST**, **MCP**, and **Embedded**. It is not an A2A capability. Negotiate it like any other capability — see `ucp-dev-patterns` for the intersection algorithm.

## Implementation Guidance

- Make `Create Cart` idempotent on your side too; agents retry aggressively.
- Populate `continue_url` — it is what makes a cart shareable and recoverable, which is the main reason Cart exists as a separate capability.
- Surface validation problems through `messages` rather than failing the whole request, so an agent can repair one line item without rebuilding the cart.
- Set `expires_at` deliberately and honour it in `Get Cart` with `not_found`.
- Reference implementation: https://github.com/Universal-Commerce-Protocol/samples

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 →