Skip to content
Browse the docs

Agent skills

Open, agent-consumable playbooks for Benchy. Give one to Claude Code, Codex, Cursor, or Grok and your agent can run your Benchy account.

What skills are

A skill is a precise, grounded playbook written for agents: a single Markdown document that teaches an MCP-capable agent — Claude Code, Codex, Cursor, Grok, or your homegrown one — how to operate a slice of Benchy correctly. Give your agent a skill and a personal access token, and it can run your Benchy account: build your bio, manage your shop, upload and validate models.

Skills encode the things agents otherwise learn the hard way — which tool to call first, which caps are enforced server-side, when to dry-run, what each error code means, and the boundaries that must never be routed around.

Install a skill

Each skill ships as a standard SKILL.md with YAML frontmatter (name, description, version, license). Use it wherever your agent reads instructions:

  • Claude Code — save it as .claude/skills/<name>/SKILL.md in your project (or ~/.claude/skills/ globally); the frontmatter description tells Claude when to load it.
  • Cursor / Codex / anything with rules or instruction files — drop the file in your rules directory or paste it into the system context.
  • Hosted agents — paste the document into the conversation before asking for Benchy work.
shell
mkdir -p .claude/skills/getting-started-with-benchy
curl -o .claude/skills/getting-started-with-benchy/SKILL.md \
  https://benchy.world/skills/getting-started-with-benchy.md

Pair the skill with an MCP connection — Connect your agent covers tokens and config.

The skills

Getting Started with BenchyThe foundation skill: how the hub-and-spoke family fits together and how an agent connects to it. Covers the MCP endpoint and transport, personal access tokens and OAuth, error handling and concurrency, and the core flows on every spoke — bio profiles, shop listings, and model uploads.Manage Your Benchy ShopThe seller-operations skill: everything commerce on benchy.shop, from a fresh Stripe Connect account to a running catalog with orders, entitlements, gated downloads, subscriptions, and refunds — including the invariants an agent must never route around.Upload and Check 3D ModelsThe pipeline skill: upload, checks, and publishing are separate states. Covers ingest grants, multipart transfer, server-enforced benchy-mesh policies, print-readiness evidence, and recovery.

How they stay true

Every claim in a skill is grounded in the code it describes — endpoints, caps, error codes, and thresholds are lifted from the implementations, not remembered. Skills are versioned in their frontmatter and published under MIT, the same open posture as the validation engine.

Use ← and → to move between pages.