> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentruntime.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform MCP authoring skills

> Public skill bundles for external AI agents — Tenant Data, workflows, Surfaces, and end-to-end design on Platform MCP.

External agents (ChatGPT, Codex, Claude) should call **`ar_get_started`** on [Platform MCP](/api/platform-mcp) first, then load skill markdown from the **public** tree below (no access to the private platform-mcp GitHub repo required).

## Raw fetch (recommended for agents)

Base URL:

```
https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/
```

| Skill | URL |
| - | - |
| **Platform design** | [SKILL.md](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/agentruntime-platform-design/SKILL.md) |
| **Tenant Data** | [SKILL.md](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/agentruntime-tenant-data-authoring/SKILL.md) |
| **Workflow authoring** | [SKILL.md](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/agentruntime-workflow-authoring/SKILL.md) |
| **Surfaces apps** | [SKILL.md](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/agentruntime-surfaces-authoring/SKILL.md) |

Browse the full tree on GitHub: [platform-mcp-skills](https://github.com/agentruntime-io/agentruntime-docs/tree/main/platform-mcp-skills).

## JSON schemas (embedded contracts)

| Schema | Raw URL |
| - | - |
| Tenant Data `{ tables[] }` | [tenantdata-logical.schema.json](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/schemas/tenantdata-logical.schema.json) |
| Surfaces v1 | [surfaces-v1.schema.json](https://raw.githubusercontent.com/agentruntime-io/agentruntime-docs/main/platform-mcp-skills/schemas/surfaces/surfaces-v1.schema.json) |

Or call Platform MCP **`tenantdata_logical_schema`** and **`surfaces_schema_catalog`** — they return the same public URLs.

## Typical order

1. `ar_get_started` — tenant, playbooks, `embedded_schema_tools`
2. Load **platform-design** SKILL, then tenant-data → workflow → surfaces as needed
3. `workflows_validate` with `tenantdata_schema` before run
4. For Surfaces apps: publish workflows first, then set **`workflow_ref` to published UUIDs** (avoid **Import pending** in Console)

## Related

* [Platform MCP](/api/platform-mcp) — endpoint, auth, tool groups
* [Workflow dry-run](/workflows/dry-run) — user-facing validate concepts


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.