Tool
draft_email_interpret_skill
Create a skill from this email
Draft a reusable Skill that interprets emails like the referenced one — extract structured data and render a result block. Ask the user what they want to happen for emails like this BEFORE calling. Pass the captured intent as `spec` (a structured LLM skill: instructions + an outputSchema describing the fields to extract + a verdict map turning them into extracted data and a UI component). Pass the referenced email as `sample` so the draft can be previewed. To EDIT an existing draft, pass its `draftId` and the updated `spec`. This never goes live on real mail — it creates a draft a teammate can preview, refine, and (as an admin) activate.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
draftId | string | no | Set to edit an existing draft (creates a new version); omit to create a new one. |
spec | object | yes | — |
▸expand spec
| |||
changeSummary | string | no | One line describing this version's change (for the history). |
sample | object | no | The example email this skill is built from (usually the referenced message). Used to preview the draft. |
▸expand sample
| |||
Example
{
"spec": {
"id": "<id>",
"label": "<label>",
"kind": "llm",
"appliesTo": "message",
"instructions": "<instructions>",
"outputSchema": "<outputSchema>",
"verdict": {}
}
}