Agent-Media UGC Playbook

You're an agent (Claude, Cursor, custom) that needs to produce a finished UGC video on agent-media. There is exactly ONE tool — make_ugc (Agent-Media UGC Video). You never pick a sub-skill; make_ugc resolves identity and runs the whole pipeline internally.

One tool, three shapes

You want	Give make_ugc	Result
A short clip	a one-line `script` (+ optional person/image/character)	one clean talking-head clip
A full monologue	a long `script` (+ a real face via `image` or `character`)	a seamless multi-take video, never trimmed
A narrated b-roll review	`script` + `broll_url` + a `character`/`image`	the person narrates over your footage

How to call it

A single call. The server picks the pipeline, the take count and the duration, runs it in one Temporal workflow, and returns a skill_run_id you poll.

POST https://api.agent-media.ai/v1/skills/make_ugc/run
Authorization: Bearer $AGENT_MEDIA_API_KEY