From agent-media
Generates 5-15s vertical UGC videos of a character holding or wearing a product, with optional lip-synced script or silent scene action modes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-media:make-product-in-handsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate a 5/10/15s vertical UGC video where your character holds, wears, and shows a product. Provide a character_sheet_url (R2-hosted) and the product image (product_image_url — any https URL — OR product_image_base64; re-hosted to R2 automatically). Two modes: script for a lip-synced talking-head product review (2-4 words/sec), OR scene_action for a silent demo / b-roll. Set subject (e.g. "a...
Generate a 5/10/15s vertical UGC video where your character holds, wears, and shows a product. Provide a character_sheet_url (R2-hosted) and the product image (product_image_url — any https URL — OR product_image_base64; re-hosted to R2 automatically). Two modes: script for a lip-synced talking-head product review (2-4 words/sec), OR scene_action for a silent demo / b-roll. Set subject (e.g. "a young woman") to lock the person's gender/appearance so a gendered product can't drift it. framing: "close_up" (chest-up, default) or "full_body" (head-to-toe, for turn-arounds / showing the whole outfit). Both the person and the exact product are locked from the reference images.
Call this skill when the user asks for the outcome described above. It runs on the agent-media vNext primitive runtime via the mcp__agent-media__make_product_in_hands MCP tool. Authentication is the user's existing agent-media Bearer token (issued by agent-media login).
Preferred path: MCP tool mcp__agent-media__make_product_in_hands. Schema is auto-published via tools/list against the same MCP server, so don't restate the schema here — trust the server's response.
Fallback path: REST.
POST https://api.agent-media.ai/v1/skills/make_product_in_hands/run
Authorization: Bearer $AGENT_MEDIA_API_KEY
Content-Type: application/json
Idempotency-Key: <any unique string per intent>
??sGET https://api.agent-media.ai/v1/primitives/runs/<run_id>
Authorization: Bearer $AGENT_MEDIA_API_KEY
agent-media login.This file is auto-generated by scripts/generate-public-skill.ts from the registry at services/api-v2/src/skills/registry.ts. Do not hand-edit; CI rejects drift.
npx claudepluginhub gitroomhq/agent-media --plugin agent-mediaOrchestrates UGC video creation on agent-media vNext runtime. Choose between one-shot `make_ugc_video` or chaining four primitives manually.
Generates multi-cut UGC product ads with jump-cuts, POV talking-head, and 5-act narrative. Auto-detects category from URL. Supports Seedance and Kling video engines.
Produces branded AI UGC shorts: generates scripts, renders vertical talking-head videos with lip-sync avatars, reuses brand memory, optionally publishes to Instagram Reels/YouTube Shorts.