agent-media ugc playbook
Playbook for Agent-Media UGC Video — the one tool for UGC video on agent-media. Always call the single makeugc skill: give it a script (any length) and optionally a person/image/character; it returns the finished captioned vertical video. Short script → one clip, long monologue → full multi-take (never trimmed), brollurl → narrated overlay. You never pick a sub-skill.
- Installs
- 122
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/gitroomhq/agent-media --skill agent-media-ugc-playbook- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads agent-media ugc playbook automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
{
"script": "Okay this is wild, I tried the new flow and it actually works.",
"person": "a friendly young woman, soft daylight, candid framing",
"name": "Maya, 27"
}
Poll with GET /v1/skills/runs/<skill_run_id> until status is succeeded; final_output.video_url is your finished MP4.
See skills/make-ugc/SKILL.md for the full field manual.
Step D — publish it (optional)
Once you have a video_url, you can post it straight to the user's TikTok / Instagram / X with the publish-to-social skill — POST /v1/social/publish (CLI agent-media social publish, MCP social_publish). The user connects each network once via OAuth (/v1/social/connect). See skills/publish-to-social/SKILL.md.
Identity
person— describe them in words;image— a photo (https URL or base64);character— a savedchar_…id orcharacter_sheet_urlfrom list_characters; omit all three for a default person.- A full monologue or a b-roll review needs a real face — pass
imageorcharacter, not justperson. - Reuse a saved character: pass the same
characteron the next call — no re-generation.
Rules
- make_ugc paces and chunks the script for you — pass the FULL line or monologue and do NOT trim it. Length is inferred from the script.
- Any image/video URL you pass must be a public https URL (make_ugc re-hosts it onto R2 for you) — or a
character_sheet_url/char_…for a saved character. - Credits are deducted as each take runs. Portrait + character-sheet prep inside a video are FREE — you only pay for the video itself.
- Don't put "selfie" or "phone" in a description — say "talking to camera" instead. make_ugc already handles this internally.
Troubleshooting
INSUFFICIENT_CREDITS— user is out. Surface the agent-media.ai billing page link.make_ugc_needs_face— a full monologue or a b-roll review needsimageorcharacter(a real face), not justperson.- Video has subject holding a phone — they used a pose hint mentioning "selfie" or "phone". Strip it or set
pose: "". - Step stuck in
submitted— Temporal worker may be restarting. Wait 30s and re-poll; if still stuck after 5 min, the workflow is hung — contact agent-media support with theworkflow_id.
See also
- reference/auth.md — first-time setup
- reference/pacing.md — 2–4 words/sec rule with examples
- reference/realism-rubric.md — the 9 realism props baked into every prompt
FAQ
What does the agent-media ugc playbook skill do?
Playbook for Agent-Media UGC Video — the one tool for UGC video on agent-media. Always call the single makeugc skill: give it a script (any length) and optionally a person/image/character; it returns the finished captioned vertical video. Short script → one clip, long monologue → full multi-take (never trimmed), brollurl → narrated overlay. You never pick a sub-skill.
How do I install agent-media ugc playbook?
Run npx skills add https://github.com/gitroomhq/agent-media --skill agent-media-ugc-playbook in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agent-media-ugc-playbook/ (personal) or .claude/skills/agent-media-ugc-playbook/ (project).
Which AI agents can use agent-media ugc playbook?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is agent-media ugc playbook safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains agent-media ugc playbook?
It is published by gitroomhq in gitroomhq/agent-media. It has 122 recorded installs.
More from gitroomhq/agent-media
agent-media ugc video
gitroomhq/agent-media
Open the skill to read its SKILL.md instructions.
make ugc video
gitroomhq/agent-media
Open the skill to read its SKILL.md instructions.
make character sheet
gitroomhq/agent-media
Open the skill to read its SKILL.md instructions.
make subtitles
gitroomhq/agent-media
Burn TikTok / Hormozi-style captions onto any vNext video (R2-hosted). Auto-transcribes via Whisper when transcript is omitted. Styles: hormozi (default), tiktok, minimal.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image