Agent Media
AI UGC video production from the terminal using the `agent-media` CLI.
Install
/plugin marketplace add yuvalsuede/agent-media-skillThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add yuvalsuede/agent-media-skill --skill agent-mediagit clone --depth 1 https://github.com/yuvalsuede/agent-media-skill.git /tmp/agent-media-skill
mkdir -p ~/.claude/skills
cp -r /tmp/agent-media-skill/. ~/.claude/skills/agent-mediaPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
npm release: https://www.npmjs.com/package/agent-media-cli agent-media cli github: https://github.com/gitroomhq/agent-media official website: https://agent-media.ai # agent-media — AI UGC Video Production & Media Generation Produce complete UGC videos, Product Acting UGC, and SaaS review videos from the terminal using the `agent-media` CLI. --- ## MANDATORY RULES — READ BEFORE EVERY COMMAND **You MUST follow ALL of these rules. Violating any rule produces a broken, unwatchable video.** ### Rule 1: ALWAYS use `--actor` — PICK A RANDOM ONE Every UGC video MUST include `--actor <slug>`. Without an actor, there is no talking head and no lip sync — the video will just be a static image with voiceover. **If the user hasn't specified an actor:** 1. Run `agent-media actor list` to get the full list of available actors 2. Pick a **random** actor from the list — do NOT always use the same one (e.g., don't always default to `sofia` or `naomi`) 3. Tell the user which actor you picked and suggest they can browse with `agent-media actor list` or pick a specific one with `--actor <slug>` **NEVER hardcode a default actor.** Every video should feel different — variety in actors is key to quality UGC content. ### Rule 2: ALWAYS count words — 2.5 words per second Natural speech is 2.5 words/second. Scripts MUST match the target duration **exactly** — too many words sounds robotic, too few words creates awkward pauses and silence: - **5s video** → 10–12 words (not fewer!)
Details
- Skill name
agent-media- Repository
- yuvalsuede/agent-media-skill
- License
- Apache-2.0
- Repo updated
- 27 April 2026
FAQ
What does the Agent Media skill do?
AI UGC video production from the terminal using the `agent-media` CLI.
How do I install the Agent Media skill?
Claude Code plugin: /plugin marketplace add yuvalsuede/agent-media-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Media popular?
It lives in yuvalsuede/agent-media-skill, which has 43 GitHub stars and 7 forks.
Related skills
Capafy Publisher
49Capafy/Capafy-skills
Creator-side Capafy workflow for publishing, updating, packaging, uploading, re-shipping, or managing an Agent/Skill. Also handles creator earnings, payouts, statistics, refunds, certification/KYC, review links, Agent continuation, and publisher-account switching. Generic buyer login, balance, orders, purchases, subscriptions, and instances belong to capafy-user.
Oobo
43ooboai/oobo
Context beyond the diff - captures AI sessions, tokens, code attribution, semantic code search, and engineering memory via MCP. Use when the user asks about commit history with AI context, session history, code attribution, token usage, code search, or engineering memory.
Claude Slim
44iops-leo/claude-slim
Analyze and reduce Claude Code token overhead. Scans skills, plugins, memory files, and CLAUDE.md for bloat — then cleans up with user approval. Use when: /claude-slim, token optimization, reduce tokens, slim down, cleanup skills, token diet, save tokens, context diet
Lengyi Shotlist
43woyin2024/lengyi-shotlist
设计电影级分镜视频提示词。输入一段文本(小说片段、一句剧情或几个主题词),拆分或扩写成一段 8-15s 视频的顺序镜头脚本,自动确定分镜数(4/6/9/12/16)与每镜时长,逐镜给出可直接复制到可灵/海螺/seedance 2.0/veo 的提示词——含镜号、场景、风格、主体、动作过程、镜头运动、剧情内容,并附"参考主体生图提示词"以锁定主体一致性。当用户要做视频分镜、分镜脚本、镜头脚本、shotlist、顺序分镜、文生视频/图生视频、AI视频镜头脚本时使用。
Fomo Cc
46zack-the-worker/fomo-cc
Brutal, no-mercy reality check for AI-hype delusions - "clone Facebook in 1 hour", "rebuild X in 30 minutes", "build Uber over the weekend", "a million-dollar SaaS in one night with vibe coding", "no need for engineers, AI does everything". Roasts hard in the user's own language and cultural tone (swearing included), then dismantles the idea with real numbers (team size, years, infrastructure, the hidden part of the iceberg) and ends with a realistic way out. Use ONLY when the user explicitly asks to be roasted or challenged hard - e.g. "roast this idea", "roast me", "tear this apart", "be bru
Gtm Pipeline:signal Search
77keinsaasforever/gtm-pipeline-skills
Find buying intent signals for target companies and score them for purchase intent. Runs a Python script (signal_search.py) that orchestrates Parallel web search (always on), Firecrawl crawl (opt-in), Parallel structured enrichment (opt-in), and a Signal Assessment LLM that scores 1-100. Universal templates live in the script; client-specific prompts come from the working directory's context/ files. Runs standalone or in either pipeline workflow — does NOT require ICP scoring as input. Also triggers on "signal search", "find signals for", "buying intent".
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.