Ugc Creator

Turns Claude into a hyper-realistic AI UGC influencer studio. Use this whenever the user wants to create, manage, or scale a synthetic/AI influencer or AI UGC creator: building a consistent character, writing image or video generation prompts for an AI model (Flux, Midjourney, Kling, Sora, Veo, etc.), producing TikTok/Reels/Shorts-style content, product/testimonial/UGC clips, or "shot on iPhone" lifestyle photos of a recurring synthetic person. Trigger it even when the user doesn't say "skill": e.g. "make my AI model look the same in every post", "generate a week of UGC for my AI girl", "why d

5 stars 1 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add 0xAnni/ugc-creator --skill ugc-creator

Manual install

git clone --depth 1 https://github.com/0xAnni/ugc-creator.git /tmp/ugc-creator
mkdir -p ~/.claude/skills
cp -r /tmp/ugc-creator/. ~/.claude/skills/ugc-creator

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# ugc-creator

Build AI UGC influencers that stay **the same person** across every shot, scene,
and video, and generate a whole content calendar from one-line briefs.

The core idea: **don't prompt a character, compile one.** A character is not a
saved image you keep re-uploading and praying the face holds. It's a **JSON
identity card** (the single source of truth) plus a deterministic **6-layer
prompt assembler**. Identity lives in data, so consistency stops being luck and
becomes a property of the system.

## When you're invoked, figure out which job this is

1. **Create an actor**: the user wants a new synthetic person. → Go to
   *Workflow A*.
2. **Generate a shot (or a batch)**: the user has an actor and wants
   image/video prompts. → Go to *Workflow B*.
3. **Animate a shot to video**: turn a still into a Kling 3.0 clip via fal.ai.
   → Go to *Workflow C*.
4. **Fix drift / lock consistency**: "she looks different every time." →
   Two layers: the identity card + consistency protocol
   (`references/prompt-layers.md`) kills prompt-side variance; the reference
   lock (`references/reference-lock.md`) kills sampler-side variance. For
   recurring content, use both.

If the user just describes a vibe ("a Swedish beach girl"), assume they want
Workflow A first, then B.

## The mental model (state this to the user once, briefly)

- **Identity = data, not a vibe.** A re-uploaded image with a begging paragraph

Read the full skill on GitHub

Details

Skill name: ugc-creator
Repository: 0xAnni/ugc-creator
License: MIT
Repo updated: 12 July 2026

FAQ

What does the Ugc Creator skill do?

How do I install the Ugc Creator skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 0xAnni/ugc-creator --skill ugc-creator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Ugc Creator popular?

It lives in 0xAnni/ugc-creator, which has 5 GitHub stars and 1 forks.

Related skills

Xxd Panel 046

nevertoday/xxd-panel-046

XXD Panel 046｜Impasto Micro-World: rebuilds the photo's subject as a small, tactile 3D miniature painted in thick impasto oil, standing on one clear diagonal band of thick paint — water, ground, a path or a strip of light — across bright white textured paper with wide whitespace, with reflections, ripples or light spots where they fit and only a few impasto clouds, a sun or mist behind. Visible paint ridges and palette-knife marks; bright, fresh colours (sky blue, lake teal, fresh green, warm yellow, coral, peach) drawn from the photo. A short title with a little small text. Outputs PNG top-bo

Images, Video & Audio

Screenshot Infographic Skill

Wanqiu12345/screenshot-infographic-skill

把「一张截图 + 一段功能描述」或「一段主题文案」自动变成一整套可在小红书/公众号/社群直接发的风格统一、视觉优美的图。两种模式：①截图模式——生成功能教程图/产品导览图（1张概览+单功能细节，局部放大，品牌色自动跟随截图）；②纯文案模式——表意型排版信息图，纯排版零插画、离线可跑，视觉元素直接编码内容。晚秋简约风：主色 #1A3A6B 深蓝 + 哑光金 #B08D45 + 暖白 #FBFAF8。适合产品教程、功能安利、新手引导、知识科普、活动预告、资讯解读。触发词：截图生成教程、功能讲解图、产品导览图、截图配图、功能安利图、把截图做成教程、文案生成信息图、小红书配图、名词科普配图、infographic generator、screenshot tutorial、 feature guide image、text to infographic。

Images, Video & Audio

AI Image to Vector Redesign

hxr223/ai-image-to-vector-redesign

Finish flattened GPT Image 2 design outputs by rebuilding text and layout into sharp, editable SVG/PDF/high-resolution PNG deliverables. Use for AI-generated posters, long images, infographics, flyers, social cards, and marketing graphics when upscaling or tracing would not fix blurry text or layout artifacts.

Images, Video & Audio

Music Mv Studio

chenqianshinian/music-mv-studio

音乐 MV（音乐视频 / 歌词可视化）全流程制作工作流。用于「给某首歌做 MV」「按歌词做分镜并生成画面」「把逐镜片段合成带字幕的成片」，也用于复盘优化已有的 MV 流水线。核心是**先锁设计再生成、一切结论用像素说话**：导演五层与开工必答 → 首帧闸门 → 逐镜生成（方向锁/结构锁/运动锁）→ 像素级验收 → 定点返修。附 73 条血泪清单（真实踩过的坑）与可运行脚本（scripts/）；Windows / macOS / Linux 三平台都有 CI 冒烟。

Images, Video & Audio

Bulkcut Coach

Juggernaut0825/bulkcut-coach

Fitness and diet tracking tool. Use when the user wants to analyze food photos for calories, log workouts, calculate metabolism (BMR/TDEE), get daily calorie summaries, or generate training/diet plans. Invoked with /bulkcut-coach.

Images, Video & Audio

Moodle Mcq

danielcregg/moodle-mcq

Generate, review, and improve Moodle quiz questions. Supports GIFT format (compact, ~6x fewer tokens) and Moodle XML format (full features with syntax highlighting). Four modes: create (easy/standard/challenging difficulty), review (improve existing MCQs). Handles MCQ, true/false, short answer, matching, numerical, and cloze questions. Enforces answer length balance (15/15/70), self-contained stems, plausible distractors, and proper Moodle XML structure including the critical <name> tag fix.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.