Genix
Generate and edit images, videos, audio, music, and 3D assets, and transcribe audio/video with ElevenLabs Scribe v2. Use for media generation, image editing, multi-image fusion, speech, speech-to-text, transcription, music, video, or 3D requests.
Install
npx skills add zhing2006/aigc-skills --skill genixgit clone --depth 1 https://github.com/zhing2006/aigc-skills.git /tmp/aigc-skills
mkdir -p ~/.claude/skills
cp -r /tmp/aigc-skills/genix ~/.claude/skills/genixPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AIGC Skills
## Python Path
The `{python}` placeholder in commands refers to the Genix virtual environment Python:
| Platform | Path |
| -------- | ---- |
| Windows | `.venv-genix/Scripts/python.exe` |
| Linux/macOS | `.venv-genix/bin/python` |
## Workflow
1. **Select generation method**: Choose the appropriate method based on user request. If not specified, use the first method listed for that content type
2. **Read reference file**: Read the corresponding reference file for the selected method
3. **Prepare input**: For generation, optimize the prompt following the reference file's "Prompt Best Practices". For transcription, use the supplied audio/video unchanged; do not rewrite, translate, or invent speech
4. **Run**: Run the script with the input and parameters as instructed in the reference file
5. **Report result**: Tell the user where the output file was saved. Do not read generated media; read transcript text only when the user asks to view or process it
## Image Generation Skills
- [Nano Banana Image](references/google-nano-banana.md)
- [OpenAI GPT Image](references/openai-gpt-image.md)
- [Volcengine Seedream Image](references/volcengine-seedream.md)
- [DashScope Qwen Image 3.0](references/dashscope-qwen-image.md)
## Audio Generation Skills
- [DashScope Text to Speech](references/dashscope-text-speech.md)
- [DashScope Voice Design](references/dashscope-voice-design.md)
- [DashScope Voice Clone](references/dashscope-voice-clone.md)Details
- Skill name
genix- Repository
- zhing2006/aigc-skills
- Path
genix/SKILL.md- License
- Apache-2.0
- Repo updated
- 5 November 2026
FAQ
What does the Genix skill do?
Generate and edit images, videos, audio, music, and 3D assets, and transcribe audio/video with ElevenLabs Scribe v2. Use for media generation, image editing, multi-image fusion, speech, speech-to-text, transcription, music, video, or 3D requests.
How do I install the Genix skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add zhing2006/aigc-skills --skill genix. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Genix popular?
It lives in zhing2006/aigc-skills, which has 5 GitHub stars and 0 forks.
Related skills
Social Post
5lp1688/skill-social-post
學習使用者的 Facebook/Instagram/YouTube/Threads/X 語氣與受眾,規劃內容、撰寫平台化貼文、經確認後發佈;並作為所有流量、演算法、留存與轉化學習的唯一結構化帳本,做跨平台/跨篇/跨集比較、實驗設計及規則升降級。使用者說「發文」「幫我寫」「用我的口氣」「排貼文」「查流量」「演算法」「分析 Reels/Shorts」「把數據訓練進去」「記錄成效」「比較這幾篇」「優化 pattern」「review」時使用。
Blender MCP
9vladmdgolam/agent-skills
Blender MCP expert for scene inspection, Python scripting, GLTF export, and material/animation extraction. Activate when: (1) using Blender MCP tools (get_scene_info, execute_python, screenshot, etc.), (2) writing Blender Python scripts for extraction or manipulation, (3) exporting scenes to GLTF/GLB for web (Three.js, R3F), (4) debugging material or texture export losses, (5) optimizing GLB files with gltf-transform, (6) using asset integrations (PolyHaven, Sketchfab, Hyper3D Rodin, Hunyuan3D). Covers critical export gotchas, material mapping survival, texture optimization pipeline, headless
Ecom Video Creative
9xianglouw/ecom-agent-skills
跨境电商多模态广告素材生产技能。三步:先定素材形态(实拍口播 / 数字人 / AI 生成 / 混剪 / 素材库剪辑 / 图文)与各自的合规红线,再按周期采样爆款前 3 秒台词、提炼黄金三秒的套路与热词、产出可追加进钩子库的候选,最后按产品定义 × 市场风格库 × 钩子模板库批量产出分镜脚本、文生视频/图生视频提示词(Seedance、Veo、Sora、Kling、即梦等)与配音字幕,并按前三秒留存法则逐条检查钩子强度、首帧主体、开场禁忌、字幕长度、口播语速与禁用词。支持英语、西语、葡语、越南语、日语、泰语、阿拉伯语等任意目标语种(内置 53 个语种)。提示词可直连用户选定的视频生成大模型(火山方舟、通义万相、可灵、海螺、Veo、Sora、Runway、Luma、Replicate、fal 等 12 个)出真实镜头片段,脚本负责组装请求、提交轮询、取回成片与记台账。涉及「这个品该做哪种素材」「最近什么样的开场容易火」「给这个产品出广告脚本」「前三秒怎么留住人」「数字人/混剪/去水印能不能用」「素材本地化到越南语/日语/泰语」「这个钩子行不行」「把提示词接到视频生成接口出片」这类请求时使用。
Video Summary
9HOWILLMAKEIT/skills
BibiGPT 风格视频总结:输入 Bilibili / YouTube 视频链接,快速抓取字幕/转写文本,并生成结构化总结(TL;DR、核心要点、章节时间线、金句,支持中英文)。Use when the user shares a video link (bilibili.com, b23.tv, youtube.com, youtu.be) and asks to summarize it, extract key points, get subtitles/transcript, 总结视频, 提炼要点, 视频笔记.
Layer
10layerai/skills
Use when generating or editing game and entertainment assets on Layer through MCP: images, video, 3D meshes, audio, sprites, textures, or marketing creative. Also when choosing a Layer base model, pricing a run in Creative Units before spending them, uploading reference files, polling a generation, applying a trained style, or recovering from MODEL_NOT_FOUND, INSUFFICIENT_BALANCE, RATE_LIMITED, or a silently degraded reference set.
Transcription Quality Evaluation
9bleakbelladonnals/asr-transcription-skills
对比评测录音转写产品/引擎(录音硬件端到端 vs 云转写模型):控制变量测试设计(2×2 音频×引擎)、ffmpeg 音频质量客观指标(响度/动态/底噪/削波/声道)、SRT 变体解析与统计、关键术语识别对照、内容锚点时间轴对齐、幻觉检测,输出对比矩阵。触发词:转写对比、转写质量、录音质量对比、ASR 评测、哪个转写好、录音笔对比、转写引擎对比。
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.