Individual skill
ai-media-generator
為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞,並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 / Aleph、Google Veo 3.1、Ideogram 3、Nano Banana Pro、Stable Diffusion 3.5(⚠<U+FE0F> OpenAI Sora 2 已於 2026-04-26 停運,API 撐到 2026-09-24,預設改推 Runway/Veo/Kling)。只要使用者提到「AI 生圖」「AI 影片」「AI 音樂」「做 MV」「做 storyboard」「寫 prompt 給 XXX」「我想用 Kling/Suno/Midjourney/Runway/Veo...」「幫我操作 OiiOii / 即夢 / 可靈」「txt2img / img2video / 文生圖 / 文生影片 / 圖生影片」「角色一致性」「多鏡頭分鏡」「運鏡」「結果有瑕疵 / 不夠精緻 / 怎麼修」,或任何跟上述平台或影像/影片/音樂生成工作流相關的任務,都要用這個 skill。即使他們沒講明平台,只要任務是要餵給某個生成模型的 prompt,就用這個 skill 幫他們選對的平台、寫對的格式。
SKILL.md
Source commit edc8aa5227f4a58f9a3a88c7bf3e99bdda2a4361
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 274
- Repository last updated
- Aug 9, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-image Repository topic
- ai-music Repository topic
- ai-video Repository topic
- claude-code Repository topic
- claude-skill Repository topic
- flux Repository topic
- generative-ai Repository topic
- kling Repository topic
- midjourney Repository topic
- prompt-engineering Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.gitignoreasset · 288 bytesCHANGELOG.mddoc · 76,988 bytesCONTRIBUTING.mddoc · 1,680 bytesLICENSEasset · 1,088 bytesREADME.mddoc · 11,234 bytesSKILL.mdcore · 34,257 bytesSKILL.mdcore · 34,257 bytesagents/openai.yamlasset · 298 bytesautomation/browser-guide.mddoc · 9,246 bytesautomation/click-protocol.mddoc · 15,972 bytesautomation/site-profiles/README.mddoc · 3,485 bytesautomation/site-profiles/_template.mddoc · 3,249 bytesautomation/site-profiles/flow.mddoc · 25,873 bytesautomation/site-profiles/ideogram.mddoc · 4,305 bytesautomation/site-profiles/kling.mddoc · 11,860 bytesautomation/site-profiles/midjourney.mddoc · 4,304 bytesautomation/site-profiles/oiioii.mddoc · 105,433 bytesautomation/site-profiles/runway.mddoc · 4,645 bytesautomation/site-profiles/seedream.mddoc · 4,231 bytesautomation/site-profiles/sora.mddoc · 4,939 bytesautomation/site-profiles/suno.mddoc · 10,725 bytesautomation/site-profiles/vidu.mddoc · 4,138 bytesevals/evals.jsonasset · 15,199 bytesreferences/aesthetic-grade.mddoc · 12,761 bytesreferences/camera-language.mddoc · 6,231 bytesreferences/cinematic-direction.mddoc · 26,506 bytesreferences/commercial-direction.mddoc · 15,473 bytesreferences/community-prompt-patterns.mddoc · 18,882 bytesreferences/concept-first-prompting.mddoc · 9,343 bytesreferences/director-style-library.mddoc · 14,314 bytesreferences/editing-transitions.mddoc · 13,533 bytesreferences/external-resources.mddoc · 12,218 bytesreferences/flux.mddoc · 6,636 bytesreferences/gemini-omni.mddoc · 13,328 bytesreferences/hailuo.mddoc · 9,607 bytesreferences/ideogram.mddoc · 14,761 bytesreferences/image-to-video-workflow.mddoc · 21,149 bytesreferences/kling.mddoc · 21,722 bytesreferences/midjourney.mddoc · 19,389 bytesreferences/model-picker.mddoc · 12,201 bytesreferences/multimodel-video-cheatsheet.mddoc · 9,050 bytesreferences/nano-banana.mddoc · 13,090 bytesreferences/oiioii.mddoc · 17,194 bytesreferences/prompt-craft-engine.mddoc · 10,396 bytesreferences/proven-prompts.mddoc · 79,218 bytesreferences/quality-control.mddoc · 24,719 bytesreferences/runway.mddoc · 16,914 bytesreferences/seedance-2-5-community-playbook.mddoc · 23,448 bytesreferences/seedance-domain-playbook.mddoc · 21,779 bytesreferences/seedance-longform-continuity.mddoc · 12,984 bytesreferences/seedance.mddoc · 19,227 bytesreferences/seedream.mddoc · 14,582 bytesreferences/selector.mddoc · 5,907 bytesreferences/sora.mddoc · 18,263 bytesreferences/sound-design.mddoc · 14,904 bytesreferences/stable-diffusion.mddoc · 6,359 bytesreferences/suno.mddoc · 20,914 bytesreferences/veo.mddoc · 8,788 bytesreferences/vfx-effects.mddoc · 17,145 bytesreferences/vidu.mddoc · 14,391 bytestemplates/advanced-recipes.mddoc · 9,678 bytestemplates/asset-library.mddoc · 10,046 bytestemplates/auto-pilot.mddoc · 17,473 bytestemplates/music-video.mddoc · 6,200 bytestemplates/negative-bank.mddoc · 6,835 bytestemplates/preset-packs.mddoc · 81,858 bytestemplates/storyboard.mddoc · 5,584 bytestemplates/token-efficient-mode.mddoc · 9,189 bytestemplates/user-flags.mddoc · 8,900 bytes
Read excerpt
# AI Media Generator
> **Codex compatibility:** References that still say “Claude in Chrome” or “Chrome MCP” describe legacy browser behavior. On Codex, load `chrome:control-chrome` and use the currently available Chrome tools; never invent or call legacy `mcp__Claude_in_Chrome__*`, `javascript_tool`, or `browser_batch` names.
幫使用者把想法變成高品質的 AI 生成內容 (圖片、影片、音樂),核心工作是 **寫對每個平台的 prompt** 以及 **必要時自動操作網站**。
**AI 短劇邊界:** 使用者要做 AI 短劇/漫劇、重生/系統/逆襲/隱藏大佬、分集連載或整季架構時,先由 [`ai-short-drama`](https://github.com/Hao0321/ai-short-drama) 建題材、Bible、pilot、分集狀態與 production pack;本 Skill 只接下游角色圖、場景圖、逐鏡影片/聲音 prompt 與模型執行,不自行重寫季弧。
## 🤖 Auto-Pilot Mode (超傻瓜一句話到成品)
**觸發:** 使用者說「幫我做 X」「做一個 X」「生個 X」「我要 X」這類命令式、且 X 含媒體類型 (圖/影片/音樂/MV/短片/海報/動畫) 或風格關鍵字 → **直接進 auto-pilot 不問**。
**流程 (見 [templates/auto-pilot.md](templates/auto-pilot.md) 完整版):**
1. **Intent Parser** — 一句話拆 9 slot (媒體/長度/畫面比/主題/風格/角色/場景/音訊/語言)