跳到正文
FunCoding

media-production

Generate and edit images, vector artwork, photos, audio and video; inspect results and deliver finished artifacts.

Star
17,571
许可证
MIT
最近提交
2026年10月12日

skills/agent/media-production/SKILL.md

在 GitHub 上查看

Media Production

  1. Establish the desired output, duration, aspect ratio and supplied reference material. A single image or speech request usually needs only its generation tool.
  2. For hosted image generation, use media_production.image.generate with the desired prompt and output options; Core resolves tool settings, inheriting the active conversation provider by default. If selection_required is returned, ask the owner which available provider to use; never silently switch accounts. Use configure only when they request a saved preference. Inspect capabilities.defaults when setup needs diagnosis. Reserve generateWithModel for an explicitly owner-requested provider/model; never pick an older model from memory or bypass a default after an error.
  3. Generate image assets with media_production.image. Use existing music_audio speech tools for narration and owner-supplied audio or video clips for other media assets.
  4. For local production, use media_production.photocraft for layered raster edits, vectorcraft for vector artwork, hyperframes for social videos and motion graphics, filmcraft for timelines, and lightcraft for photo development. These tools run headlessly; PhotoCraft desktop control is optional. For Craft tools, discover commands and parameter schemas before edits, inspect the source, and use returned object/media IDs instead of guessing. Ordinary edits produce new artifacts while preserving originals. Keep referenced media available and use absolute asset paths. Select persistent LightCraft libraries only when the owner requests library work.
  5. For an authored social video or motion graphic, establish a short storyboard and consistent visual direction: one main idea per scene, readable typography at phone size, deliberate spacing, a focused palette, and useful visual assets. Match pacing to the brief; avoid walls of small text, repeated generic panels and gratuitous effects. Use hyperframes.create for a new project and the file tool to author its HTML, CSS and scene timelines. Look for suitable catalog components before inventing complex effects. Preserve supplied source by working in a copy. Tool guidance owns the composition and animation contract.
  6. Batch independent grounding reads and author related files together. Use hyperframes.inspect to ground scene timing, then hyperframes.check with options.mode=lint to catch source errors cheaply. During repairs use mode=targeted with affected times and preview neighboring frames; verify text fit, safe margins and continuity. On the final source run the default full check and require scope=full, complete=true and checks.ok=true. Targeted/lint success is partial evidence. Independent checks and previews may run together once source is stable; never edit files while they are being inspected. Reuse current-run evidence and successful checks while relevant source/assets are unchanged. Render delivery quality once and review that exact video for motion, pacing and audio; use a separate draft only when useful for unresolved motion. Rerender only after changes or an observed defect. Passing checks or looking at a still frame alone cannot establish that a video is ready to share.
  7. Preview edited artwork and representative timeline/composition positions. Use existing FFmpeg and FFprobe tools for simple composition, conversion and validation. Inspect frames and audio/duration before claiming the result is verified. Wait for background renders to complete before delivery.
  8. Generated and edited artifacts are attached automatically. Attach other composed/local files through file_system.file.attach so the owner receives a player or download. Do not expose provider URLs, credentials or base64 in chat.

相似的 Skill

blender-motion-state-inspection

AFaffaan-m/ECC278k近 7 天新增 4,046 个 star

官方

slack-gif-creator

ANanthropics/skills181k近 7 天新增 1,119 个 star

精选

algorithmic-art

用 p5.js 生成流场和粒子系统,通过种子随机性创作原创算法艺术。

ANanthropics/skills181k近 7 天新增 1,119 个 star

thinking-out-loud

SHShubhamsaboo/awesome-llm-apps141k近 7 天新增 808 个 star

moneyprinterturbo-video

HAharry0703/MoneyPrinterTurbo130k近 7 天新增 1,722 个 star

complain

PApaperclipai/paperclip101k近 7 天新增 2,948 个 star