从文字或图像生成3D模型,并与目录素材搭配使用。在Blender中检查形状、材质、大小和接地情况,记录生成条件、来源及费用,再将素材加入场景。
- 根据文字生成独特的3D道具
- 将概念图中的物体转为3D模型
- 用目录中的植被和岩石填充背景
按需求查找背景音乐、音效、图片和图标,优先使用已有素材与共享缓存,必要时搜索HeyGen,并保存到本地、登记素材台账,供多个项目重复使用。
Agent Media OS — resolve any media need (BGM, SFX, image, icon) into a frozen local file + ledger record. One verb (`resolve`) handles the full cascade — project cache, global cache, HeyGen catalog search, freeze, register. Keeps search noise on disk, hands the agent a path. Use when a composition needs background music, sound effects, images, or icons.
用文字描述所需素材,media-use便会查找背景音乐、音效、图片或图标,并返回可用的本地文件路径。它依次检查项目中已登记的素材、现有的assets/目录和共享缓存,必要时再搜索HeyGen。获取的文件会保存到本地,并登记到素材台账和清单。搜索候选、评分及来源信息会保留在磁盘上。
适合为视频准备声音和图片,也适合整理手头素材以便重复使用。同样的需求可以直接复用共享缓存中的文件,避免重复下载。还可将现有assets/目录中的素材批量导入台账。
assets/中的素材,列出时长和图片尺寸。”运行脚本需要Node.js,读取素材信息使用ffprobe。从HeyGen获取素材时,需要v0.1.6或更高版本的heygen CLI,并用有效的API密钥完成认证。素材清单可在.media/index.md中查看。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 仅根据 SKILL.md 的内容,从 4 个方面进行了评估。星标数和热度不计入评估。
总分按每项 A=25 分、B=15 分、C=5 分相加。 由 AI(OpenAI Codex)于 2026年10月23日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
Resolve media needs into frozen local files. One verb, four types, zero context noise.
Call resolve whenever a composition needs media — background music, sound effects, images, or icons. media-use searches the HeyGen catalog, downloads the best match, freezes it locally, and registers it in a manifest. The agent gets back one line; all search noise stays on disk.
node <SKILL_DIR>/scripts/resolve.mjs --type <type> --intent "<description>" --project <dir>
Returns one line: resolved <id> → <path> (<type>, <metadata>)
| Type | What it finds | Provider |
|---|---|---|
bgm | Background music | HeyGen audio catalog (10k+ tracks) |
sfx | Sound effects | Bundled 19-file library + HeyGen catalog |
image | Photos, backgrounds | HeyGen asset search (75k+ vectors) |
icon | Icons, logos | HeyGen asset search (type=icon) |
# Background music
node <SKILL_DIR>/scripts/resolve.mjs --type bgm --intent "upbeat tech launch" --project .
# → resolved bgm_001 → .media/audio/bgm/bgm_001.mp3 (bgm, 25s)
# Sound effect
node <SKILL_DIR>/scripts/resolve.mjs --type sfx --intent "whoosh" --project .
# → resolved sfx_001 → .media/audio/sfx/sfx_001.mp3 (sfx, 0.57s)
# Image
node <SKILL_DIR>/scripts/resolve.mjs --type image --intent "gradient tech background" --project .
# → resolved image_001 → .media/images/image_001.jpg (image)
# Icon
node <SKILL_DIR>/scripts/resolve.mjs --type icon --intent "rocket" --project .
# → resolved icon_001 → .media/images/icon_001.png (icon, transparent)
| Flag | Description |
|---|---|
--type, -t | Media type: bgm, sfx, image, icon |
--intent, -i | What you need (natural language) |
--entity, -e | Entity name for cache matching (optional) |
--project, -p | Project directory (default: .) |
--adopt | Bulk-import existing assets/ into manifest |
--json | Output JSON instead of one-line result |
.media/manifest.jsonl for exact-prompt matchassets/ directory for unregistered files matching the need~/.media/ for reusable asset.media/<type>/, register in manifest, regenerate index.mdThe agent gets back one line. Candidates, scores, provenance stay on disk.
Most HyperFrames projects already have assets in assets/. media-use adopts them:
node <SKILL_DIR>/scripts/resolve.mjs --adopt --project .
# → adopted 9 assets from assets/
# bgm_001 → assets/bgm/mango-fizz.mp3 (bgm, 146.6s)
# image_001 → assets/images/avatar.jpg (image, 400×400)
ffprobe extracts real duration and dimensions. During resolve, unregistered files in assets/ matching the intent are adopted on the fly.
After resolve or adopt, read .media/index.md for the full inventory:
# .media · 4 assets
id type dur dims path description
bgm_001 bgm 25s — .media/audio/bgm/bgm_001.mp3 upbeat tech launch
sfx_001 sfx 0.6s — .media/audio/sfx/sfx_001.mp3 whoosh
image_001 image — 1920×1080 .media/images/image_001.jpg gradient tech background
icon_001 icon — 200×200 .media/images/icon_001.png rocket
Assets are cached automatically on resolve. Subsequent resolves for the same prompt hit the global cache at ~/.media/ — no re-download, no provider call. Promote an asset explicitly with organize --promote <id> to make it reusable across all projects.
.media/manifest.jsonl — machine SSOT, one JSON record per line.media/index.md — agent-readable table (id, type, dur, dims, path, description)~/.media/ — global cross-project reuse cache (content-addressed, SHA-256)| Tool | Purpose | Required? |
|---|---|---|
ffprobe | Probe duration, dimensions, codec on adopt | Yes |
heygen | Audio catalog, asset search | For providers |
Install the heygen CLI (single static binary, no runtime) and authenticate:
curl -fsSL https://static.heygen.ai/cli/install.sh | bash # installs latest to ~/.local/bin
heygen update # if already installed: needs >= v0.1.6
export HEYGEN_API_KEY=<your-key> # or: heygen auth login --key <key>
Requires heygen >= v0.1.6 — the providers tag requests with the allowlisted --headers 'X-HeyGen-Client-Source: media-use' flag, added in v0.1.6. asset search is a pre-launch command hidden from heygen --help, but it runs. Without a heygen on PATH (or a valid key) the providers print a one-line diagnostic to stderr and resolve falls through to "no provider could resolve".
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
从文字或图像生成3D模型,并与目录素材搭配使用。在Blender中检查形状、材质、大小和接地情况,记录生成条件、来源及费用,再将素材加入场景。
使用ACE-Step 1.5生成视频背景音乐和带歌词的歌曲,可指定曲风、时长、速度与调性,也支持改编参考音频,以及从混合音频中分离人声或乐器。
使用ElevenLabs创建语音对话助手或角色,配置声音、应答规则、语言模型及外部工具,支持嵌入网站,并通过Twilio集成设置电话外呼。
根据文字描述或参考图片生成AI视频,并按用途和费用选择生成服务。支持设置画面比例、查看生成进度,以及通过Gemini Omni对话修改现有视频。
根据文字或参考图像生成AI视频,并按用途、可用服务和预算选择模型。可制作社交平台竖屏短片、让商品照片动起来,也可通过对话编辑已有片段。
通过Atlas Cloud使用多种模型生成和编辑图像与视频,只需一个API密钥,即可保存生成素材,以及所用模型、提交设置和预估费用等记录。