wan-media-generation SKILL.md skillA
wan-media-generation from evovexai/evoflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add evovexai/evoflow/wan-media-generation@git:20261028.1756e02Pins git:20261028.1756e02 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- evovexai/evoflow
- Path
skills/public/wan-media-generation/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261028.1756e02, committed Oct 28, 2026
- First version recorded
- Sep 12, 2026
- Size
- 4,650 bytes
- Repository stars
- 611
- License
- a license file GitHub does not identify
通义万相 / DashScope（wan）生图/改图/生视频。用户指定万相、wan、DashScope、通义，或已配 DASHSCOPE_API_KEY 时使用。 ⏰ 触发：「用万相生图/生视频」「DashScope wan 画图」等。 对话内快速单张/单段优先 platform → media.*（model=wan2.7-*）；多步流水线再用本技能 scripts。 火山生图请用 byted-ark-seedream-skill；火山短片请用 media-production。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 通义万相 / DashScope（wan）媒体生成 Harness provider 名 **`wan`**。运行时与平台 `media.*` **共用** `providers/factory` + `dashscope_wan`（按模型号选协议）。 ## 优先路径（对话内） 单张图 / 单段视频 → **`platform`**： 1. `media.catalog`（看模型与凭据） 2. `media.generate_image` / `media.generate_video`（`confirm=true`，`model=wan2.7-image` 或 `wan2.7-i2v`） 3. 视频再 `media.task_wait` 本技能 `wan_api.py`：用户明确要求终端脚本、批量、或要 `--last-frame-url` / `--audio-url` 等细参时再用。 ## 模型与协议（默认 2.7） | 模型 | 能力 | 协议 | |------|------|------| | `wan2.7-image` / `wan2.7-image-pro` | 文生图 / 图生图 | multimodal-generation **同步** | | `wan2.7-i2v` | 图生视频（首帧/首尾帧 + 可选 driving_audio） | video-synthesis **异步** `input.media[]` | | `wan2.7-t2v` | 文生视频 | 同上异步 | | `wan2.6-t2i` / `wan2.6-i2v` / `wan2.6-t2v` | 兼容旧配额 | legacy text2image / `img_url` | 未传 `--model` 时脚本与平台一致：图默认 `wan2.7-image`，视频默认 `wan2.7-i2v` / `wan2.7-t2v`。 ## 官方文档 | 能力 | 文档 | |------|------| | 万相 2.7 图像 | [图像生成与编辑](https://help.aliyun.com/zh/model-studio/wan-image-generation-and-editing-api-reference) | | 万相 2.7 图生视频 | [图生视频 API](https://help.aliyun.com/zh/model-studio/wan-i2v-api-reference) | | 万相视频总览 | [视频生成 API](https://help.aliyun.com/zh/model-studio/wan-video-generation-api-reference) | …
Read the whole file at its exact version.
How to install
mdr add evovexai/evoflow/wan-media-generation@sha256:4168f01bf631792dThe line at the top of this page pins the label git:20261028.1756e02, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_bbkccly4ix3sojk3)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 12, 2026 and Oct 28, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.1756e02 latest | 2026-10-28 | 1756e02 | 4,650 B | A | view · diff |
| git:20261027.9d5beef | 2026-10-27 | 9d5beef | 4,597 B | A | view · diff |
| git:20260912.6c490fd | 2026-09-12 | 6c490fd | 2,944 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4650 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
evovexai/evoflow · 611 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bbkccly4ix3sojk3 GET https://markdownregistry.com/api/v1/resolve?ref=evovexai/evoflow/wan-media-generation GET https://markdownregistry.com/api/v1/blob/4168f01bf631792d079207b0322c95eaac0efec79515704456b6fb737705a88b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.