character-video-collection SKILL.md skillA
character-video-collection from shenrui-ma/video-regen-recipes is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shenrui-ma/video-regen-recipes/character-video-collection@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shenrui-ma/video-regen-recipes
- Path
templates/character-showcase/video-collection/SKILL.md- Versions recorded
- 2
- Latest version
- v0.1.0, committed Sep 16, 2026
- First version recorded
- Sep 11, 2026
- Size
- 4,206 bytes
- Repository stars
- 9
- License
- MIT
从一句话制作角色动态立绘合集；使用 ComfyUI 生成角色参考图和首帧图，本地 MiniMax H3 逐段 I2V，再剪辑视频合集或原图→对应视频混剪。也处理用户明确要求的已有视频重剪。.
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
# 角色视频合集 原创配方：**Shenrui Ma（四倍体果蝇）**。交付成片、实际输入清单和生成记录。完整链路是“角色设定 → ComfyUI 参考图/首帧图 → 独立 H3 片段 → 合集剪辑”。 ## 按顺序执行 1. **接住一句话。** 沿用用户指定角色、图片及已有项目设定。只说角色名也可以开始：默认三个独立镜头、固定服装、轻微自然动作，每段目标约10秒，最终1080×1920、60fps。默认 D 视频合集；明确要“原图再动起来”时选 C。把默认值写入当前项目计划，不用逐项追问。没有角色且无项目身份时，仅询问角色；不要擅自选备用人物。 2. **分清新生成和重剪。** 用户明确要剪已有视频、复用画面或只换音乐时，建立显式素材列表后跳到后期。新的角色需求必须生成对应素材。不要用旧视频冒充新结果，缺少输入也不要偷偷换版本。 3. **准备环境。** 读[生成链路](references/generation.md)，通过关联 Toolkit 获取 `h3-i2v-live-portrait`，先确认本地 ComfyUI、模型和节点可用；用户指定服务器才走远程连接与文件传输。新建项目目录，源素材只读。需要适配时核对当前安装版本的真实节点，不能编造节点或直接替换成 Ref2VA。 4. **生成图。** 调用 [ComfyUI 参考图 Skill](../../../skills/comfyui-reference-images/SKILL.md)，准备身份参考与每镜头首帧。按现有模型选择 SDXL/Anima，缺模型沿用该 Skill 的 Civitai/Hugging Face 发现、兼容性核对及下载流程。使用[图像提示词](prompts/reference-image.txt)，先完成一张，再批量完成其余；用户自己的可用首帧直接登记，不强制重生。 5. **生成动态片段。** 使用[动作提示词](prompts/i2v-motion.txt)，逐图绑定首帧 I2V，保存每条 `prompt_id`、工作流、seed 和输出文件。各镜头独立，不接前一条的 latent，不套动作重演参考视频。先确认首条技术结果再继续；断线查询原任务，失败只重试该镜头。不要对既有 H3 参数或输出帧数做未经证实的假设。 6. **锁定剪辑清单。** C 模式记录 `图1→视频1→图2→视频2`，每对共用 `pair_id`；D 只列视频。按真实媒体信息填入源时长、裁切、速度及相对路径。用户调整顺序时整对移动。按[剪辑规则](references/editing.md)选择布局与音频，不套图片动画到视频上。 …
Read the whole file at its exact version.
How to install
mdr add shenrui-ma/video-regen-recipes/character-video-collection@sha256:80fcb012e2c6661bThe line at the top of this page pins the label v0.1.0, 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_q3e3pkavjfmvbcmg)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 11, 2026 and Sep 16, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-09-16 | 1d6c844 | 4,206 B | A | view · diff |
| git:20260911.150af77 | 2026-09-11 | 150af77 | 4,078 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 (4206 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
shenrui-ma/video-regen-recipes · 9 stars · license MIT · pushed 2026-09-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q3e3pkavjfmvbcmg GET https://markdownregistry.com/api/v1/resolve?ref=shenrui-ma/video-regen-recipes/character-video-collection GET https://markdownregistry.com/api/v1/blob/80fcb012e2c6661b07f30598ee9b610c36b004286a4da02f8b47aa6b76f08064
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.