short-drama-production SKILL.md skillA
short-drama-production from mini-yifan/open-source-video-gen-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mini-yifan/open-source-video-gen-skill/short-drama-production@git:20260906.fe772b9Pins git:20260906.fe772b9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mini-yifan/open-source-video-gen-skill
- Path
skills/short-drama-production/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260906.fe772b9, committed Sep 6, 2026
- First version recorded
- Sep 1, 2026
- Size
- 8,679 bytes
- Repository stars
- 40
- License
- a license file GitHub does not identify
Orchestrate an end-to-end short-drama or short-film production from a user's theme: approved brief, then — for multi-episode projects — a graded episode outline, then per-episode screenplay with dialogue, art reference assets, and video generation with optional music and dubbing, to a finished video. Single short films (about one minute, not a series) skip the outline stage. Use when a user wants an AI agent to turn a drama or short-film idea into a production, or to resume such a project.…
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
# 短剧/短片全流程制作 把用户提出的主题逐步做成成片。本技能只规定阶段顺序、确认关卡和文件组织；每个阶段的产出怎么写、怎么生成，由当前 Agent 自行判断。配套工具技能只提供操作手段，不规定各阶段产出的内容格式。 ## 流程 按题材规模二选一： - **多集 / 长视频**：`Brief → 分级概要 → 每集剧本与台词 → 每集美术 → 每集视频`。一次只制作当前获批的集数，第 1 集交付后按同一流程续作。 - **单部小短片**（约 1 分钟、非多集剧情）：跳过分级概要，`Brief → 剧本与台词 → 美术 → 视频`。 Brief、（多集时的）分级概要、剧本+台词、美术各有一个用户确认关卡，成片交付后再确认修改方向。用户未明确通过不进入下一阶段，沉默不算通过。仅当用户明确要求跳过或全自动执行时才可合并关卡。 用户提出修改时，只修改当前阶段并重新确认；上游通过的内容被修改后，把受影响的下游状态改回 `待更新`，不沿用旧内容。 各阶段要点： 1. **Brief**：从主题出发与用户对齐方向；用户没有提供的信息（剧名、集数、时长、平台、风格、禁区等）写 `[待定]`，不用大量提问阻断起稿。Brief 只确认方向，不写分集剧情。 2. **分级概要**（仅多集）：以获批 Brief 为边界，把全部集数写进同一份概要文件；集数和单集时长服从 Brief，不自行设定默认值。 3. **剧本与台词**：写可演的剧本与台词，并产出视频生产用的字幕台词时间轴。剧本是剧情与台词的唯一可编辑真源，时间轴是从剧本生成的投影；时间轴发现超时或表演空间不足时，先回剧本改，再重建时间轴，不只改时间轴。若修改会改变已通过 Brief 或概要中的关键设定，停下来向用户说明，不静默改写上游。 4. **美术**：从剧本提取需要锁定的形象资产（人物/形象、关键道具、主要场景），先写清资产定义，再逐张生成、逐张验收；先出主要形象的基准参考，其余资产和装扮变体拿已验收的基准图当参考。 5. **视频**：把剧本与时间轴拆成生成片段，逐段写提示词，先试产一个片段校准风格与参考策略，再批量生成；H3 片段自带音轨，配乐与配音是可选增强；拼接出无配乐母版与配乐版成片，交付并询问修改方向。 ## 工程红线（踩过的坑） 1. 不把 Token、SSH 密码、服务器密码写进项目文件、提示词或本技能。 2. 角色唯一性是视频生成硬指标：除非剧情明确需要分身、克隆、镜中人等，同一具名角色在同一画面只能出现一次。每段提示词先正向精确计数，再补负向禁令；验收时逐段抽帧检查，任何一帧出现同一角色的多个实体、相同脸群演或无叙事依据的镜像副本，该片段必须重生成。 …
Read the whole file at its exact version.
How to install
mdr add mini-yifan/open-source-video-gen-skill/short-drama-production@sha256:1a1142730b8dea1dThe line at the top of this page pins the label git:20260906.fe772b9, 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_edditgvqzblwrxpn)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 1, 2026 and Sep 6, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.fe772b9 latest | 2026-09-06 | fe772b9 | 8,679 B | A | view · diff |
| git:20260904.2bc353a | 2026-09-04 | 2bc353a | 23,632 B | A | view · diff |
| git:20260902.e686e77 | 2026-09-02 | e686e77 | 23,560 B | A | view · diff |
| git:20260901.66a8add | 2026-09-01 | 66a8add | 23,243 B | A | view · diff |
| git:20260901.d472b7a | 2026-09-01 | d472b7a | 23,127 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 (8679 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
mini-yifan/open-source-video-gen-skill · 40 stars · license a license file GitHub does not identify · pushed 2026-09-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_edditgvqzblwrxpn GET https://markdownregistry.com/api/v1/resolve?ref=mini-yifan/open-source-video-gen-skill/short-drama-production GET https://markdownregistry.com/api/v1/blob/1a1142730b8dea1d429e77fd53d17877bada1a3fe02dad7d8b3491d544e55cd0
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.