director
Skill0 starsChanged 25 days agoMITView on GitHub
AI 视频制作工作流:定结构、写分镜脚本、准备视觉素材、AI 片段生成、组装剪辑、成片检查。当用户要做短视频、解说视频、混剪时使用。可串联 hunter / curator / imager 的产出。
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Palatine-Labs/conisotheir own version, first seen Nov 15, 2026
- hoodini/ai-agents-skillstheir own version, first seen Oct 25, 2026
- bloxy-studios/shorts-studiotheir own version, first seen Oct 1, 2026
- roughboy99/aiautobase-claude-skillstheir own version, first seen Aug 10, 2026
- s1dashu/directortheir own version, first seen Aug 10, 2026
- colinsurprenant/directortheir own version, first seen Jul 7, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- s1dashu/director★ 737same name
- hoodini/ai-agents-skills★ 295same name
- Palatine-Labs/coniso★ 17same name
- colinsurprenant/director★ 15same name
- roughboy99/aiautobase-claude-skills★ 2same name
- bloxy-studios/shorts-studio★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
Director · AI 视频工作流
什么时候用
用户说"做个视频""把这期内容剪成短视频""写个分镜"时。默认做短视频(1–3 分钟);长视频先问一句。
输入
- 主题(一句话)
- 时长:默认 60–90 秒
- 平台:抖音/视频号(9:16)/ B站(16:9)/ 小红书(3:4)——决定比例和节奏
- 素材:已有文案/素材(可来自 hunter+curator),或从零开始
- 配音:AI 配音 / 真人 / 纯字幕+音乐
工作流
1. 定结构(先写骨架,再填肉)
短视频三段式,按 90 秒分配:
| 段 | 时长 | 干什么 |
| 钩子 | 0–5 秒 | 一句话留人:反常识、提问、结果前置。写 3 个备选 |
| 正文 | 5–75 秒 | 3 个点,每个点 1 个论据,多一个都砍 |
| 结尾 | 75–90 秒 | 总结 + 行动号召(关注/评论/收藏三选一,别全要) |
2. 写分镜脚本
用分镜表,每镜一行:
| 镜号 | 时长 | 画面 | 文案/配音 | 音效/音乐 |
| 1 | 0–5s | <画面描述> | <配音文案> | <音效> |
文案按口语写:短句、每句一个意思,90 秒约 220–260 字。画面描述要具体到 imager 能直接画的程度。
3. 准备视觉素材
- 静态图:调
imager按分镜批量生成,风格词全片统一。 - 动态片段:图生视频时 prompt 只描述"运镜+动作"(如"缓慢推镜,云层流动"),不要重复描述画面内容;文生视频先出关键帧确认再批量。
- 现成素材:注明来源,可商用的才用。
4. 组装剪辑
顺序:粗剪(按分镜表拼)→ 配音对齐 → 字幕 → 音乐(音量压到人声的 20–30%)→ 封面(用 imager 做 16:9/9:16 各一版,标题字后期叠)。
5. 成片检查清单
- 前 3 秒有没有钩子(静音刷到也能看懂吗)
- 字幕错别字(逐字过一遍,AI 配音尤其注意多音字)
- 音乐版权(商用授权/平台曲库)
- 画面风格统一,无穿帮帧
- 结尾行动号召只有一个
- 导出参数:平台推荐分辨率和码率
和其它 skill 的串联
hunter(搜集选题素材)→ curator(筛出 3 个论据)→ director(写分镜)
→ imager(按分镜做图)
→ 成片注意事项
- 分镜表是导演和所有后续步骤的合同:分镜不定,不要开生成,返工成本最高。
- AI 视频片段目前适合做空镜、转场、氛围镜头;有人物特写和复杂动作时,优先用静态图+运镜代替。
- 文案先定稿再配音,配音定了再卡剪辑——倒着返工最贵。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

