agentleFS
feicaiclubfeicaiclub/ad-storyboarder/.claude/skills/ad-edit/SKILL.md

ad-edit

Skill6 starsChanged 29 days agoMITView on GitHub

写剪辑表、总装成片、做声音,多个交付规格各出一版;先出草稿量数再出正式版。每段过审之后用;返修改剪辑和声音也用。产出:剪辑/ 里的剪辑表和草稿,final/ 里每个规格的成片。

The file

Files
SKILL.md

[任务] 剪辑服务创意:节奏、卡点、产品时刻停多久、配乐和音效怎么配,都按这条片子定。配乐、音效、旁白在 Higgsfield 上生成(adapters/higgsfield.py audio),拼接、混音、响度在本地做。

[前置] 入片的段都已过审。

[剪辑表] 写法见 .claude/tools/剪辑表示例.py;真的剪辑表放 剪辑/剪辑表.py(竖版另写就叫 剪辑表_竖版.py),总装和放映室都读它。 片内切点前后 2 帧不能当入出点(总装会报)。 画面里要读清的字(品牌名、slogan、读数)默认由剪辑程序渲染,字一定对;创意要它在画面里生成出来也行,出完逐字核对。 画面处理链默认不加(LOOK = "none");要加什么效果写在剪辑表里,产品的颜色和纹理不能变,改了处理链产品对比表重拼一次。 多个交付规格:同一份剪辑表用 --size、--frame、--target 覆盖出各版;竖版构图不同的另写一份剪辑表。

[总装] python3 .claude/tools/assemble.py --edl 剪辑/剪辑表.py --out final/片名_主版.mp4 [--draft]:画面按整帧截,声音按画面实际帧数摆;按内容哈希缓存每段,只重渲改过的;画幅、响度目标写在剪辑表顶上(来自需求文档)。改声音不碰画面缓存,改画面不动音轨。

[门禁] 每个规格的草稿和正式版都跑 python3 .claude/tools/gate.py final/片名_主版.mp4 [--expect 规格数]:同步差 ≤1 帧;无连续 2 秒低于 -45 dBFS 的无声洞(刻意的用 --allow 列出来);无单秒高于 -6 dBFS;整合响度按剪辑表顶上的目标 ±1、真峰值 ≤-1.5;final 里成片数等于交付规格数。不过不交。

[完成标准] 门禁输出贴进交付说明;final/ 每个规格一个文件。

[文件结构] ad-edit/ └── SKILL.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.