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

ad-review

Skill6 starsChanged 29 days agoMITView on GitHub

交付前自审整片写自审文件;收到反馈后返修、归档旧版、交付。每次成片出来之后用;用户说"不好"但说不清时也用。产出:final/自审.md、归档的旧版、需求文档里这一轮的条目。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. alexandremendoncaalvaro/CorridorKey-Runtime★ 755same name
    2. AY-kkk/ad-gtm★ 1same 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.

  • In this repository7 other files it gives its agents.

The file

Files
SKILL.md

[任务] 自己先当观众和审片员看一遍,问题按影响排序写下来,能修的修完再交。

[前置] 成片过了门禁。

[自审] 派审片员拿成片、产品造型表、分段表(期望的旁白和台词、每段的 imperfections),返回带时间码的清单;清单没回来不交片。 先当观众从头看一遍:开头三秒抓不抓人;看完记不记得住产品和那一两个点;产品时刻够不够好看;有没有哪一下"像 AI"、哪一段画面在不动。这一条门禁量不出来,只能你看。 再看三样:每秒一帧的总览;全片产品对比表(产品最清楚的几帧和产品图并排);音轨落点表(剪辑/audio_report.txt)。 写 final/自审.md:一句结论和主因;问题表(时间码、哪一项、看到或量到什么、证据、修法、处理),按对观众的影响排;要用户定的;门禁输出原样贴;每轮返修在末尾加一节"返修结果"。 主观的(够不够高级、音乐好不好听)不替用户判断:给数,列成问题、带选项、推荐在前;用户授权全权时按推荐做,不问。

[返修] 用户点名一处先查同类(同一张参考的其他用处、同一类音效、同一条处理链)一起改。 正式版再跑门禁,派审片员只核改动点和它前后两秒,不重查全片;数写进"返修结果":用户指出的、根因、改法、量出来的数、没改的和为什么。

[交付] final/ 每个规格只留一个成片,加一份自审;上一版移进 _旧版_vN。交付说明分开写"你指出的"和"我自己改的"、没改的和为什么、替他定了什么、这一版花了多少积分(估价和流水各一个数);按需求文档的 AI 标识写一句发布时要做什么。 成片放进放映室给他看(/ad-studio)。放映室只放成片,不放过程稿。

[门禁] 自审文件随片;每条用户反馈在需求文档里有 R- 条目和状态。

[完成标准] 用户看完说过关;或用户授权全权时,自审里没有"必须修"的项。

[文件结构] ad-review/ └── 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.