agentleFS
yuntao1122yuntao1122/ai-media-skills/skills/curator/SKILL.md

curator

Skill0 starsChanged 25 days agoMITView on GitHub

对素材池做筛选:语义去重、四维度质量打分、分级精选,输出精选集与带理由的淘汰清单。当用户说"素材太多帮我挑""筛选一下""哪些能用"时使用。通常接在 hunter 之后。

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. KarimJebara/Curator★ 8same name
    2. Quarktex/qcobrain★ 4same 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 repository3 other files it gives its agents.

The file

Files
SKILL.md

Curator · 素材筛选

什么时候用

已经有一批素材(hunter 的产出,或用户自己丢过来的一堆链接),需要挑出真正能用的。输出是精选集 + 淘汰清单,不做内容创作。

输入

  • 素材清单(hunter 格式,或一批链接/文档)
  • 用途:写文章 / 做视频 / 做图片(决定筛选标准权重)
  • 精选数量目标(默认 5–10 条)

工作流

1. 语义去重

hunter 只做了粗去重,这里做语义级去重:不同标题但讲同一件事、同一数据的,合并为一条,保留信息最全、来源最权威的版本,备注"合并了 X 条同类"。

2. 四维打分

每条素材按四个维度打 1–5 分:

维度5 分长什么样1 分长什么样
相关性直接回答主题的核心问题擦边、标题党
权威性官方、一手、权威媒体营销号、匿名帖
时效性最新、可验证时间过时、时间不明
独特性有别处没有的信息/视角全网通稿、人人都在转

总分 20。16 分以上"必用",11–15 分"备选",10 分以下"淘汰"。

3. 分级输出

  • 必用:按逻辑顺序排好,直接可用于创作。
  • 备选:注明适合用在哪个部分。
  • 淘汰:每条一句话理由(如"2023 年旧数据,已被官方新口径取代")。

4. 缺口提醒

如果必用素材撑不起用户的用途(如"想做视频但缺案例"),明确指出缺什么、建议补什么——而不是硬凑。

输出模板

# 精选:<主题>
去重:<N> 条 → <M> 条;精选目标 <K> 条

## 必用(<n> 条)
| # | 标题 | 来源 | 得分 | 用途建议 |
|---|---|---|---|---|

## 备选(<n> 条)
| # | 标题 | 来源 | 得分 | 适合用在 |

## 淘汰(<n> 条)
| 标题 | 理由 |

## 缺口
- <缺什么、建议怎么补>

注意事项

  • 打分要敢给低分: curated 的价值就在于敢淘汰,全部"必用"等于没筛。
  • 权威性和时效性冲突时(如官方旧文档 vs 媒体新报道),按用途定:做教程看权威,做资讯看时效,并在备注里写清取舍。
  • 淘汰理由必须具体,"质量不高"不算理由。

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.