cross-platform-review
Skill10 starsChanged 55 days agoApache-2.0View on GitHub
跨平台统一复盘 SOP 官方套件(行业配置层 v2):各平台指标口径对齐→Top/Flop 双向归因→可执行结论。样本不足标「低置信」,只读纪律不处置。安装后被复盘分析师调用,周节奏(biz_rhythms.weekly)固定产出。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- PedroPicciani/native-mobile-designtheir own version, first seen Aug 14, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- PedroPicciani/native-mobile-design★ 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.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- client-demo-recorderSkill
- deal-flowSkill
- demo-mirrorSkill
- ripping-reverseSkill
- oss-watchSkill
- 反封锁浏览器矩阵(BrowserAct 执行面 · 可选)Skill
- 浏览器剧本自动化(Playwright 执行面)Skill
- 自适应数据采集框架(Scrapling 采集面)Skill
The file
Files
跨平台统一复盘 SOP
适用场景
- 周度跨平台内容复盘(抖音/小红书/B站/视频号/TikTok/YouTube)
- 爆款复制与扑街规避的归因分析
- 选题池与内容日历的复盘驱动调整建议
方法
- 口径对齐:播放/完播/互动/转化统一标准口径;平台原生口径差异(如 B站完播 vs 抖音完播)必须先声明再入对比表。
- 双向归因:
- Top3 爆款:拆做对了什么——题材、前 3 秒钩子、发布时段、平台流量机制、封面标题;
- Flop3 扑街:拆做错了什么——同维度对照,给出与爆款的差异点。
- 可执行结论:每条结论落到「下一条做什么/不做什么」,禁只报数据不判断;结论回写选题卡(topic_card)供排期引用。
- 低置信纪律:单平台样本 <5 条或周期 <7 天,结论标「低置信」,不下强结论。
输出契约
- 周复盘报告:口径对齐说明 + Top3/Flop3 归因表 + 可执行结论清单(每条挂题材/钩子/时段标签)。
- 所有对比数字可回溯到 account_metric 原始快照;无工具回执的关键数字标「未核实」。
- 报告为内部产物:不擅自改排期/停内容/回评论,调整建议以报告形式提交主理人。
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.

