来源信息
- 仓库
- LgrappaG/Workflows-Agents
- 最近来源活动
- 2026年3月29日 21:56
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 2
- 分支
- 0
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- analytics-user-segmentation
- description
- Segment players into cohorts for analysis
- risk
- low
- source
- workspace
- date_added
- 2026-03-24
- usage
- Whale vs casual player segmentation, region-based content delivery, retention cohort analysis (churned after day 3), VIP user targeting for offers
- avoid
- Computing segments on every single event causing cascading latency, using stale event data (>5min old) inflating segment size estimates, ignoring consent flags including non-opted users, hard-coding segment logic without versioning causing AB test data corruption
- mandates
- Segment accuracy >=95%, cohort refresh latency <5min from event, max 1000 concurrent named segments, consent-verified membership only
- response
- Define segments with SQL-like conditions (e, g, , revenue>100 AND retention_day_7>=0, 6) stored in Segment Registry, versioning each definition for audit trails
# Analytics User Segmentation
Segment players into cohorts for analysis
## Risk Level
**LOW**
## Core Rules
- Implement properly
- Test thoroughly
- Validate results
## Response Pattern
1. Design appropriate approach
2. Implement solution
3. Test edge cases
4. Validate quality
## Usage Contexts
- Cohort analysis
- Development workflows
## What NOT to Do
- Arbitrary segmentation
- Incomplete testing
- Deploy without validation
在 GitHub 查看