yanhua1010/self-media-content-workflow / skills/self-media-content-analytics
self-media-content-analytics
Verified分析单篇、系列、周度或月度自媒体数据并形成可执行复盘。用于读取平台后台截图、CSV、表格、公开链接或用户提供的数据,计算关注效率和深度互动,比较同平台基线,归因选题、标题、封面、开头、结构、发布时间、标签和行动,并输出加码、改包装、再适配、停止或继续收集样本的决策。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.8 KB |
| agents/openai.yaml | config | 259 B |
| assets/content-review-template.md | markdown | 1008 B |
| assets/metrics-ledger-template.md | markdown | 538 B |
| assets/monthly-review-template.md | markdown | 733 B |
| assets/weekly-review-template.md | markdown | 710 B |
| references/metrics.md | markdown | 1.4 KB |
references/metrics.md
View on GitHub# 指标定义与比较规则
## 原始字段
| 字段 | 说明 |
|---|---|
| 曝光 | 内容被展示的次数 |
| 阅读或播放 | 用户实际打开或播放的次数 |
| 完播 | 平台提供的完成率或完成次数 |
| 点赞 | 轻量正反馈 |
| 评论 | 公开讨论和问题 |
| 收藏 | 延迟使用价值 |
| 分享 | 主动传播 |
| 新关注 | 内容带来的新增关注,平台未提供时留空 |
| 转化 | 注册、咨询、购买等明确目标行为 |
| 收入 | 可归因收入,无法归因时留空 |
| 制作分钟 | 从研究到交付的人工投入 |
## 派生指标
- 每千浏览新关注 = 新关注 ÷ 阅读或播放 × 1000。
- 深度互动率 = 评论、收藏、分享之和 ÷ 阅读或播放。
- 点击率 = 阅读或播放 ÷ 曝光,仅在字段定义一致时计算。
- 转化率 = 转化 ÷ 指定分母。必须注明分母。
- 单个有效成品时间 = 制作分钟 ÷ 达到成功标准的成品数。
分母为 0 或字段缺失时留空,不填 0。
## 比较规则
- 只比较同平台、同内容类型和相近观察窗口。
- 优先使用中位数和 P75,避免平均数被爆款拉高。
- 跨平台只比较标准化指标,不比较原始播放量。
- 商单和自然内容分开。
- 至少 3 个同类样本才描述初步模式,至少 4 个样本才考虑调整长期比例。
- 热点、投流、账号体量和平台推荐可能造成混杂,无法排除时标记不确定。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |