‹ 首页

analyze-performance

@techwolf-ai · 收录于 1 周前

Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.

场景内容复盘效果优化

适合你，如果你运营社媒账号，想从数据中提炼爆款规律

/ 下载安装
analyze-performance.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add techwolf-ai/ai-first-toolkit/analyze-performance
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- techwolf-ai/ai-first-toolkit/analyze-performance
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify techwolf-ai/ai-first-toolkit/analyze-performance
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
90GitHub stars
~529上下文体积 · 单文件
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · 8b3107b

Analyze Content Performance

Identify patterns in high-performing posts to inform future content strategy.

Process
  1. Run ./scripts/print-published.sh linkedin-post to read all published LinkedIn posts
  2. Extract posts that have engagement data (engagement.reactions, engagement.views, etc.)
  3. Analyze patterns across high-performing vs low-performing posts
Analysis Dimensions
Hook Analysis
  • What hook styles correlate with higher engagement?
  • Personal anecdote vs company experience vs surprising data vs news hook?
  • First 210 characters (LinkedIn cutoff) - what patterns work?
Content Characteristics
  • Word count vs engagement correlation
  • Use of concrete examples vs abstract concepts
  • Presence of frameworks or mental models
  • Use of lists/structure vs flowing narrative
Topic Analysis
  • Which tags correlate with higher engagement?
  • Which themes resonate most?
  • Timing patterns (if publishedDate available)
Structural Patterns
  • Opening style (question, statement, story)
  • Closing style (call-to-action, reflection, question)
  • Paragraph length and density
Performance Tiers

Categorize posts by reaction count:

  • High performers: 100+ reactions
  • Medium performers: 30-99 reactions
  • Lower performers: <30 reactions
Output Format

Provide:

  1. Summary statistics - Total posts analyzed, average engagement by tier
  2. Top performers - List highest-engagement posts with their key characteristics
  3. Pattern insights - What distinguishes high vs lower performers?
  4. Recommendations - Actionable suggestions for future content
Example Analysis Output
## Performance Summary
- Posts analyzed: 12 (with engagement data)
- High performers (100+): 3 posts
- Medium performers (30-99): 5 posts
- Lower performers (<30): 4 posts

## Top Performers
1. "Title" - 245 reactions
   - Hook: Personal anecdote
   - Topic: AI productivity
   - Word count: 180

## Key Patterns
- Personal anecdotes in the first sentence correlate with 2x higher engagement
- Posts with concrete examples outperform abstract posts by 40%
- Optimal word count appears to be 150-200 words

## Recommendations
1. Lead with personal or company-specific openings
2. Include at least one specific example or data point
3. Keep total length under 220 words
Notes
  • Only analyze posts with engagement data (skip posts without metrics)
  • Correlation is not causation - note patterns but don't overclaim
  • Consider recency bias - newer posts may still be accumulating engagement
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…