analyze-performance
Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.
git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit /tmp/analyze-performance && cp -r /tmp/analyze-performance/plugins/content-studio/skills/analyze-performance ~/.claude/skills/analyze-performanceSKILL.md
# 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
Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac. Use when the user wants to recall something they did before but can't find it , phrasings like "where did I work on X", "find that session where I…", "when did I last do Y", "pull up the conversation about Z", "that time I built/tried/discussed …". Searches by kind (code/cowork), time range, title, working directory, or free-text content across all transcripts.
Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic skills that would reduce iteration. Use when the user asks to "analyse my Claude use", "build a task profile", "what tasks do I do with Claude", "where am I spending tokens", "what skills would help me", or mentions reviewing past sessions for patterns. Produces profile.csv (shareable), explorer.html (personal coaching view with AI-first principle comparison + token-spend chart), and skill-proposals.md.
Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation length distribution, marathon share, cache rebuild costs, and per-project diagnosis (good projects and problem projects) right in the terminal. Then offers a deeper dive that fans out parallel Haiku subagents over your most expensive (and most efficient) sessions and writes a tight Markdown report. Use when the user asks "why is my Claude spend so high", "where am I burning tokens", "diagnose my Claude habits", "audit my Claude usage", or asks for a personal token-cost diagnosis.
Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, improve, 'ai-firstify', or start a new project. Performs deep analysis across 7 dimensions, actively restructures existing projects, or guides new project setup through discovery questions. Based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp.
Generate LinkedIn post ideas from external sources (files, URLs, research). Use when the user provides source material (PDFs, URLs, articles) to brainstorm topics. NOT for writing or developing drafts - use write-linkedin-post instead.
Generate opinion piece ideas from recent LinkedIn posts (last 30 days). Use when asked to find opinion topics, brainstorm article ideas, or cross-pollinate content between LinkedIn and opinion pieces.
Entry point for the TechWolf content-studio plugin. Use to understand the workflow, pick the right content skill, or start setup for a new author/repository.
Set up a new content studio for a person. Copies the plugin template, adapts it to the person's voice, themes, and content types through interactive discovery. Use when asked to create a content studio for someone new.