• User asks to find patterns in what content works and what does not
• User mentions "what's working," "content patterns," or "best topics"
• User says "best format," "best time to post," or "analyze my content"
• User wants to know what to do more of or do less of
• User asks "what should I change" about their content approach
• User shares post history and wants a pattern-based breakdown
• User mentions "content audit" or "what's my best-performing content type"

1. list_posts

   — retrieve the full post history, paginating until you have 30+ posts (use larger date ranges if needed)

2. get_post_analytics

   — pull per-post metrics for every post: impressions, likes, comments, reposts, saves, link clicks, profile visits

3. get_metric_timeseries

   — pull engagement rate over time to identify trend direction (weekly view recommended)

4. get_consistency

   — check posting frequency and cadence to identify whether consistency correlates with pattern shifts

"To find content patterns, I need data across at least 15–30 posts. You can share:

• A CSV export from your analytics dashboard
• Screenshots of your post analytics
• Manual input using the template below

Data Collection Template: For each post, capture:

Post (summary)	Date	Format	Topic/Pillar	Hook type	Impressions	Likes	Comments	Reposts	Saves

The more posts you provide, the more reliable the patterns."

• Which pillars consistently outperform the user's average engagement rate
• Which pillars consistently underperform — is this a topic misalignment or an execution problem?
• Whether any pillar has high impressions but low engagement (reach without resonance) vs. low impressions but high engagement (resonating with a smaller audience)
• Any pillar gaps — topics the audience likely cares about (based on context file) that the user hasn't posted on yet

Pillar: Productivity Tips
Posts: 12 | Avg ER: 6.1% (vs. 3.8% baseline)
Top post: "3 tools that cut my content time in half" (9.2% ER)
Signal: Consistently outperforms — do more

Pillar: Company Updates
Posts: 8 | Avg ER: 1.4%
Top post: "We just launched v2.0" (2.1% ER)
Signal: Consistently underperforms — reframe or reduce

• Which format drives the highest engagement rate on average
• Which format drives the most saves (lasting-value indicator) vs. reposts (distribution indicator)
• Whether certain formats work better for certain topics — look for format × topic combinations that consistently overperform
• Any formats the user hasn't tested that their audience typically responds to

• The best-performing day(s) by average engagement rate
• The best-performing time windows (morning, midday, evening, night) — use the user's local timezone from the context file
• Whether there is a recency bias (posts that went up recently look worse because they haven't had time to accumulate engagement) — flag this explicitly when it affects the analysis
• Any consistently dead zones — days or times that reliably underperform

• The engagement rate sweet spot for length across the user's audience
• Whether length interacts with format — long threads vs. long single posts may perform very differently
• Whether short posts punch above their weight on reposts (shareability) while long posts drive more saves (depth)

• Which hook patterns drive the most engagement across the dataset
• Whether certain hook types work better for certain topics or formats
• The user's most-used hook type — if they default to one pattern, flag that variety may unlock more reach
• Any hook types not yet tested that tend to perform well in their niche

• Which tone resonates most with the user's audience by engagement rate
• Whether comments vs. saves vs. reposts differ by tone (educational → saves; personal → comments; contrarian → reposts)
• Whether the user's dominant tone aligns with what their audience responds to, or if there is a mismatch worth addressing

• Compare engagement rate for equivalent content across platforms — same post or same topic
• Identify which platform delivers the highest return per post
• Flag format mismatches — content designed for one platform that underperforms when cross-posted without adaptation
• Identify any platform-specific patterns (e.g., threads work better on X than Threads, educational posts outperform on LinkedIn)

1. Identify posts that were published on more than one platform
2. Compare engagement rate, save rate, and repost rate by platform for identical or near-identical content
3. Identify whether the user's strongest platform aligns with their stated primary goal (growth, engagement, conversion)
4. Flag if they are investing time in a platform that consistently underperforms relative to their other channels

• Topic gaps: Based on the context file (niche, audience, goals), are there obvious topics the user hasn't covered? Look for topics adjacent to their top-performing pillars.
• Format gaps: Are there formats the user hasn't tested (e.g., they only post threads but their audience saves image posts)? Check what performs in their niche generally.
• Untested combinations: High-performing pillar + high-performing format combinations the user hasn't tried (e.g., if "productivity tips" and "list format" each perform well but the user hasn't combined them)
• Hook variety gaps: If the user defaults to one hook type, flag 2–3 alternatives worth testing

Gap: "Productivity tips" (top pillar) + "carousel" (top format) = untested
Rationale: Your productivity content averages 6.1% ER and your carousels
average 5.8% ER — but you have never published a productivity carousel.
Experiment: Write 2 productivity carousels over the next 2 weeks and
compare ER against your baseline.

• Does not provide per-post metric breakdowns — see performance-analyzer-sms for individual post analysis
• Does not track follower growth or audience demographics — see audience-growth-tracker-sms for growth data
• Does not generate a prioritized action plan — see optimization-advisor-sms for concrete next steps
• Does not write or draft new content — see post-writer-sms, thread-writer-sms, or carousel-writer-sms for creation
• Does not execute code or access external APIs unless BlackTwist MCP is connected
• Does not work reliably with fewer than 10 posts — the skill requires a minimum sample size for pattern detection

• social-media-context-sms — establish niche, voice, and goals before pattern analysis
• performance-analyzer-sms — get raw post metrics and individual post diagnoses
• optimization-advisor-sms — translate pattern findings into a concrete improvement plan