• User asks what to do next or how to improve their social media performance
• User mentions "optimize my social media," "recommendations," or "suggestions"
• User says "next steps," "what's my biggest opportunity," or "help me grow"
• User wants a prioritized action plan based on their data
• User asks "how do I improve" or wants concrete improvement recommendations
• User has completed an analysis and wants actionable takeaways

• performance-analyzer-sms findings — top and bottom posts, engagement trends, posting patterns
• audience-growth-tracker-sms findings — growth rate, growth drivers, spike correlations, milestone progress
• content-pattern-analyzer-sms findings — Do More / Do Less patterns, untested combinations, format and topic performance

1. list_posts

   — retrieve the last 30 posts to establish a baseline

2. get_post_analytics

   — pull engagement rate, impressions, saves, and reposts per post

3. get_follower_growth

   — check the growth trend over the last 30 days

4. get_recommendations

   — retrieve platform-generated suggestions from BlackTwist

"To give you the most useful recommendations, I need a quick picture of what's working. Can you share:

• Your 2–3 best-performing posts (what you posted, approximate engagement)
• Your 2–3 worst-performing posts
• Your current posting frequency
• Your primary goal right now (growth, engagement, conversions, other)

Even rough answers unlock much better recommendations than starting blind."

• "Start every post with a specific number — your top 3 posts all open with a stat and average 3× your baseline engagement rate"
• "Shift your Friday posts to Wednesday — Friday averages 1.8% ER vs. 5.1% on Wednesday"
• "Add 'Save this for later' to the end of your educational posts — your how-to content gets high impressions but 60% fewer saves than your average"

Quick Win #1: Start every educational post with a specific number

Why: Your top 3 posts all open with a stat (avg 7.8% ER vs. 3.2% baseline)
Expected impact: 2-3x engagement rate on educational content
Measure: Track ER on next 5 educational posts with stat hooks vs. previous 5 without

• "Shift 20% of your motivational content to storytelling — your personal story posts outperform motivational posts by 40% on engagement rate and drive 3× more comments"
• "Reduce LinkedIn posting from daily to 4× per week and invest the saved time into longer-form threads — your engagement rate drops on days when you post twice, suggesting quality dilution"
• "Move from a 60/40 educational/personal split to 50/50 — personal content drives your follower spikes but currently makes up less than a quarter of your output"

• Hypothesis: "If I [specific action], then [expected outcome] because [reason from data]"
• Test: What to do, how many posts, over what time period
• Success criteria: What result confirms the hypothesis
• Failure criteria: What result tells you to drop it

• Hypothesis: Posting LinkedIn carousels on Tuesday drives more engagement than text-only posts because your top carousel got 4× your average saves. Test: Publish 3 carousels on Tuesdays over the next 3 weeks. Success: Average ER ≥ 2× your text-post baseline. Failure: ER under 1.5× after 3 tries — move on.
• Hypothesis: Ending threads with a direct question increases comments because your two most-commented threads both ended with a question. Test: Add a specific question CTA to your next 5 threads. Success: Comments per thread increase by 30%+.

Experiment: Tuesday carousel test
Hypothesis: If I post LinkedIn carousels on Tuesdays, then saves increase 2x
  because my top carousel (4x avg saves) was posted on a Tuesday.
Test: Publish 3 carousels on Tuesdays over the next 3 weeks
Success: Average ER >= 2x text-post baseline
Failure: ER under 1.5x after 3 tries — move on

• "Stop posting promotional content without a value hook — your direct promotion posts average 0.9% ER vs. 4.3% for posts that lead with a useful insight before mentioning the offer"
• "Stop cross-posting identical content to LinkedIn and Threads without adaptation — your cross-posted content underperforms native Threads content by 55% on every metric"
• "Stop posting on Sundays — you have 6 months of Sunday data and no Sunday post has ever hit your average engagement rate. That time is better spent writing for Monday"

1. What to do — one clear, specific action (not a category, not a vague suggestion)
2. Why — the evidence from their own data (engagement rates, specific posts, growth spikes)
3. Expected impact — what should improve and by approximately how much
4. How to measure — what metric to track and over what time window

1. [Action]
   • Why: [Evidence]
   • Expected impact: [Specific improvement]
   • Measure: [Metric + window]
2. [Action] ...

1. [Action]
   • Why: [Evidence]
   • Expected impact: [Specific improvement]
   • Measure: [Metric + window]

• Hypothesis: [If/then/because]
• Test: [Specific action, N posts, X weeks]
• Success: [Threshold]

• Why: [Evidence]
• Do instead: [Replacement behavior]

"This recommendation is based on a limited sample (8 posts). It is directionally useful but treat it as an experiment, not a confirmed pattern."

• Does not pull raw metrics or build analytics dashboards — see performance-analyzer-sms for data collection
• Does not track follower growth or audience demographics — see audience-growth-tracker-sms for growth data
• Does not detect content patterns from scratch — see content-pattern-analyzer-sms for pattern analysis
• Does not write or draft 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 provide generic advice — every recommendation must reference the user's own data or stated context

• performance-analyzer-sms — get raw post metrics and per-post diagnoses before advising
• audience-growth-tracker-sms — understand follower growth patterns before advising on growth tactics
• content-pattern-analyzer-sms — identify Do More / Do Less patterns before advising on content mix
• social-media-context-sms — establish niche, voice, and goals as the foundation for any recommendation