Twitter Thread Writer

Error Handling

• No product info: Pull recommended_program from S1 context if available. Otherwise ask what product they want to promote.
• No personal experience: Write research-based content. Flag that personal experience threads get 2-3x more engagement and suggest adding a real data point.
• Thread feels too promotional too early: Move product mention to tweet 6+. Add 1-2 more value tweets before the recommendation.
• Content is too generic: Use web_search to add specific stats, quotes, or examples. Replace every vague claim with a concrete number or example.
• Tweet over 280 characters: Auto-split or suggest cut. Never truncate — the full thought must fit in one tweet.
• Creator has no X following: Add note: "New accounts should engage in replies for 1-2 weeks before posting threads. Algorithm rewards accounts with engagement history."

Examples

Example 1: User: "Write a Twitter thread promoting ConvertKit to freelancers" → Angle: "How I built a 3,000-subscriber email list as a freelancer — what worked" → Framework: Numbers Story → 9 tweets: Hook (metrics) → 6 lessons → ConvertKit mention at tweet 6 → CTA + #ad → Emphasis: free plan, creator-friendly, no bloat

Example 2: User: "I want to write a contrarian thread about email marketing tools" → Angle: "Most people pick the wrong email platform. Here's why:" → Framework: Contrarian Take → Myths to bust: "Mailchimp is fine for beginners", "you need fancy automations" → Natural product mention: "After trying 5 tools, I settled on ConvertKit because..."

Example 3: User: "8-tweet thread about HeyGen for video creators" → Framework: How-to Tutorial — "How to create a talking-head video without a camera" → Step-by-step: sign up → upload script → pick avatar → generate → edit → export → Product mention woven in at step 1 (that's HeyGen) → CTA: "HeyGen has a free plan — I made my first 3 videos for free: [link] #ad"

References

• shared/references/ftc-compliance.md — #ad placement rules for Twitter/X
• shared/references/platform-rules.md — X character limits, link handling, thread best practices
• shared/references/affiliate-glossary.md — terminology
• shared/references/flywheel-connections.md — master flywheel connection map

Revenue & Action Plan

Expected Outcomes

• Revenue potential: A viral thread (1,000+ bookmarks) can drive 200-500 affiliate link clicks from the CTA tweet. At 3% conversion and $50 commission = $300-750 per thread. Threads compound — bookmarked threads resurface in search for months
• Benchmark: Affiliate threads with 5,000+ impressions and 2%+ engagement rate typically convert at $0.10-0.50 per impression in affiliate revenue
• Key metric to track: CTA tweet click-through rate. Industry benchmark: 1-3% CTR on the last tweet. Below 1% = weak CTA or product-thread mismatch

Do This Right Now (15 min)

1. Post the thread NOW at the recommended time (or schedule for the next optimal window)
2. Immediately like all your tweets in the thread (boosts visibility)
3. Post the pinned reply within 2 minutes of the thread going live
4. Reply to every comment in the first hour — this is when the algorithm decides if your thread spreads

Track Your Results

After 48 hours: how many clicks on the affiliate link? How many bookmarks? Bookmarks predict long-term traffic — bookmarked threads get resurfaced by the algorithm for weeks.

Next step — copy-paste this prompt: "Expand my Twitter thread about [product] into a full blog review" → runs affiliate-blog-builder

Flywheel Connections

Feeds Into

• affiliate-blog-builder (S3) — thread content expanded into blog posts
• content-pillar-atomizer (S2) — successful threads become content to atomize
• social-media-scheduler (S5) — threads ready to schedule
• ab-test-generator (S6) — hook variants for testing

Fed By

• affiliate-program-search (S1) — recommended_program product data
• purple-cow-audit (S1) — remarkable angles for thread hooks
• content-pillar-atomizer (S2) — atomized Twitter pieces from pillar content

Feedback Loop

• performance-report (S6) reveals which thread hooks and lengths perform best → optimize thread structure

Quality Gate

Before delivering output, verify:

1. Would I share this on MY personal social?
2. Contains specific, surprising detail? (not generic)
3. Respects reader's intelligence?
4. Remarkable enough to share? (Purple Cow test)
5. Irresistible offer framing? (if S4 offer skills ran)

Any NO → rewrite before delivering.

Volume Mode

When mode: "volume":

• Generate 5-10 hook variations instead of 1
• Prioritize speed + variety over perfection
• Tag each with variant ID for A/B tracking
• Let data pick the winner

volume_output:
  variants:
    - id: string
      content: string
      angle: string

chain_metadata:
  skill_slug: "twitter-thread-writer"
  stage: "content"
  timestamp: string
  suggested_next:
    - "social-media-scheduler"
    - "content-pillar-atomizer"
    - "ab-test-generator"