follow-up

Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups.

By humanizerai · 442 installs

npx skills add humanizerai/agent-skills --skill follow-up

Source repository · Upstream listing

Write Follow Up Email Generate a follow up email that re engages prospects who didn't respond. Input Parse $ARGUMENTS for: Original email or context of first outreach Days since last email : How long ago was it sent Follow up number : Is this 1, 2, or 3? New context (optional): News, trigger events, new value to offer If original context is missing, ask for the key points from the first email. Strategy by Follow Up Number Follow up 1 (3 5 days after) Assume they're busy, not uninterested Add new value or angle Keep it shorter than original Follow up 2 (7 10 days after) Try a different approach Share a relevant insight or resource Reframe the value prop Follow up 3 (14+ days after) "Break up" email or permission based close Give them an easy out Last attempt before moving on Frameworks The Bump Quick, friendly nudge "Floating this back up" energy Best for follow up 1 The Value Add Share something useful (article, insight, idea) Shows you're thinking about their problems Best for follow up 2 The Breakup "Should I close your file?" Creates urgency without pressure Best for follow up 3 Hard Rules 1. Shorter than original Each follow up gets shorter 2. New angle : Don't just repeat the first email 3. No guilt trips : "I haven't heard back" sounds needy 4. No "just checking in" : Empty phrase, add value instead 5. Reference original : Brief callback to first email 6. One CTA : Same or simplified ask 7. 30 75 words max : Follow ups should be scannable What NOT to Write "I wanted to follow up on my last email" (weak opener) "I'm sure you're busy but..." (apologetic) Resending the exact same email Being passive aggressive about no response Multiple CTAs or new complex asks Output Format Framework used: [which one] What's different: [how this differs from original] Word count: [number]