follow-up — Claude Code skill: what it does, how to install
Drafts concise follow-up emails that re-engage prospects without annoying them. Adapts messaging based on sequence timing and previous context.
npx skills add humanizerai/agent-skills --skill follow-up -a claude-codeWhat follow-up does
The skill accepts your initial pitch summary, elapsed days, and the sequence stage from 1 to 3. It selects between three frameworks depending on timing. Follow-up 1 uses The Bump for a brief touchpoint after 3 to 5 days. Follow-up 2 applies The Value-Add with fresh resources after 7 to 10 days. The third outreach delivers The Breakup after 14 days to cleanly close the conversation.
Every generated message stays strictly between 30 and 75 words with a single call to action. The instructions explicitly ban passive-aggressive openers, apologies, and empty lines like "just checking in". If you do not provide context from the original outreach, the agent stops and asks for it before drafting.
What it helps with
- draft follow-up emails capped at 30 to 75 words
- re-engage cold prospects using The Bump or The Value-Add framework
- write a clean break-up message after two weeks of silence
- remove weak openers and keep exactly one call to action
Example prompts for the agent
- Draft follow-up #1 for my partnership pitch sent 4 days ago
- Write follow-up #2 for the product demo email sent 8 days ago, share our new benchmark guide
- Generate follow-up #3: 15 days since pitch, close the conversation cleanly
How to install follow-up
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill follow-up -a claude-code2Manually: put the files in place
~/.claude/skills/follow-up/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/follow-up/
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill follow-up -a codex2Manually: put the files in place
.agents/skills/follow-up/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill follow-up -a cursor2Manually: put the files in place
.cursor/skills/follow-up/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install humanizerai/agent-skills follow-up2Manually: put the files in place
.github/skills/follow-up/SKILL.md1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill follow-up -a gemini-cli2Platform CLI
gemini skills install https://github.com/humanizerai/agent-skills --path skills/follow-upManually: put the files in place
.devin/skills/follow-up/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill follow-up -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about follow-up
How to install follow-up in Claude Code?
Run npx skills add humanizerai/agent-skills --skill follow-up -a claude-code in your terminal.
What rules does the follow-up skill enforce?
It caps emails at 30-75 words, restricts the text to one call to action, removes guilt trips, and shortens each subsequent message.
Which frameworks are included?
It includes The Bump for a gentle nudge, The Value-Add to share relevant resources, and The Breakup to offer an easy out after 14 or more days.
Source text
SKILL.md · MIT
--- name: follow-up description: Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups. user-invocable: true argument-hint: "[original email context] [days since sent] [follow-up number 1-3]" --- # 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 ``` Subject: Re: [original subject] or [new short subject] [Email body] [First name] ``` **Framework used:** [which one] **What's different:** [how this differs from original] **Word count:** [number]
© humanizerai · MIT · humanizerai/agent-skills
