cold-email-sequence
Skill0 starsChanged 7 months agoMITView on GitHub
Use to draft a 4-touch cold email sequence with behavior-based branching. Each touch has a different angle (pain, proof, peer, parting). Output is paste-ready for any sequencer (Apollo, Outreach, Smartlead). Drafts only; never sends.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- agiea-brain/agency-skillstheir own version, first seen Nov 8, 2026
- prosyo-ai/gtm-skilltheir own version, first seen Oct 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- prosyo-ai/gtm-skill★ 13same name
- agiea-brain/agency-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- code-reviewSkill
- content-calendarSkill
- funnel-analysisSkill
- market-researchSkill
- qualify-leadSkill
- release-notesSkill
- seo-outlineSkill
- write-linkedin-postSkill
The file
Files
cold-email-sequence
A working cold sequence is four touches over two weeks, each with a different angle. If they reply at any point, the sequence stops. If they open but don't reply, branch to a softer angle. If they don't open, change the subject line and angle entirely.
Inputs to gather
- ICP / persona — who is this targeting? (Role, company shape, trigger.)
- Offer — one sentence on what we sell and the outcome we deliver.
- Proof point — one customer quote, case study, or metric we can cite.
- Personalization variables —
{{first_name}},{{company}},{{recent_event}}, etc. - CTA preference — meeting, reply with yes/no, content asset?
Sequence shape
| Touch | Day | Angle | Subject line shape | Length |
| 1 | Day 0 | Pain — name their problem precisely | Question or fragment | ≤ 90 words |
| 2 | Day 3 | Proof — one peer's outcome | "How {{peer}} did X" | ≤ 90 words |
| 3 | Day 7 | Peer / pattern — observation about their segment | Insight | ≤ 110 words |
| 4 | Day 14 | Parting — "closing the loop" | "should I close the loop?" | ≤ 50 words |
Branching:
- Replied → stop sequence, hand to AE.
- Opened ≥ 2x, no reply → on Touch 3, switch to a question-only email (no pitch).
- No opens → on Touch 2, swap subject style (fragment → question or vice versa).
Hard rules
- Subject line: ≤ 6 words, lowercase unless proper noun.
- Body opens with a sentence about them, not about us.
- One link maximum per email. Track it.
- One CTA per email. Either a meeting time or a yes/no question.
- No
{{first_name}}in the first sentence — too obvious. - No "hope this finds you well", "quick question", "just checking in", "circling back."
Output format
## Touch 1 — Day 0 — Pain
Subject: <subject>
Preview: <first 70 chars>
---
<body>
CTA: <the ask>
P.S. <optional, one line>
Why this works: <one line on the angle and the personalization hook>Repeat for Touches 2-4. End with:
## Branching logic
- Replied → stop, route to AE
- Opened 2+ no reply → on Touch 3 swap to <variant>
- No opens after Touch 1 → on Touch 2 swap subject to <variant>
## Variables to fill
- {{first_name}}
- {{company}}
- {{recent_event}} ← most likely to be empty; populate from research before sendDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

