Three-touch cold email sequence personalised from one trigger
Writes a short, plain three-email outbound sequence built around one real trigger you found about the prospect, with subject lines and send timing. No fake familiarity, no invented proof points.
Prompt in Sales by AISkillHub Library
What it does
Cold email that works is short, specific and honest about why you are writing. This prompt builds a three-touch sequence around a single real trigger (a job post, a funding announcement, a product launch, a public talk) and one clear problem your product solves for people in that situation.
**Use it when** you are prospecting a named contact and have found at least one concrete, public reason to reach out now.
**What you get** - Email 1: the trigger, the problem it likely creates, one line on how you help, and a low-effort ask. - Email 2: a different angle on the same problem, such as a useful observation or a relevant customer outcome you supply. - Email 3: a short, polite close-the-loop message that makes it easy to say "not now". - Two subject line options per email, under 50 characters, lowercase-friendly and not clickbait. - Suggested spacing between touches. - A personalisation check listing which lines depend on the trigger, so you can verify them.
**What it will not do** - It will not invent case studies, customer names, metrics or awards. It uses only the proof points you provide; if you provide none, it writes without them. - It will not fake a relationship ("Loved your recent post!") unless your notes say you actually read it and what you thought. - It will not use false urgency, fake "re:" or "fwd:" subject lines, or guilt-trip breakup emails.
Check your local rules on commercial email (for example CAN-SPAM, GDPR or CASL, depending on where you and the recipient are) and include an opt-out line if they require it. The prompt adds a placeholder opt-out line when you ask for one.
How to use it
## How to use
1. Open `prompts/cold-email-sequence.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{prospect}}`: name, role, company. - `{{trigger}}`: the specific public event or signal and where you saw it, e.g. `posted a job for a RevOps manager on 3 Oct mentioning Salesforce cleanup`. - `{{problem_we_solve}}`: the problem your product solves for someone in this situation, in one or two sentences. - `{{proof_points}}`: real, approved outcomes or customers you can mention. Write `none` if you have none. - `{{sender}}`: your name and role. - `{{ask}}`: what you want, e.g. `15-minute call`, `permission to send a 2-minute video`. - `{{include_opt_out}}`: `yes` or `no`.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
Files
Save each file at the path shown, relative to your project root.