Signal-Based Outreach

Sales skill, available on Zeplik

Signal-Based Outreach is a ready-to-run sales skill on Zeplik. Not for general cold outreach sequences (use draft-outreach). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Document artifact -- structured written deliverable with headed sections and a TL;DR (see artifact-templates/document.md).

The Signal-Based Outreach skill loads automatically when your request matches it, or you can invoke it directly by typing /compose-outreach in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.

What the Signal-Based Outreach skill can do

Try these prompts on Zeplik

Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.

How the Signal-Based Outreach skill works

/compose-outreach

Write outreach anchored to a specific signal the user observed and pasted: a post, a question, a job change, a repo star, a usage event, a funding announcement. The signal is the message -- everything else exists to earn the right to mention it. Deliver three formats: email, call script, and LinkedIn message.

Lane boundary: this skill requires an observed signal to react to. For general cold or warm outreach without a triggering event, use draft-outreach.

Step 1: Capture the signal

From what the user pasted, pin down:

  • What happened -- the exact activity (posted about X, changed jobs, starred the repo, asked a question, hit a milestone)
  • When -- recency drives everything; a signal older than ~2-4 weeks may need reframing ("a while back you mentioned...") or a fresher supplement
  • Where -- public (they know you could have seen it) vs private telemetry (reference it tactfully: "teams at your stage often..." rather than "I saw you clicked...")

If the user asks for signal-driven outreach but has not pasted the signal, ask for it -- do not invent one.

Step 2: Optionally strengthen with web search

If the signal is thin or slightly stale, search for a reinforcing external hook: recent company news, their latest public post, a launch or funding event. Prioritize hooks that are very recent, publicly visible, and change-signaling. Never replace the user's signal; supplement it.

Step 3: Rank the hooks

If multiple signals are in play, lead with the one that is:

  1. Most recent -- days beat weeks
  2. Most specific -- a concrete action they took, not a trend
  3. Most relevant -- connects directly to a value the user's product delivers

Good hooks: asked a question about X in a community, just hired 5 engineers, started using [feature], raised a Series B, champion changed jobs. Bad hooks: "I noticed you're a customer", generic industry trends.

Step 4: Generate all three formats

Ask for the user's product/positioning context if not already given -- the value bridge must be theirs, not generic. Then produce all three, clearly labeled:

## Outreach for [Name / Company]

### Email
**Subject:** [4-8 words, references the hook]
[3-5 sentences: signal acknowledgment -> value bridge -> single low-friction ask]

### Call Script
**Opening:** [name, company, hook -- 10-15 seconds]
**Value Bridge:** [why now, tied to the signal -- 20-30 seconds]
**Ask:** [one specific, low-friction next step]

### LinkedIn Message
[Under 300 characters. Warm, personal, references the signal, no pitch.]

### Signal Notes
[2-4 sentences: which signal anchored the drafts, assumptions made, and an alternative angle if the primary hook does not land]

Format rules, examples, and tone calibration by context (inbound vs cold vs re-engagement vs executive vs job change): references/outreach-formats-guide.md.

Quality standards

  • Every message references the specific signal -- if the signal were deleted, the message should stop making sense.
  • Open with them, not you: "Saw your post about...", never "I hope this finds you well."
  • Match tone to signal type: warm for community/inbound signals, congratulatory for job changes, concise and outcome-focused for executives.
  • LinkedIn stays under 300 characters, no exceptions; the call script must be speakable -- read it aloud mentally.
  • Never fabricate signals or familiarity; only reference what the user provided or web search returned.

Usage

/compose-outreach $ARGUMENTS

How to use the Signal-Based Outreach skill

  1. Sign in to Zeplik

    Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Signal-Based Outreach skill right away.

  2. Describe your sales task

    Ask in plain language, or type /compose-outreach to invoke the skill directly. Zeplik recognizes the Signal-Based Outreach skill and applies its method.

  3. Review and refine the result

    Zeplik returns a structured document you can edit, download, and reuse. Ask follow-ups to refine it.

Source and credit

Author
anthropic
License
Apache-2.0

Adapted from the open-source anthropics/knowledge-work-plugins project and tuned to run natively on Zeplik. View source on GitHub.

Frequently asked questions

What is the Signal-Based Outreach skill?
Signal-Based Outreach is a ready-to-run sales skill on Zeplik. Not for general cold outreach sequences (use draft-outreach). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Document artifact -- structured written deliverable with headed sections and a TL;DR (see artifact-templates/document.md).
How do I use Signal-Based Outreach on Zeplik?
Sign in to Zeplik and ask in plain language, or type /compose-outreach in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
Which AI model does the Signal-Based Outreach skill use?
Any model you choose. Zeplik works across every model in one chat, so the Signal-Based Outreach skill runs on your preferred model for the task.
Where does the Signal-Based Outreach skill come from?
The Signal-Based Outreach skill is adapted from the open-source anthropics/knowledge-work-plugins project (Apache-2.0) and tuned to run natively on Zeplik. The original source is linked on this page.
How much does the Signal-Based Outreach skill cost?
Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.

Related sales skills

More on Zeplik

Try Signal-Based Outreach on Zeplik

Every model, one chat. Bring the Signal-Based Outreach skill into your next conversation and let the assistant do the work.

Browse all skills
Signal-Based Outreach - Sales skill for Zeplik AI | Zeplik Chat