# Outbound Prospecting

> Design and diagnose evidence-safe cold outreach sequences across email, phone, and professional social channels. Use when building a prospecting sequence, fixing low reply or meeting rates, choosing personalization depth, or testing channel and message changes.

- Skill: `majesticlabs-dev/outbound-prospecting` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add majesticlabs-dev/outbound-prospecting`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majesticlabs-dev/outbound-prospecting/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: majesticlabs-dev (https://skillmd.com/u/majesticlabs-dev)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/majesticlabs-dev/outbound-prospecting

---


# Outbound Prospecting

## Boundary

Own sequence architecture, personalization, response handling, and diagnosis. Do not evade channel or jurisdiction rules, fabricate personalization or proof, or optimize opens as the primary outcome. If contact eligibility cannot be verified, do not produce an executable sequence.

## Required Inputs

- Target account and buyer criteria
- Verified problem, offer, proof, and permitted claims
- Channels, list source, target jurisdictions, and lawful contact basis
- Applicable consent, suppression, do-not-call, identification, and platform requirements
- Current sequence, volume, reply, positive-reply, meeting, show, and conversion data

## Workflow

1. Verify list provenance and channel eligibility for each target jurisdiction, including suppression, do-not-call, sender identification, and platform status. Stop and escalate legal uncertainty to qualified counsel before writing executable outreach.
2. Choose a single goal and one primary response action.
3. Map a short sequence where each touch adds a distinct reason to respond.
4. Set personalization depth by account value and available verified evidence.
5. Write channel-appropriate touches without pretending a template variable is known.
6. Define positive, objection, not-now, unsubscribe, and no-response branches.
7. Diagnose from reply, positive-reply, meeting, and downstream quality. Treat opens as directional only.
8. Run one-variable tests with a decision date and guardrail metric.

## Output

1. **Target and sequence hypothesis**
2. **Touch-by-touch sequence with response branches**
3. **Evidence and personalization fields**
4. **Measurement and test plan**

## Quality Gate

- Every claim is supported or qualified.
- Eligibility and list provenance are verified before execution.
- The sequence stops on reply, opt-out, do-not-call status, or suppression.
- No fixed cadence or benchmark is presented as universally optimal.
- Open-rate distortion from mail privacy is acknowledged.

## Reference

Read [benchmark-safety.md](references/benchmark-safety.md) before using external performance ranges.