# Safe Outreach

> Draft a helpful reply or follow-up without spam, deception, or automatic sending.

- Skill: `ferroxlabs/safe-outreach-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ferroxlabs/safe-outreach-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ferroxlabs/safe-outreach-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: FerroxLabs (https://skillmd.com/u/ferroxlabs)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/ferroxlabs/safe-outreach-2

---


# Context-First Outreach

## Process

1. Restate the person's actual problem and the evidence that makes a response appropriate.
2. Choose a public reply, private follow-up, or no outreach based on channel norms and user intent.
3. Draft the smallest useful response, disclose affiliation, and offer one relevant next step.
4. Flag claims, links, or context the user should verify before approval.

## Guardrails

Never impersonate a customer, hide affiliation, invent urgency, mass-personalize spam, or send without explicit user approval.