Cold Outreach
Use when creating or improving B2B outbound, prospecting, cold email, LinkedIn outreach, account research, sales sequences, or founder-led direct outreach.
Install
$ agentstack add skill-infinite-labs-ai-infinite-skills-cold-outreach ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-infinite-labs-ai-infinite-skills-cold-outreach) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Cold Outreach
Build outbound around a verifiable reason to contact a specific person now, with claim risk and reply friction made explicit.
Research The Reason
For each segment or account, find:
- Business event or pressure.
- Role-level responsibility.
- Current tool, workflow, or public initiative.
- Likely pain or missed opportunity.
- Mutual context or credible source.
- Offer or next step that fits the moment.
If no account-specific signal is available, use segment-level relevance and keep the claim modest.
Check Relevance
Score each prospect or segment:
- Reason-to-reach: how specific and timely the reason is.
- Timing evidence: public event, hiring, tool change, funding, launch, regulation, role change, review, complaint.
- Source confidence: first-party, third-party, inferred, stale, unknown.
- Claim risk: how likely the message overstates what is known.
- Reply friction: how hard it is for the recipient to answer or take the next step.
- Fit: whether the problem, role, and offer plausibly match.
Do not write personalized claims that cannot be verified from the research.
Write The Sequence
Use a clear arc:
- Message 1: specific reason, problem, credible offer.
- Follow-up 1: useful proof or example.
- Follow-up 2: different angle or objection.
- Breakup: polite close or permission to stop.
Keep each message short. One idea, one ask. Avoid fake familiarity, exaggerated flattery, and generic "quick question" openings.
Output
Outbound angle:
Target:
Trigger:
Problem:
Offer:
Proof:
Qualification filters:
- Include:
- Exclude:
Relevance score:
| Prospect/segment | Reason-to-reach | Timing evidence | Source confidence | Claim risk | Reply friction |
Sequence:
Email 1
Subject:
Body:
Follow-up 1
Subject:
Body:
Follow-up 2
Subject:
Body:
Personalization fields:
| Field | Source | Example |
Risk checks:
- [claim to verify]Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Infinite-Labs-AI
- Source: Infinite-Labs-AI/infinite-skills
- License: MIT
- Homepage: https://infinite.fast/agents/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.