Install
$ agentstack add skill-bcharleson-cursor-for-gtm-demo-gtm-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.
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
GTM Outreach
When to Use This Skill
Apply this skill as the entry point for any cold outreach work in this project. Route to specialized skills based on the task.
Skill Routing
| User need | Read and follow | |-----------|-----------------| | Inbox placement, DNS auth, ESP/SEG setup, sending infrastructure | [cold-email-deliverability](../cold-email-deliverability/SKILL.md) | | Writing, editing, or reviewing email copy | [cold-email-copywriting](../cold-email-copywriting/SKILL.md) | | LinkedIn messaging or connection requests | Coming soon — apply email copy principles until dedicated skill exists |
Outreach Stack (Mental Model)
Sending infrastructure Message Recipient environment
───────────────────── ─────── ─────────────────────
SPF / DKIM / DMARC → Plain text, relevant → Google / Microsoft / custom ESP
Domain reputation Hook → Bridge → CTA SEGs (Proofpoint, Mimecast…)
Plain text, no links Low-friction ask Corporate security filters
Agent Workflow
- Clarify the goal — Who is the ICP? What is the offer? What outcome does the user want (reply, meeting, asset sent)?
- Check infrastructure first — Before drafting or approving send plans, verify deliverability prerequisites via the deliverability skill.
- Draft or review copy — Use the copywriting skill. Never approve copy that violates deliverability rules unless the user explicitly opts in.
- Validate as a unit — Infrastructure + copy + CTA must align. A great email on a broken domain still fails.
Non-Negotiables
- Deliverability is always top of mind.
- Cold email defaults to plain text with no links or images unless the user intentionally chooses otherwise.
- Missing SPF, DKIM, or DMARC must be flagged immediately — do not treat as optional.
- No small talk, no flattery openers, no novels.
- CTAs should be low-friction; hard asks for meetings are the exception, not the rule.
Business-Agnostic Adaptation
These skills define how to outreach. The user supplies what:
- ICP (ideal customer profile)
- Value proposition and proof (case studies, outcomes)
- Sending domain and tooling
Ask for missing context rather than inventing specific claims, metrics, or customer names.
Project Context
For broader project intent and agent behavior defaults, see [cursor/gtm-outreach-overview.md](../../../cursor/gtm-outreach-overview.md).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bcharleson
- Source: bcharleson/cursor-for-gtm-demo
- License: MIT
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.