Install
$ agentstack add skill-xuxchloris-hermes-export-skills-email-crafting ✓ 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
Email Crafting
Overview
Write concise B2B trade emails grounded in prospect evidence and product facts. The core rule is that personalization must be earned by research, not invented.
When to Use
Use this skill when the user asks for a first-touch email, follow-up sequence, reply to inquiry, catalog offer, sample discussion, or buyer-facing message.
Do not use it to send email automatically.
Inputs
- Company research output
- Prospect score and priority
- Product context
- Tone rules from
TONE.yaml - Sender signature
Outputs
{
"subject": "",
"body": "",
"draft_status": "draft_ready|blocked_no_evidence",
"cta": "",
"personalization_evidence": [],
"review_notes": []
}
Procedure
- Confirm the prospect priority is A or B. For C prospects, write only if the user explicitly asks. For D prospects, recommend no outreach.
- Check
personalization_evidence. If no fetched evidence is present, returndraft_status: "blocked_no_evidence"and explain what evidence is missing. - Do not invent company activity, buyer intent, product interest, contact names, or sourcing needs.
- Select one concrete personalization point from company research.
- Select one matching product value point from product context.
- Write a short subject line without spammy wording.
- Write 120-160 words unless the user requests a different length.
- Structure the body:
- opening line based on prospect evidence
- product relevance
- one proof point such as certification, specification, or manufacturing capability
- light CTA
- signature
- Add an opt-out line for regions where cold outreach compliance requires it.
- Return review notes for any uncertain claims.
Verification
- The email includes at least one evidence-backed personalization point.
blocked_no_evidenceis used when personalization evidence is missing.- The email does not claim the prospect buys the product unless evidence says so.
- The email does not include unapproved prices.
- The CTA is light and specific.
- The output is a draft requiring human review.
Common Mistakes
| Mistake | Fix | | --- | --- | | Writing "I saw you are looking for..." without proof | Say "I noticed you carry..." only when visible | | Overloading first email with specifications | Mention one relevant proof point | | Using aggressive sales language | Keep it professional and low-friction | | Sending to D-level prospects | Recommend not contacting them |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Xuxchloris
- Source: Xuxchloris/hermes-export-skills
- 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.