agentleFS
JackJanoianJackJanoian/deal-desk/skills/deal-desk-outreach/SKILL.md

deal-desk-outreach

Skill1 starsChanged 6 months agoMITView on GitHub

How to draft and queue outreach emails through DealDesk's approval workflow. Use whenever you need to email a target or intermediary.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before drafting any outreach, verify a Gmail account is connected:

    line 12
  2. Very specific:

    If accounts is empty or all accounts have revokedAt set, stop.

    line 18
  3. Very specific:

    If configured is false, ask the user to add an Apollo API key at /deal-desk/email-accounts.

    line 26
  4. Distinctive:

    Create and enrich contacts before drafting:

    line 30
  5. Distinctive:

    When Apollo is configured, draft auto-enriches the contact and returns 422 if no email can be found.

    line 64
  6. Distinctive:

    Do not invent contact email addresses.

    line 70
  7. Very specific:

    Do not contact anyone on dd_suppression_list.

    line 71
  8. Distinctive:

    Do not call any "send" or "approve" endpoint yourself.

    line 72
  9. Distinctive:

    Do not draft more than 5 sends per heartbeat without user direction.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

DealDesk Outreach

You draft outreach emails. You never send — every send is queued for the user to approve in the Outreach Approvals UI.

Prerequisites

Before drafting any outreach, verify a Gmail account is connected:

GET /api/companies/{companyId}/deal-desk/tools/email-accounts

If accounts is empty or all accounts have revokedAt set, stop. File an issue asking the user to visit /deal-desk/email-accounts and click Connect Gmail.

Also verify Apollo enrichment is configured when contact emails are unknown:

GET /api/companies/{companyId}/deal-desk/tools/apollo-api-key

If configured is false, ask the user to add an Apollo API key at /deal-desk/email-accounts.

Contact setup

Create and enrich contacts before drafting:

POST /api/companies/{companyId}/deal-desk/tools/contacts
{
  "targetId": "<uuid>",
  "firstName": "Jane",
  "lastName": "Doe",
  "title": "CEO",
  "isPrimary": true
}
POST /api/companies/{companyId}/deal-desk/tools/contacts/enrich/{contactId}

The enrich endpoint requires the target to have a website/domain and the contact to have first and last names.

Drafting a Send

POST /api/companies/{companyId}/deal-desk/tools/outreach/draft
Content-Type: application/json

{
  "campaignId": "<uuid>",
  "targetId": "<uuid>",
  "contactId": "<uuid>",
  "subject": "Subject line under 80 chars",
  "body": "Email body. Plain text. Under 150 words. Personalized."
}

When Apollo is configured, draft auto-enriches the contact and returns 422 if no email can be found.

Response: 201 { "id": "<send-uuid>" }. The send is now awaiting_approval.

What NOT To Do

  • Do not invent contact email addresses. Create contacts and run Apollo enrich instead.
  • Do not contact anyone on dd_suppression_list.
  • Do not call any "send" or "approve" endpoint yourself. Approval is a human-only action.
  • Do not draft more than 5 sends per heartbeat without user direction.

Reporting Back

In chat, summarize: "Drafted N outreach emails awaiting approval at /deal-desk/outreach-approvals."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.