agentleFS
youdcodeyoudcode/open-company/.agents/skills/draft-outreach/SKILL.md

draft-outreach

Skill2 starsChanged 53 days agoMITView on GitHub

Writes short, personal first messages for hot and warm qualified leads, saved as drafts for human approval in the live page. Never sends anything. Use when the human types "draft".

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write the message following roles/sales.md (120 words max, sourced signal first, one claim from the profile at most, soft call to action, …

    line 13

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Draft outreach

Role: sales (delegate to the sales subagent if available, otherwise follow roles/sales.md).

  1. List candidates: node tools/leads.mjs list --tier hot then --tier warm. Keep leads with status qualified (skip do_not_contact, replied, and leads that already have a pending draft).
  2. For each (max 10 per run): read the lead (tools/leads.mjs get) and its account file.
  3. Write the message following roles/sales.md (120 words max, sourced signal first, one claim from the profile at most, soft call to action, opt-out line for email, prospect's language).
  4. Save: write the body to workspace/tmp/<id>.txt, then node tools/drafts.mjs new <id> --as sales --subject "..." --body-file workspace/tmp/<id>.txt.
  5. Optional but recommended for the first batch: ask the auditor to check the drafts.
  6. Tell the human how many drafts wait in the Outreach tab. Remind them that approved messages are exported with export, never sent by the company.

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.