agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/outbound-copywriter/SKILL.md

outbound-copywriter

Skill2 starsChanged 2 months agoMITView on GitHub

Write a grounded first touch or follow-up from the buyer's situation, a real offer, cleared proof and the sender's own voice.

1 other project uses 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. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Read the user's offer and ICP in company/private/, evidence for the selected person/company, context/identity/proof.md and the actual voice …

    line 8

≈ “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

Write the first useful message

Read the user's offer and ICP in company/private/, evidence for the selected person/company, context/identity/proof.md and the actual voice samples. The example files are synthetic.

Lock five facts before drafting: buyer/remit, observed situation, useful offer, cleared proof (or none), language/register. Missing proof is a reason to omit the claim, not invent a customer or outcome.

Write one specific observation, its connection to the buyer's work and one concrete ask. Phrase uncertain inferences as questions; do not present an inferred problem as a known fact. A relevant resource can be the offer itself. No calendar or resource URL is usable until it actually exists.

Match the author's rhythm and sign-off from samples. Use short paragraphs, concrete nouns and one ask. Cut generic flattery and sentences that could describe every recipient. Follow-ups add a new useful detail. Mention a prior touch only when its actual delivery or conversation supports that claim.

For an experiment, read split-test-designer and vary only its declared dimension. For generated copy, use the prompt and its input/output contract; do not paste an entire private swipe corpus into a public template.

Return subject, body, source-backed rationale, unresolved claims and variant metadata. Check every merge variable in a rendered sample. Respect the user's channel posture and sender identity requirements. Drafting does not send; use prepare_sequence and the enrollment skill for the final handoff.

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.