agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/write-outreach/SKILL.md

write-outreach

Skill14 starsChanged 3 months agoMITView on GitHub

Create signal-led outreach and reply handling. Use for cold email, founder outreach, partnership or sales messages, LinkedIn or other DMs, proposals, follow-ups, inbound reply handling, deliverability, compliance, or evaluating whether sent outreach earned qualified conversations.

3 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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create the smallest useful sequence:

    line 24
  2. Distinctive:

    follow-up that adds value or closes the loop.

    line 31
  3. Distinctive:

    Do not use false urgency, deceptive threading, manufactured familiarity, or an endless cadence.

    line 33
  4. Distinctive:

    Do not send, enrich, upload contacts, write to a CRM, or schedule a sequence without explicit approval for the exact action.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 3 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

Write trustworthy outreach

Earn relevance from an observable signal, make a small honest ask, and preserve the recipient's control.

Establish selection and proof

Define one segment, channel, observed selection signal, costly moment, affiliation, proof boundary, and next action. A job title or company category alone is not personalization.

Trace target-specific statements to public, operator-supplied, or permissioned evidence. Never invent a trigger, private deal, shared connection, customer result, or familiarity.

Write the sequence

Create the smallest useful sequence:

  • subject/opening tied to the signal;
  • why the issue may matter now;
  • credible mechanism or useful artifact;
  • proof appropriate to the evidence available;
  • one low-friction ask;
  • follow-up that adds value or closes the loop.

Do not use false urgency, deceptive threading, manufactured familiarity, or an endless cadence. Preserve founder/company voice and channel norms.

Prepare concise reply handling for interested, objection, not now, wrong person, proof question, unsubscribe, and ambiguous responses. Never request sensitive material through an unsafe channel.

Protect deliverability and consent

State the applicable identity, opt-out, suppression, lawful-basis, and platform-policy requirements. Monitor delivered volume, bounce, complaint, unsubscribe, reply quality, and sender reputation. Stop when deliverability or compliance crosses the predeclared boundary.

Deliver

Return:

  1. selection signal and exclusions;
  2. finished sequence;
  3. proof and personalization sources;
  4. reply bank;
  5. compliance/deliverability checklist;
  6. qualified-conversation metric, diagnostics, batch size, and stop rule.

Do not send, enrich, upload contacts, write to a CRM, or schedule a sequence without explicit approval for the exact action.

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.