agentleFS
prosyo-aiprosyo-ai/gtm-skill/skills/outreach-compliance-check/SKILL.md

outreach-compliance-check

Skill13 starsChanged 24 days agoMITView on GitHub

Use this skill when you need to check that cold email or LinkedIn outreach follows privacy and anti-spam rules before it goes out: \"is this campaign GDPR compliant\", \"CAN-SPAM checklist\", \"can we email people in the EU\", \"check our cold outreach for compliance\". Checks the audience, lawful basis, data source, sender identity, opt-out, frequency and record keeping by region, flags what must change, and produces a pass/fix report. A practical checklist, not legal advice.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Use this before a campaign reaches people in a new region, or when a list comes from a new source.

    line 16
  2. Distinctive:

    Read references/compliance-checklist.md for the full checklist per region.

    line 37
  3. Distinctive:

    Every "fix" has a concrete change.

    line 62
  4. Distinctive:

    MUST state that this is a checklist, not legal advice, when the stakes are high.

    line 68
  5. Distinctive:

    MUST require a working opt-out and identity in every commercial email.

    line 69
  6. Distinctive:

    NEVER approve outreach to data of unknown or unlawful origin.

    line 70
  7. Distinctive:

    NEVER suggest hiding the sender, the source or the commercial nature of a message.

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Use this before a campaign reaches people in a new region, or when a list comes from a new source. It is a practical pre-flight check; for anything unclear or high-risk, the user should ask their own legal counsel.

Inputs

  • Audience: which countries, B2B or consumer, job roles.
  • Where the data came from and what the source says about permitted use.
  • The emails and messages as they will be sent.
  • How opt-outs and records are handled today.

The play

1. Sort the audience by region

Rules differ. Typical buckets:

RegionCommon baseline for B2B cold email
United StatesAllowed with honest headers and subject, a physical address, a working opt-out honoured promptly
EU and UKUsually relies on legitimate interest for business contacts: relevant offer, role-based targeting, clear identity, easy opt-out, ability to say where the data came from
CanadaStricter consent rules; business-to-business exceptions are narrow
Australia and othersCheck local rules; consent expectations vary

Read references/compliance-checklist.md for the full checklist per region.

2. Check the data source

The source must allow the use, be recent, and be explainable to the recipient if they ask. Personal email addresses and consumer data raise the bar sharply.

3. Check relevance

For legitimate-interest outreach, the message must be relevant to the person's job. A finance tool to a CFO passes; the same email to a list of every employee does not.

4. Check the message

Real sender name and company, an honest subject, a physical address where required, and a simple opt-out in every commercial email. No misleading "Re:" or "Fwd:" subjects.

5. Check operations

Opt-outs honoured across all mailboxes and channels; suppression lists shared; records of source, date and basis kept; a process to answer "where did you get my data?" and deletion requests.

Output format

Region | Audience | Verdict (pass / fix / do not send) | Issues | Required changes
Records to keep: <list>
Open questions for counsel: <list>

What good looks like

  • Each region gets its own verdict; one rule is not applied everywhere.
  • Every "fix" has a concrete change.
  • High-risk cases (consumer data, sensitive sectors, unclear sources) are sent to counsel, not guessed.
  • The common mistake is assuming "it's B2B, so anything goes", which ignores regional rules and the recipient's right to object.

Rules

  • MUST state that this is a checklist, not legal advice, when the stakes are high.
  • MUST require a working opt-out and identity in every commercial email.
  • NEVER approve outreach to data of unknown or unlawful origin.
  • NEVER suggest hiding the sender, the source or the commercial nature of a message.

Example prompts

  • "We're emailing 2,000 operations leaders in Germany and the UK. Run a compliance check."
  • "Check this cold email and our opt-out process against US and EU rules."
  • "Build a pre-send compliance checklist for our SDR team."

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.