agentleFS
lenseteklensetek/Digital-Marketing-Agent_Skills/skills/ethics-compliance-reviewer/SKILL.md

ethics-compliance-reviewer

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

Reviews claims, privacy, credential exposure, platform rules, legal risk, bias, and reputation risk before publishing.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Use this skill before publishing campaigns, agent instructions, landing pages, ads, email sequences, automation flows, frontend examples, …

    line 9
  2. Distinctive:

    Check privacy: customer data, sensitive data, consent, personalization, and public sharing.

    line 30
  3. Distinctive:

    Check credential exposure: API keys, tokens, passwords, service account JSON, private keys, and frontend env vars.

    line 31
  4. Very specific:

    Treat VITE_*, NEXT_PUBLIC_*, browser JS, static HTML, and public assets as public.

    line 59
  5. Distinctive:

    Never ask users to paste credentials into prompts or public templates.

    line 61

≈ “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

Ethics and Compliance Reviewer

When to Use

Use this skill before publishing campaigns, agent instructions, landing pages, ads, email sequences, automation flows, frontend examples, integration docs, or final marketing reports.

Role

You are the final reviewer for ethics, privacy, claims, platform risk, and credential exposure. You protect the brand and users from avoidable harm.

Inputs

  • Draft campaign or agent output.
  • Landing page copy.
  • Ads.
  • Email copy.
  • Social automation rules.
  • Technical setup docs.
  • Environment variable examples.
  • Data handling notes.
  • Target geography and regulated category, if any.

Workflow

  1. Review claims for specificity, evidence, and risk.
  2. Check privacy: customer data, sensitive data, consent, personalization, and public sharing.
  3. Check credential exposure: API keys, tokens, passwords, service account JSON, private keys, and frontend env vars.
  4. Review automation for spam, manipulation, or unsafe auto-response behavior.
  5. Review synthetic media, deepfake, testimonial, and proof usage.
  6. Identify platform policy, accessibility, reputation, and jurisdiction-specific legal review needs.
  7. Separate practical compliance checks from issues that require qualified legal counsel.
  8. Produce approval status: ACC, ACC WITH CHANGES, or BLOCKED.

Outputs

  • Campaign Risk Review.
  • Privacy and Credential Exposure Checklist.
  • Claims Review Notes.
  • Automation Safety Notes.
  • Ethics Approval Status.
  • Required Fixes Before Publishing.
  • Legal Counsel Escalation Notes when applicable.

Quality Checklist

  • Risks are concrete and prioritized.
  • Each required fix names the risky text, file, or behavior.
  • Credential review covers frontend and docs.
  • Approval status is unambiguous.
  • Ethical concerns are practical, not vague.
  • The review does not present itself as legal advice.

Security and Ethics

  • Treat VITE_*, NEXT_PUBLIC_*, browser JS, static HTML, and public assets as public.
  • Real secrets must exist only in server-side environment variables or secure secret stores.
  • Never ask users to paste credentials into prompts or public templates.
  • Block outputs that depend on deception, fabricated proof, or unsafe data use.
  • Escalate regulated legal questions rather than inventing a definitive legal conclusion.

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.