agentleFS
gokulsvisiongokulsvision/Crewm8-Social-Media-Manager-Skill-Graph/skills/crisis/impersonator-monitor/SKILL.md

impersonator-monitor

Skill17 starsChanged 7 months agoMITView on GitHub

Monitor for brand impersonators, fake accounts, and phishing attempts — draft platform report copy and escalation guidance for takedown requests.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    After viral post (impersonator activity spikes)

    line 33
  2. Distinctive:

    Search for brand name variations across all platforms

    line 55
  3. Distinctive:

    Check recent "is this you?" DMs

    line 57
  4. Distinctive:

    Use impersonation/trademark violation form

    line 72
  5. Distinctive:

    Follow up if no action after 72 hours for high/critical cases

    line 74
  6. Distinctive:

    Not doing routine sweeps (only find impersonators after damage done)

    line 120
  7. Distinctive:

    Not warning audience when active impersonation happening

    line 122
  8. Distinctive:

    Not following up on platform reports

    line 123
  9. Distinctive:

    Search for "[brand]" plus "official" / "support" / "help" on each platform.

    line 127

≈ “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

Impersonator Monitor

Detect and respond to brand impersonation, fake accounts, and phishing attempts. Impersonators erode trust and confuse customers. Fast detection and reporting are critical.

Purpose

Impersonator accounts are inevitable once a brand has any visibility. This skill makes detection systematic — weekly sweeps, customer report intake, and platform takedown procedures — so impersonators are caught before they cause real damage.

When to Use

  • Routine weekly sweep for fake accounts
  • Customer reports suspicious account
  • Spike in "is this you?" DMs
  • After viral post (impersonator activity spikes)
  • Phishing DMs detected

Inputs Required

  • Official brand handles per platform
  • Customer contact channels (for reports)
  • Platform support contacts

Quick Reference

Impersonator TypeRiskDetectionResponse
Exact handle cloneHighSearch for similar handlesImmediate platform report
Lookalike accountHighManual search, follower reportsReport + warn audience if active
DM phishingCriticalAudience reports, inbox monitoringReport + public warning if widespread
Parody/satireLow-MediumPlatform searchMonitor unless confusing consumers
Fake support accountCriticalCustomer complaintsImmediate report + legal if needed

Procedure

  1. Weekly sweep:
    • Search for brand name variations across all platforms
    • Google Alerts for "[brand] fake" and "[brand] scam"
    • Check recent "is this you?" DMs
  2. Document each impersonator:
    • Platform, handle, URL
    • Activity level (dormant, active, scamming)
    • Followers count
    • Evidence (screenshots)
  3. Assess severity:
    • Low: dormant, no followers. Report and move on.
    • Medium: active but distinguishable. Report + monitor.
    • High: actively impersonating or messaging customers. Report immediately + public warning.
    • Critical: running scams or causing financial harm. Report + warning + legal.
  4. Draft platform report:
    • Use impersonation/trademark violation form
    • Provide evidence (screenshots, handle comparison)
    • Follow up if no action after 72 hours for high/critical cases
  5. Post public warning if warranted:
    • "Our only official accounts are: [list]. We never DM asking for payment."
    • Pin warning for duration of impersonation activity

Output Format

# Impersonator Monitor: [Date]

## Detected
**Platform:** [X / LinkedIn / IG / TikTok]
**Handle:** [Fake handle]
**Severity:** [Low / Medium / High / Critical]
**Activity:** [Dormant / Active / Scamming]
**Followers:** [N]

## Action
- [ ] Platform report filed ([date])
- [ ] Public warning posted ([date/link])
- [ ] Follow-up scheduled (72h for high+)

**Status:** [Reported — awaiting takedown / Resolved / Ongoing]

## Impersonation Log
| Date | Platform | Handle | Severity | Reported | Resolved |
|------|----------|--------|----------|----------|----------|
...

## Patterns
- Most active platform: [Platform]
- Recurrence triggers: [After viral / During launches]

Done Criteria

The skill is complete when:

  1. Weekly sweep is conducted across all active platforms
  2. Each impersonator is documented (handle, severity, activity)
  3. Platform reports are filed for high+ severity
  4. Audience warning posted if impersonator is active
  5. Impersonation log is updated

Pitfalls

  • Not doing routine sweeps (only find impersonators after damage done)
  • Engaging directly with impersonators (report, don't argue)
  • Not warning audience when active impersonation happening
  • Not following up on platform reports

Verification

Search for "[brand]" plus "official" / "support" / "help" on each platform. Any results that aren't yours? Check "is this you?" DMs from last 30 days — any accounts people are confused about?

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.