Is Deepfake Drill free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Deepfake Drill

Q: How do I know the Deepfake Drill output is good?

The skill verifies itself against its own quality checks: The scenario is built from the org's own process and public information —; generic scripts don't find real gaps; Zero content that teaches attack technique: no cloning tools, methods, or; detection-evasion — pressure is scripted as dialogue only.

🔵 Stable🕐 updated 2026-07-26 🔷 SkillSpec L3 pm-2027

Run a tabletop drill of a voice-clone or deepfake fraud attempt — the 'CEO needs this wire today' call — against your actual approval process, before a real attacker does, then debrief the tells and fix the process gap. Use when someone asks to train the team on deepfake fraud, test wire-transfer controls, run a social-engineering tabletop, or 'could we get CEO-frauded?'. Produces a drill scenario pack, a facilitator script, a tells checklist, and the process fixes the drill exposed. Defensive training only.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The scenario is built from the org's own process and public information —

✓generic scripts don't find real gaps

✓Zero content that teaches attack technique: no cloning tools, methods, or

✓detection-evasion — pressure is scripted as dialogue only

✓The debrief framing is process-blame, not person-blame, explicitly

✓The callback rule appears verbatim in the tells checklist with the

✓"no exceptions for rank" clause

✓Every gap in the report has an owner and a re-drill date

⚠️ What it refuses to do

Do not produce actual cloned audio, cloning instructions, or tool

recommendations for impersonation — decline that direction plainly, even

"for realism"; the drill works as read-aloud tabletop

Do not run fully unannounced ambush drills on individuals — announced

windows train; ambushes traumatize and get the program cancelled

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="deepfake-drill"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Deepfake Drill is one of 822 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog