Audit your AI tool stack
Where your data is going, who can see it, what to turn off.
- 1.Open ChatGPT or Claude.Either works. The skill is just text.
- 2.Inspect the real preview, then unlock the full file.One click; no install, no setup.
- 3.Paste it as your first message.The assistant now knows how to do this one job.
- 4.Give it your specifics, get the result.Roughly 15 min, every time you need it.
Give it context. Get back a work product.
Illustrative sample using the same output shape. Verify live facts in the tool you run it in.
Small team using ChatGPT, Claude, Cursor, Perplexity, Notion AI, meeting transcription, and two AI note tools with mixed data policies.
Letting AI tools sprawl across a team until cost, data, and security questions become impossible to answer.
Keep / cut / merge
- Keep: tools with clear owners, business-critical workflows, and acceptable data controls.
- Merge: duplicate note tools unless teams can name different use cases.
- Review: any tool receiving customer data, source code, contracts, or sensitive meeting notes.
30-day cleanup plan
- Week 1: inventory tools, owners, data types, and contract terms.
- Week 2: disable risky defaults and remove inactive seats.
- Week 3-4: consolidate duplicates and document approved use cases.
Sensitive skills copy first and open a blank chat, so your filled context does not travel in the URL.
Sensitive skills copy first and open a blank chat, so your filled context does not travel in the URL.
Fill the blanks first.
Add context before you run it. These fields update the preview and ChatGPT/Claude buttons instantly.
Permanent agent install needs the full body.
This page is only showing a preview. Unlock the full skill to install it in Claude Code, Claude Projects, or a Custom GPT.
# Audit your AI tool stack You are an AI tool risk auditor. I will list the AI tools my team uses, what data goes into them, who uses them, and what settings are enabled. Find practical risk and cleanup steps. ## Output | Tool | Use case | Data sensitivity | Access | Main risk | Fix | Then: - **Tools to keep** - **Tools to restrict** - **Settings to change** - **Data that should never go in** - **Team policy draft:** short and readable. ## Rules [Preview stops here. Unlock the Pro library for the full rules, guardrails, examples, and copyable file.]
This preview is cut from a real Pro workflow. Unlock the founding Pro library for the full file, rules, examples, and installable skill.
- ✓ Input checklist
- ✓ Step-by-step workflow
- ✓ Quality bar
- ✓ Guardrails
- ✓ Output format
- ✓ Example run
- ✓ Install formats