- Home
- Skills
- Agents & Orchestration
- Idea Stress-Test
Idea Stress-Test
Pressure-test a new idea before you build it: a critic attacks it from 8 angles, then your agent sorts every objection into real risk, over-worry or your call.
Free
Works with the AI Agents you already use
About this skill
Most AI critique is either flattery or a wall of worst cases. This skill runs a loop that sits in between.
How it works
- A critic (a separate subagent where your agent supports one, otherwise an explicit inline pass) assumes the idea will fail and attacks it from eight angles: load-bearing assumptions, problem and value, prior art, feasibility, cost vs payoff, execution fit, a pre-mortem and blind spots.
- Your agent then filters every objection into real risk, over-worry (with the reason, so you can overrule it) or your call, and asks only the 2-4 questions that change the decision.
- It loops on your answers until the idea holds up, capped at three rounds, and scales the effort to the stakes.
- Once the idea matures, it records the final form, the cracks found and how each one was resolved.
Works with any agent that loads SKILL.md files (Claude Code, OpenCode, Codex CLI and others). Also on GitHub: Kenny-JT/idea-stress-test.
MIT licensed.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account