The Fool plays devil’s advocate with method. It restates your position in its strongest form, asks which kind of challenge you want, then applies one of five reasoning modes: Socratic questioning, dialectic, pre-mortem, red team or evidence audit.
It presents the three to five strongest challenges, waits for your response, and finishes with a synthesis and an offer of a second pass in a different mode.
What You Get
- A five-step flow: identify, select, challenge, engage, synthesize
- Two-step mode selection through structured questions to the user
- Five modes, each with an output template: assumption inventory, counter-argument, ranked failure narratives, attack vectors, evidence audit
- Six reference files, one per mode plus a mode selection guide
Common Use Cases
- Pre-mortem on an architecture before implementation starts
- Challenging a vendor or technology choice
- Red-teaming a design for abuse and perverse incentives
- Checking whether the evidence behind a business proposal supports its conclusion
What Makes It Unique
Most review skills look at code. This one reviews the reasoning behind a decision. It requires a steelman before any challenge, caps the challenges at the strongest few, forbids strawmen and stacked minor objections, and always ends with a synthesis the user can act on.
Under The Hood
The skill loads SKILL.md and opens one reference file for the chosen mode. It asks you questions through the agent’s structured question tool to pick the mode, and it waits for your reply before it synthesizes. It runs no commands, calls no APIs, fetches no web pages and writes no files. The skill ships no scripts.