Rude Q&A: The Constructive Devil's Advocate
Stress-test any decision, plan, pitch, or positioning against sharp questions until you can defend it or admit it isn't ready. Adapted from Rude Q&A: The constructive devil's advocate.
- Input
- A plan, pitch, decision, or positioning — a one-line dilemma or a fully-supported brief.
- Output
- A markdown document with sharpened decisions, accepted consequences, and the next questions you owe yourself.
What this is about
The hardest part of a hard decision is that you cannot interrogate yourself. Denial and rationalization are the default human operating mode, which is why strategy documents are full of optimism and confirmatory data instead of the scary challenges actually facing the business. The way through is an outside attacker — someone willing to ask the unfair questions, refuse fluffy answers, and stay on a point until you've earned a real answer.
This skill turns Claude into that attacker. Bring it anything you're attached to and uncertain about — a decision, a plan, a pitch, a target market, a pricing scheme, an idea still forming — as a one-line dilemma or a fully-supported brief. Claude will grill it from every angle, including the unfair ones, dwell wherever your answers go fuzzy, and refuse to wrap up with "approximately fine." You walk away with one of three honest outcomes: a sharpened plan made of real decisions with consequences explicitly accepted, a clear list of what you need to gather or decide before the plan can be defended, or the admission that it was the wrong idea after all.
The exercise is "heavy bat" practice — swinging against attacks harder than reality will deliver, so that reality feels easy. The questions are deliberately rude; the framing around them is collegial. The final output is a markdown document capturing the decisions, the reasoning, the consequences you accepted, and where you were uncomfortable along the way.
Example invocation
You can invoke the skill like this:
/asb-rude-qa I'm writing a book which is outlined in the file
/Users/jcohen/book/Hidden Multipliers. In that file you can also see who
my audience is and why they should be interested in it. I don't know
exactly who my ICP is or how to market it.
Every soft spot gets pressed — ICP, differentiation, market size, competitive alternatives — until you've earned a real answer or admitted what you still need to find out.
One practical note: say where you're working. Name a directory (or point at your existing files) when you invoke, and the skill keeps the method's files together there — if you don't, it asks before creating anything.
From the source
Two articles form the foundation of this skill:
- Rude Q&A: The constructive devil's advocate — the technique itself, including why unfair, hostile, even erroneous questions are a feature rather than a flaw, and why dissatisfaction with your own answer is the signal the exercise is working.
- Failure to face the truth — the philosophical scaffolding underneath: why denial and rationalization are the default human operating mode, and why an outside attacker is the only reliable way through. Rude Q&A is the operational answer to the question this article poses.
Supporting articles each cover a piece of the mechanism or the target the interrogator is reaching for:
- What makes a strategy great — defines "Candid" and "Decisive" as non-negotiable qualities of strategy. Those qualities are the target state the interrogation drives toward.
- Strategic choices: When both options are good — what a real decision looks like (both sides smart, consequences accepted, mutually reinforcing). That's the conclusion phase of the exercise.
- The "Opposite Test" — the specific stress-test the interrogator uses to detect meaningless claims and force them into real choices.
- Scars — why even highly introspective operators cannot fix their blind spots alone, which is the deepest reason this skill needs to exist at all.