Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →code-saurabh/office-hours
Pre-code ideation and startup validation skill.
Passed 14 of 23 test cases with the skill, and 5 of 23 without it.
and 16 more in the full report
10 fixed4 passed either way8 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are considering a new B2B marketplace direction for local food producers, but we want to validate the idea before drafting product specs or tech architecture. Help me evaluate if this is worth building. Interrogate my market assumptions one question at a time, expose hidden gaps, and format the final outcome into a design document ready for strategic review.
| Checked | Without skill | With skill |
|---|---|---|
| Begins with a context acknowledgment summarizing the B2B food marketplace proposal | Missed | Passed |
| Asks a single question focused on demand reality and specific desperate customers | Passed | Passed |
The instructions your model reads when the skill loads.
Run this skill before any code is written. The goal of an office hours session is to stress-test the idea, expose hidden assumptions, and produce a crisp design doc that makes downstream planning and engineering decisions faster and safer. Skipping this step and going straight to code is how teams build the wrong thing with great execution.
Office hours is not brainstorming for its own sake. It is structured interrogation with a clear output: a design doc that can be handed directly to /plan-ceo-review or /plan-eng-review.
Proactively invoke this skill — do not answer directly — when:
Always run office hours before:
/plan-ceo-review (strategy scope)/plan-eng-review (architecture decisions)Detect which mode applies based on context. Ask if unclear.
Triggers: B2B or B2C product, SaaS, marketplace, consumer app intended to find customers and generate revenue.
Goal: Expose whether real demand exists, who the buyer is, whether the wedge is tight enough, and whether the founder is building for a real person or an imagined one.
Posture: Act as a YC partner running a 10-minute office hours session. Be direct, be skeptical of assertions, demand specificity. Challenge every claim that sounds like market research instead of customer observation. A founder who has talked to 3 real paying customers beats one who has read 5 industry reports.
Triggers: Side project, open-source tool, hackathon build, learning project, personal automation, indie product.
Goal: Clarify the builder's intent (learn, ship, explore, impress), identify the simplest version that delivers that outcome, and surface the traps that turn fun projects into abandoned half-finished repos.
test cases passed, vs 5 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.