Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:office-hours <topic> — YC-style 6-question founder interrogation before any advice. Forces clarity on problem, customer, distribution, defensibility, capital, and founder fit. Use when a founder question is too vague to route — e.g. 'should we grow faster?' — or before drafting a strategy brief.
.claude/skills/alirezarezvani-office-hours/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 10% | 0% |
Command: /cs:office-hours <topic>
Before any advice, the founder must answer six questions. Modeled on YC office hours: no analysis until the founder has done the thinking. This is the cognitive forcing function that prevents drift into solutionism.
The founder must answer all six in writing before any C-role weighs in.
Whose problem is this, and how do they describe it in their own words?
Who is the ICP? Name one real person who would buy this today.
How does the customer first hear your name?
If this works, what stops a competitor from copying it in 6 months?
What does this cost, when does it pay back, and what's the alternative use of the money?
Why are you the right person to do this — and why does this matter enough to spend the next 3 years on it?
After the founder answers all six, this command produces a one-page brief:
markdown# Office Hours Brief: <topic> **Date:** YYYY-MM-DD **Founder:** <name> ## 1. Problem > [founder's verbatim answer] ## 2. Customer > [founder's verbatim answer] ## 3. Distribution > [founder's verbatim answer] ## 4. Defensibility > [founder's verbatim answer] ## 5. Capital > [founder's verbatim answer] ## 6. Founder Fit > [founder's verbatim answer] --- **Assessment** (one of): - 🟢 GREEN — ship the brief to /cs:boardroom - 🟡 YELLOW — sharpen Q[N] before proceeding - 🔴 RED — kill or redefine; do not proceed
After the brief is GREEN, route to:
/cs:{role}-review/cs:brief then /cs:boardroomMost bad decisions don't fail at execution — they fail at framing. Forcing six concrete answers surfaces the framing weaknesses before anyone burns time on analysis. The founder either fills the gaps or recognizes the question wasn't ready.
This is the YC office hours pattern adapted for Claude Code: the interrogation is the value.
/cs:brief — turn the answers into a one-page strategy brief/cs:boardroom — multi-role deliberation/cs:founder-mode — let the system pick the next stepcs-chief-of-staff triggers /cs:office-hours when intake is unclearVersion: 1.0.0
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 20,191 | 12,429 | -38% | 1 | 1 | 0% | 3,184 | 3,021 | -5% | 0 | 0 | — |
case-05 | pass→fail | 23,784 | 7,340 | -69% | 1 | 1 | 0% | 4,915 | 2,227 | -55% | 0 | 0 | — |
case-06 | pass→pass | 26,332 | 18,264 | -31% | 1 | 1 | 0% | 2,531 | 3,499 | +38% | 0 | 0 | — |
case-11 | pass→pass | 9,225 | 6,430 | -30% | 1 | 1 | 0% | 1,605 | 1,961 | +22% | 0 | 0 | — |
case-03 | fail→pass | 6,311 | 3,764 | -40% | 1 | 1 | 0% | 1,149 | 1,714 | +49% | 0 | 0 | — |
case-01 | fail→pass | 8,568 | 4,247 | -50% | 1 | 1 | 0% | 1,382 | 1,789 | +29% | 0 | 0 | — |
case-02 | fail→pass | 18,221 | 8,656 | -52% | 1 | 1 | 0% | 2,985 | 2,611 | -13% | 0 | 0 | — |
case-07 | fail→fail | 11,708 | 7,598 | -35% | 1 | 1 | 0% | 1,534 | 2,228 | +45% | 0 | 0 | — |
case-08 | fail→pass | 8,854 | 6,725 | -24% | 1 | 1 | 0% | 1,485 | 2,054 | +38% | 0 | 0 | — |
case-09 | fail→pass | 9,312 | 5,433 | -42% | 1 | 1 | 0% | 1,699 | 1,870 | +10% | 0 | 0 | — |
case-10 | pass→pass | 11,522 | 9,406 | -18% | 1 | 1 | 0% | 1,932 | 2,393 | +24% | 0 | 0 | — |
case-12 | fail→pass | 8,165 | 4,764 | -42% | 1 | 1 | 0% | 1,538 | 1,773 | +15% | 0 | 0 | — |
case-13 | pass→pass | 9,700 | 7,168 | -26% | 1 | 1 | 0% | 1,593 | 2,137 | +34% | 0 | 0 | — |
case-14 | fail→pass | 9,162 | 4,230 | -54% | 1 | 1 | 0% | 1,677 | 1,871 | +12% | 0 | 0 | — |
case-15 | pass→pass | 7,959 | 3,957 | -50% | 1 | 1 | 0% | 1,337 | 1,580 | +18% | 0 | 0 | — |
case-16 | fail→pass | 10,738 | 3,560 | -67% | 1 | 1 | 0% | 1,796 | 1,598 | -11% | 0 | 0 | — |
case-17 | pass→pass | 6,778 | 5,696 | -16% | 1 | 1 | 0% | 1,274 | 1,847 | +45% | 0 | 0 | — |
case-18 | pass→pass | 7,860 | 3,951 | -50% | 1 | 1 | 0% | 1,335 | 1,700 | +27% | 0 | 0 | — |
case-19 | fail→pass | 9,373 | 6,344 | -32% | 1 | 1 | 0% | 1,519 | 2,081 | +37% | 0 | 0 | — |
case-20 | pass→pass | 11,031 | 7,729 | -30% | 1 | 1 | 0% | 1,888 | 2,206 | +17% | 0 | 0 | — |
case-21 | fail→pass | 8,303 | 6,300 | -24% | 1 | 1 | 0% | 1,379 | 1,913 | +39% | 0 | 0 | — |
case-22 | fail→pass | 13,382 | 7,268 | -46% | 1 | 1 | 0% | 2,207 | 2,235 | +1% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.