Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:onboard — Founder interview that populates ~/.claude/company-context.md using the canonical 7-dimension cs-onboard schema. The first command to run when starting with c-level-agents. Use when setting up the virtual C-suite for a new company, or when advisors lack company context — e.g. before a first /cs:boardroom or after a fundraise changes the numbers.
.claude/skills/alirezarezvani-onboard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 112% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 2% | 0% |
Command: /cs:onboard
The first command to run when adopting c-level-agents. A structured founder interview that produces ~/.claude/company-context.md — the file every cs- advisor reads before responding. Without this, the advisors are guessing.
~/.claude/company-context.md — a single file with the durable facts about the company. Read by:
cs-chief-of-staff (routing decisions)/cs:brief (assumptions in any new decision)Canonical schema: ~/.claude/company-context.md is owned by the cs-onboard skill and follows its 7-dimension schema (../../../c-level-advisor/skills/cs-onboard/templates/company-context-template.md): Company Identity, Stage & Scale, Founder Profile, Team & Culture, Market & Competition, Current Challenges, Goals & Ambition. The 12 questions above are a faster structured intake that populates that same file — Identity/Business/Financial → Stage & Scale, Team → Team & Culture, Quarter priorities/risks → Current Challenges + Goals & Ambition. Write [not captured] for dimensions the quick intake doesn't reach (Founder Profile, Market & Competition); run the full cs-onboard interview to fill them. Never create a second context file or a divergent layout.
The intake summary captured by the 12 questions:
markdown# Company Context **Generated:** YYYY-MM-DD **Last updated:** YYYY-MM-DD ## Identity - **Company:** <name> - **Pitch:** <one sentence> - **Stage:** <stage> - **HQ + remote:** <distribution> ## Business - **Model:** <type> - **ICP:** <description + named customer> - **ACV:** $<median> (range $<low> - $<high>) - **Deal count (LTM):** N - **ARR growth (YoY):** X% ## Financial - **Cash on hand:** $<amount> - **Net burn (monthly):** $<amount> - **Runway base:** N months - **Runway bear:** N months - **Last raise:** $<amount> at $<post> in <month YYYY>, led by <investor> ## Team - **Total headcount:** N - **Eng:** N | Product: N | GTM: N | Ops: N | G&A: N ## Quarter - **Top priorities (Q<X> YYYY):** 1. <priority> 2. <priority> 3. <priority> - **Top risks:** 1. <risk> 2. <risk> 3. <risk> ## Routing Hints [Optional: any role the founder wants to use sparingly or rely on heavily]
~/.claude/company-context.mdbash ln -sf ~/company-vault/00-meta/company-context.md ~/.claude/company-context.md
/cs:boardroom for a high-stakes decisionBy default, ~/.claude/company-context.md is local to the founder's machine. To make it persistent across machines / shareable:
../../references/llm-wiki-bridge.md~/.claude/cs-onboard — the underlying interview protocolcontext-engine — reads this file../../references/llm-wiki-bridge.mdVersion: 1.0.0
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | fail→fail | 26,416 | 24,049 | -9% | 1 | 1 | 0% | 3,679 | 4,440 | +21% | 0 | 0 | — |
case-03 | fail→pass | 7,972 | 4,772 | -40% | 1 | 1 | 0% | 1,316 | 2,205 | +68% | 0 | 0 | — |
case-09 | fail→pass | 16,830 | 11,378 | -32% | 1 | 1 | 0% | 1,921 | 2,412 | +26% | 0 | 0 | — |
case-01 | fail→pass | 13,872 | 12,161 | -12% | 1 | 1 | 0% | 1,441 | 2,547 | +77% | 0 | 0 | — |
case-02 | fail→pass | 6,953 | 11,643 | +67% | 1 | 1 | 0% | 1,215 | 2,571 | +112% | 0 | 0 | — |
case-04 | fail→pass | 24,528 | 8,166 | -67% | 1 | 1 | 0% | 2,686 | 2,739 | +2% | 0 | 0 | — |
case-05 | pass→pass | 16,842 | 8,201 | -51% | 1 | 1 | 0% | 1,779 | 2,669 | +50% | 0 | 0 | — |
case-06 | pass→pass | 18,287 | 12,373 | -32% | 1 | 1 | 0% | 2,041 | 2,554 | +25% | 0 | 0 | — |
case-07 | fail→pass | 15,494 | 8,979 | -42% | 1 | 1 | 0% | 1,638 | 2,059 | +26% | 0 | 0 | — |
case-08 | fail→pass | 17,805 | 2,833 | -84% | 1 | 1 | 0% | 1,795 | 1,856 | +3% | 0 | 0 | — |
case-10 | fail→pass | 7,858 | 2,749 | -65% | 1 | 1 | 0% | 1,309 | 1,703 | +30% | 0 | 0 | — |
case-11 | fail→pass | 11,179 | 7,633 | -32% | 1 | 1 | 0% | 934 | 1,712 | +83% | 0 | 0 | — |
case-12 | pass→pass | 12,264 | 7,807 | -36% | 1 | 1 | 0% | 1,948 | 1,785 | -8% | 0 | 0 | — |
case-13 | pass→pass | 11,564 | 11,304 | -2% | 1 | 1 | 0% | 1,826 | 2,542 | +39% | 0 | 0 | — |
case-19 | fail→pass | 12,051 | 3,232 | -73% | 1 | 1 | 0% | 955 | 1,839 | +93% | 0 | 0 | — |
case-14 | pass→pass | 14,725 | 10,470 | -29% | 1 | 1 | 0% | 2,474 | 3,231 | +31% | 0 | 0 | — |
case-15 | pass→pass | 10,834 | 3,275 | -70% | 1 | 1 | 0% | 1,727 | 1,854 | +7% | 0 | 0 | — |
case-16 | fail→pass | 11,586 | 2,171 | -81% | 1 | 1 | 0% | 959 | 1,724 | +80% | 0 | 0 | — |
case-17 | fail→pass | 18,104 | 13,955 | -23% | 1 | 1 | 0% | 2,105 | 2,868 | +36% | 0 | 0 | — |
case-18 | pass→pass | 16,729 | 2,996 | -82% | 1 | 1 | 0% | 1,981 | 1,844 | -7% | 0 | 0 | — |
case-21 | fail→fail | 8,158 | 8,040 | -1% | 1 | 1 | 0% | 469 | 2,515 | +436% | 0 | 0 | — |
case-22 | fail→fail | 17,769 | 28,968 | +63% | 1 | 1 | 0% | 3,311 | 6,583 | +99% | 0 | 0 | — |
case-23 | pass→pass | 14,650 | 10,862 | -26% | 1 | 1 | 0% | 1,936 | 2,768 | +43% | 0 | 0 | — |
case-24 | fail→pass | 17,641 | 18,977 | +8% | 1 | 1 | 0% | 2,293 | 3,259 | +42% | 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. 24 cases were attempted. The headline lift of +54 percentage points is the difference between those two pass rates over the 24 comparable cases.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/11/2026 | +39% |
Other measured skills in the registry, with their headline benchmark lift.