Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.
.claude/skills/mkurman-board-update/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 123% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 47% | 0% |
------|-------|-----------------| | 1 | Executive Summary | CEO | Three sentences: current state, major event, next direction | | 2 | Key Metrics Dashboard | COO | 6-8 KPIs in table format with targets and status indicators | | 3 | Financial Update | CFO | P&L summary, cash runway, burn multiple trends, plan variances | | 4 | Revenue & Pipeline | CRO | ARR waterfall, NRR, pipeline stages, top deals with confidence levels | | 5 | Product Update | CPO | Shipped features, upcoming work, user impact evidence, PMF signals | | 6 | Growth & Marketing | CMO | CAC by channel, pipeline contribution, channel testing results | | 7 | Engineering & Technical | CTO | Velocity trends, tech debt ratio, uptime, security status | | 8 | Team & People | CHRO | Headcount vs plan, hiring pipeline, attrition, engagement scores | | 9 | Risk & Security | CISO | Security controls status, compliance deadlines, incidents, top 3 risks | | 10 | Strategic Outlook | CEO | Next quarter priorities ranked, board decisions needed, specific asks | | 11 | Appendix | — | Detailed financials, full pipeline, retention charts, headcount breakdown |
Every section follows: Headline - Data - Narrative - Ask/Next.
Apply this to every section, especially when explaining variances:
This structure works for both positive and negative scenarios.
Investors forgive bad quarters. They do not forgive founders who hide problems until they become crises.
| Format | When | Length | Distribution | |--------|------|--------|-------------| | Monthly email | Seed through Series A | Under 800 words | First week of following month | | Quarterly board deck | Series A onward | 20-30 slides | Pre-read 48 hours before meeting | | Monthly condensed deck | Any stage | 8-12 slides | Metrics, financials, pipeline, risks | | Ad-hoc update | Material events | 1 page, 1 topic | Immediately | | Fundraising deck | Pre-raise | Market/vision focus | Closing ask structure |
process-docs — chain to create an SOP for the internal board-update preparation process, ensuring consistent quality each cycle.pitch-deck — chain when the board update reveals a need to begin fundraising or when the update doubles as a re-up deck for existing investors.User: "Write my February investor update. MRR hit $85K (up from $72K), we hired a VP Engineering, but we lost our largest customer."
Good output excerpt: > TL;DR: February MRR grew 18% to $85K driven by strong mid-market expansion, but we lost Acme Corp ($12K/mo) due to budget restructuring outside our control. We hired Sarah Chen as VP Engineering (ex-Stripe). Net: ahead on product velocity, slightly behind on net revenue retention. 14 months runway remaining. > > Key Metrics > | Metric | Feb | Jan | vs. Plan | > |--------|-----|-----|----------| > | MRR | $85K | $72K | +3% | > | Net New ARR | $156K | $120K | +8% | > | Gross Churn | $12K | $2K | -$10K | > | Burn | $110K | $105K | On plan | > | Runway | 14 mo | 15 mo | On plan | > > On the churn: Acme Corp's new CFO cut all software contracts under $50K ARR during a company-wide cost reduction. We had 30 days notice and attempted a reduced plan; they declined. This was not a product failure, but it exposes revenue concentration risk — Acme was 14% of MRR. We are diversifying our top-10 account exposure. > > Asks > 1. Intros to mid-market fintech companies — specifically VP Operations or Head of Compliance contacts. > 2. Referrals for a Senior Backend Engineer. JD attached.
User: "We're going to miss our quarterly target by a lot. Help me write this update."
Good output approach: Open with the miss stated plainly in the executive summary. Quantify the gap. Explain root cause in 2-3 sentences using owned language, not excuses. Follow immediately with the remediation plan including timeline and revised forecast with confidence levels. Close with specific asks for help. Never let bad news be the last thing the reader sees — always end with forward momentum and concrete next steps.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,389 | 11,890 | +27% | 1 | 1 | 0% | 1,658 | 3,752 | +126% | 0 | 0 | — |
case-02 | fail→fail | 25,809 | 24,355 | -6% | 1 | 1 | 0% | 3,658 | 5,468 | +49% | 0 | 0 | — |
case-03 | fail→fail | 15,184 | 13,228 | -13% | 1 | 1 | 0% | 2,261 | 3,797 | +68% | 0 | 0 | — |
case-04 | pass→pass | 18,031 | 21,634 | +20% | 1 | 1 | 0% | 2,995 | 5,107 | +71% | 0 | 0 | — |
case-05 | pass→pass | 21,306 | 26,861 | +26% | 1 | 1 | 0% | 2,957 | 5,765 | +95% | 0 | 0 | — |
case-06 | pass→pass | 15,217 | 13,677 | -10% | 1 | 1 | 0% | 2,406 | 3,866 | +61% | 0 | 0 | — |
case-07 | fail→pass | 12,916 | 10,485 | -19% | 1 | 1 | 0% | 1,825 | 3,256 | +78% | 0 | 0 | — |
case-08 | fail→pass | 15,249 | 13,037 | -15% | 1 | 1 | 0% | 2,255 | 3,845 | +71% | 0 | 0 | — |
case-09 | fail→fail | 8,022 | 8,216 | +2% | 1 | 1 | 0% | 1,469 | 3,235 | +120% | 0 | 0 | — |
case-10 | fail→fail | 11,130 | 9,839 | -12% | 1 | 1 | 0% | 1,876 | 3,484 | +86% | 0 | 0 | — |
case-11 | fail→fail | 5,228 | 9,030 | +73% | 1 | 1 | 0% | 808 | 3,084 | +282% | 0 | 0 | — |
case-12 | fail→pass | 10,235 | 10,291 | +1% | 1 | 1 | 0% | 1,599 | 3,209 | +101% | 0 | 0 | — |
case-13 | fail→fail | 11,220 | 8,916 | -21% | 1 | 1 | 0% | 1,656 | 2,927 | +77% | 0 | 0 | — |
case-14 | pass→pass | 10,002 | 11,935 | +19% | 1 | 1 | 0% | 1,586 | 3,537 | +123% | 0 | 0 | — |
case-15 | pass→pass | 14,964 | 9,215 | -38% | 1 | 1 | 0% | 2,274 | 3,125 | +37% | 0 | 0 | — |
case-16 | fail→pass | 8,484 | 8,474 | -0% | 1 | 1 | 0% | 1,358 | 3,033 | +123% | 0 | 0 | — |
case-17 | pass→pass | 11,966 | 8,628 | -28% | 1 | 1 | 0% | 1,811 | 3,105 | +71% | 0 | 0 | — |
case-18 | pass→pass | 10,800 | 10,500 | -3% | 1 | 1 | 0% | 1,645 | 3,279 | +99% | 0 | 0 | — |
case-19 | fail→pass | 15,345 | 11,633 | -24% | 1 | 1 | 0% | 2,361 | 3,467 | +47% | 0 | 0 | — |
case-20 | fail→pass | 14,702 | 12,577 | -14% | 1 | 1 | 0% | 2,250 | 3,653 | +62% | 0 | 0 | — |
case-21 | fail→pass | 15,277 | 18,981 | +24% | 1 | 1 | 0% | 2,344 | 5,027 | +114% | 0 | 0 | — |
case-22 | fail→fail | 15,714 | 11,207 | -29% | 1 | 1 | 0% | 2,419 | 3,322 | +37% | 0 | 0 | — |
case-23 | pass→pass | 14,475 | 14,097 | -3% | 1 | 1 | 0% | 2,023 | 3,864 | +91% | 0 | 0 | — |
case-24 | fail→fail | 11,240 | 9,553 | -15% | 1 | 1 | 0% | 1,880 | 3,416 | +82% | 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 +29 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.
Other measured skills in the registry, with their headline benchmark lift.