Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Board Update · mkurman | DecimalAI

financeby mkurman

Board Update

mkurman/board-update

Source mkurman/zorai ↗License MIT

When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

SkillScore63Maintained

Automatic

Project Management pack

Last verified 8/21/2026

What it changes

Passed 15 of 24 test cases with the skill, and 8 of 24 without it.

Without skill33%

With skill63%

Checks it passed that the model alone missed

The update follows the four-step sequence: Headline, Data, Narrative, Ask/Next.
The response recommends keeping the quarterly board deck within 20 to 30 slides.
The section commentary follows the sequence: Headline, Data, Narrative, Ask/Next.

and 7 more in the full report

7 fixed8 passed either way9 still failing0 broke

Pass-rate lift: +29 pp
Tokens: +82%
Agent turns: 0%
Response time: -4%

Model gemini-3.6-flashMeasured 8/21/2026v115 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/mkurman-board-update/SKILL.md https://app.decimal.ai/s/mkurman-board-update/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add mkurman-board-update, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/mkurman-board-update/ and pins it in .decimal/skills.lock

decimalai skills add mkurman-board-update

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/mkurman-board-update/SKILL.md https://app.decimal.ai/s/mkurman-board-update/SKILL.md

Raw file: /s/mkurman-board-update/SKILL.md ↗ · machine-readable summary at /s/mkurman-board-update.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Draft Section 5 (Product Update) for our monthly report. We shipped automated reporting, user engagement grew 25%, and retention rate reached 85%.

What was checked, without and with the skill
Checked	Without skill	With skill
The update follows the four-step sequence: Headline, Data, Narrative, Ask/Next.	Missed	Passed
The narrative details shipped features accompanied by user impact or product-market fit signals.	Passed	Passed

case-16 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md103 linessingle file

------|-------|-----------------| | 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.

Frameworks & Best Practices

The Four-Act Narrative Structure

Apply this to every section, especially when explaining variances:

Prior targets — what we said we would do
Current reality — what actually happened
Gap explanation — why (owned cause, not excuses)
Remediation — specific fixes with timeline

This structure works for both positive and negative scenarios.

Transparent Bad-News Delivery

State the fact plainly. "We missed our Q3 revenue target by 22%." No euphemisms.
Own the cause. "Two enterprise deals worth $180K ARR slipped to Q4 due to procurement delays we did not anticipate." Do not lead with context or excuses.
Demonstrate understanding. Show the analysis that explains the root cause.
Present specific fixes. "We implemented procurement-tracking in our sales process and added 30 days of buffer to enterprise deal timelines."
Update the forecast. "Revised Q4 target is $X." Include confidence levels, not single-point estimates: "High confidence $2.6M, upside to $2.9M if two late-stage deals close."
Ask for help if needed. "A warm intro to their CFO would accelerate procurement."

Investors forgive bad quarters. They do not forgive founders who hide problems until they become crises.

Metrics Presentation Rules

Track record

Benchmark

15 / 24

test cases passed, vs 8 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mkurman / zorai

skills/nontechnical/startup-founder-skills/board-update/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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.