Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsBoard Pack & Executive Summary — Narrative, Finance Framing
Uncomfortable facts—concentration risk, burn over plan, delayed mega-deals—get softened until Q&A goes badly.
$19
Board Pack & Executive Summary — Narrative, Finance Framing
Example session with this skill installed
Company: HelioGrid — Series B climate-tech VPP platform for utilities
Period: Q2 2026 board
Board: growth VC, climate fund, ex-utility operator, financial director
Metrics: 420 MW (target 500), ARR $12.6M (target $14M), GM 61% (target 65%),
NRR 112%, burn $890k/mo (ceiling $800k), cash $18.4M, pipeline $7.1M vs $9M
Progress: optimizer shipped; ERCOT connector 70% / 5 wks late
Risks: MidwestCo ~90 MW stuck on PUC docket; River Municipal SLA escalation
Draft ask: approve +4 field FTEs
Compose pack: tension, red flags, finance, decidable options, Q&A. No invented metrics.
- Read your context and instructions
- Compiled the board & executive
Board Pack & Executive Summary
1. Pack Summary
Mode: Compose · Series B climate/VPP · Q2 2026
Verdict: NEEDS-STRENGTHENING
2. Executive Summary
420 MW (+60 QoQ) and $12.6M ARR (+18% QoQ) but under plan. Burn $890k above $800k
ceiling; ~20.7 mo base runway on $18.4M cash (heuristic). Elephant: MidwestCo PUC delay
while asking for more FTEs. Recommend phased hire (Option B), not blanket +4.
3. Narrative arc
Headline: real growth; regulatory timing + burn discipline are the story.
Tension addressed head-on with controllable actions (ERCOT, River war-room, phased spend).
4. Red flags (framed)
Plan miss on MW/ARR · burn over ceiling · GM mix · MidwestCo binary · River escalation
5–6. KPIs + financial intelligence
Dashboard with target/actual/so-what; burn multiple heuristic; base/downside runway;
unit economics marked incomplete (data gaps).
7–8. Progress & risks
Optimizer shipped; ERCOT late; CS automation blocked. Risks owned with mitigations.
9. Decidable ask
A full +4 · B phased 2 now + gate · C freeze → recommend B
10. Q&A rehearsal
MidwestCo real? · Hire into miss? · Services company (GM)? · River churn? · True runway?
11–14. Appendix, trajectory N/A, data gaps, path to BOARD-READY
Not financial advice. JSON includes full structure + not_financial_advice: true
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
- Board packs often bury the only thing directors care about under operational noise.
- Uncomfortable facts—concentration risk, burn over plan, delayed mega-deals—get softened until Q&A goes badly.
- Asks like “approve more headcount” arrive without options, recommendation, or capital context.
- Founders under-rehearse the questions a VC, operator, or financial director will actually ask.
What it does
- Adapts to company stage and board composition (VC, climate/impact, operator, financial).
- Builds a narrative arc with the elephant in the room named and addressed.
- Surfaces red flags with pre-emptive honest framing and a plan.
- Runs financial intelligence on your numbers: burn multiple heuristics, base/downside runway, unit-economics coherence checks, gross margin context.
- Contextualizes every KPI (target, actual, trend, variance, “so what”).
- Rewrites vague asks into decidable decisions with options and a recommendation.
- Produces a ranked Q&A rehearsal with answers and data to have ready.
- Issues BOARD-READY / NEEDS-STRENGTHENING / NEEDS-DATA with a clear path.
Frameworks & tools
- Modes: Compose, Critique, Rehearse, Track.
- Works for SaaS, climate-tech, marketplaces, and other venture-backed or growth companies—stack-agnostic.
- Compatible with Claude Code, Cursor, Codex CLI, OpenClaw; no live board portal integration required.
Why this beats prompting it yourself
- Thinks like the board first, not like an internal ops report.
- Forces tension and red flags into the open with framing, not burial.
- Financial checks are explicit and assumption-labeled—not fake precision.
- Asks must be decidable; open-ended “support us” language gets rewritten.
- Q&A is ranked by likelihood × difficulty with data prep lists.
- Clear “not financial advice” boundary and no fabricated benchmarks.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
• Does not invent metrics or pull live data systems
• Not financial, legal, or investment advice
• Stage benchmarks are heuristics and labeled as such
• Without a prior pack, trajectory is unavailable
• Does not send the pack to the board for you
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 21 days ago
Permissions
This skill only uses the metrics and notes you paste or open. It drafts a pack for you to edit and send. It does not contact directors, invent KPIs, or access bank/accounting APIs. Grant Read only.