Install
$ agentstack add skill-mohitagw15856-pm-claude-skills-board-pre-read ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Board Pre-Read Skill
The best board meetings spend zero time on status because the board already read it. A pre-read sent 48+ hours ahead does that: it conveys the state of the business and, crucially, tells the board exactly what input and decisions are needed — so the meeting is discussion and decisions, not a slide-reading session. This skill structures that document.
Required Inputs
Ask for these only if they aren't already provided:
- The headline — the one thing the board should take away this period (good or bad).
- Metrics vs. plan — the key numbers against the plan/forecast (revenue, growth, burn, runway, the north-star).
- What changed — major wins, misses, and shifts since last meeting.
- Decisions/asks — what you actually need from the board (approval, input, introductions).
Output Format
Board Pre-Read — [company], [month/quarter]
Sent: [date, ≥48h before the meeting]
1. TL;DR — 3–5 bullets: the state of the business, the headline, runway, and the decisions you're bringing. A busy board member should get the gist from this alone.
2. Metrics dashboard — the core numbers vs. plan, with the trend and a one-line "so what" each. Show misses honestly — boards trust founders who surface bad news first.
| Metric | This period | vs. plan | Trend | Note | |---|---|---|---|---|
3. What's working — the 2–3 things going well and why (so they can be doubled down on).
4. What's not — the 2–3 problems, what you're doing about them, and where you want the board's help. Candour here is the whole game.
5. Decisions & asks — explicit: "We're asking the board to approve X" / "We'd value input on Y" / "We need intros to Z." Tie each to the agenda.
6. Risks & watch-items — the top risks to the plan and runway, and the leading indicators you're watching.
Appendix — detail, financials, and supporting data (linked, not inline).
Quality Checks
- [ ] It's genuinely a pre-read — sent ahead, readable without a presenter
- [ ] The TL;DR stands alone for a time-pressed director
- [ ] Metrics are shown vs. plan, with misses surfaced honestly (not buried)
- [ ] The decisions/asks for the board are explicit and tied to the agenda
- [ ] Runway and the top risks are stated plainly
Anti-Patterns
- [ ] Do not save bad news for the live meeting — boards punish surprises; lead with the hard numbers
- [ ] Do not send a deck to be read aloud — a pre-read is prose/dashboards designed for solo reading
- [ ] Do not omit the asks — if the board doesn't know what you need, the meeting defaults to status theatre
- [ ] Do not vanity-metric the dashboard — show the numbers that govern the business, against plan
- [ ] Do not inline 40 pages of appendix — link the detail; keep the core pre-read tight
Based On
Board-management practice — pre-circulated reading, metrics-vs-plan transparency, and decision-focused agendas.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mohitagw15856
- Source: mohitagw15856/pm-claude-skills
- License: MIT
- Homepage: https://mohitagw15856.github.io/pm-claude-skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.