Skip to main content
ClaudeWave
Skill1.3k repo starsupdated 3d ago

all-hands-deck

Build an all-hands that lands with everyone from intern to VP — the mixed-altitude structure (the story for all, the numbers for some), the wins-with-names section done right, the hard-news slide handled straight, and the Q&A design that gets real questions. Use when asked build the all-hands deck, make the monthly town hall not boring, how do we share the numbers with everyone, or announce this change at all-hands. Produces the segment structure, the altitude-mixed content rules, the hard-news handling, and the Q&A mechanics.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/all-hands-deck && cp -r /tmp/all-hands-deck/exports/openclaw/all-hands-deck ~/.claude/skills/all-hands-deck
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# All Hands Deck Skill

The all-hands serves the widest audience in the company — new hires and executives, engineers and sales, the anxious and the checked-out — and decks built for any single altitude lose the rest: pure strategy bores the floor, pure metrics baffle the new, pure celebration reads as evasion in a hard quarter. The working structure mixes altitudes deliberately (the story everyone follows, the numbers that keep trust, the wins with *names*, the hard news handled straight), and treats the Q&A as a designed segment — because the questions people actually have determine what the meeting was *about*, whatever the slides said.

## What This Skill Produces

- **The segment structure** — the recurring skeleton: the narrative open, numbers, wins-with-names, the focus segment, hard news when owed, Q&A
- **The altitude rules** — per segment: what the newest hire needs vs. what the veterans check
- **The hard-news handling** — straight, early, with the what-it-means-for-you answered before it's asked
- **The Q&A mechanics** — pre-submitted + live, the no-softball discipline, and the answer-or-commit rule

## Required Inputs

Ask for these if not provided:
- **The month's material** — the numbers, the wins, the news (including the uncomfortable); the deck is assembled from reality, and the temptation to skip the bad month is the trust-killer to resist
- **The company's current mood** — post-layoff, post-win, mid-uncertainty; the structure holds but the emphasis calibrates (anxious companies need the hard-news slide *more* prominent, not less)
- **The metrics that recur** — the same 4–6 every time ([kpi-tracker-design](../kpi-tracker-design/SKILL.md) discipline: trends visible, definitions stable), because rotating metrics read as narrative management
- **The Q&A history** — what got asked last time, what went unanswered; unanswered questions compound

## Framework: The Structure Rules

1. **Open with the story, one slide:** the month in one narrative sentence ("we shipped the platform bet and paid for it in support load — here's both") — the frame everyone, at every altitude, carries through the numbers. Openings that jump to dashboards ask the floor to build their own narrative, and they build worse ones.
2. **The same numbers, trended, every time:** the recurring 4–6 metrics with their history visible ([data-slide-design](../data-slide-design/SKILL.md) rules) — consistency is the trust mechanism; a metric that vanishes the month it dipped teaches everyone to read absences. Down months get shown *with the same prominence* and one honest sentence of why.
3. **Wins carry names, and names rotate:** specific work by specific people ("the checkout rewrite — Ana, Jorge, and the platform team — cut latency 40%") — the recognition segment is half the meeting's retention value, and the rotation audit (who *hasn't* been named lately?) keeps it from becoming the same five people's highlight reel.
4. **Hard news goes early and straight:** the miss, the departure, the change — stated plainly in the deck's first half ([changelog-for-humans](../changelog-for-humans/SKILL.md) breaking-first logic), with the what-it-means-for-you slide answering the question every seat is silently asking. Bad news buried at slide 30, or worse left for Q&A extraction, converts one bad fact into a credibility debt.
5. **Q&A is designed, not appended:** pre-submitted questions (anonymous channel — the real ones need cover) mixed with live, the hardest pre-submitted question *taken first* (the signal that the segment is real), and the answer-or-commit rule: every question gets an answer or a named owner and date ("I don't know — [name] will post the answer by Friday"). The unanswered-question log is next month's open.

## Output Format

# All-Hands: [month] — [T] min

## The Structure
| Segment | Content | Altitude notes | Min |
|---|---|---|---|
[Story open (1 slide) · Numbers (the standing 4–6, trended) · Wins (names, rotated) · Focus topic · Hard news (early, if owed) · Q&A (designed)]

## Hard News Handling (when present)
[The plain statement · the what-it-means-for-you slide · placed at segment [early]]

## Q&A Mechanics
[The anonymous pre-submit channel · hardest-first rule · answer-or-commit with owners · last month's open questions, answered]

## Quality Checks

- [ ] The open is one narrative sentence, not a dashboard
- [ ] The metrics are the standing set, trended, shown in down months at full prominence
- [ ] Wins name people, and the rotation was checked
- [ ] Hard news appears early with the for-you slide
- [ ] Q&A takes the hardest pre-submitted question first, and last month's commits were honored

## Anti-Patterns

- [ ] Do not rotate metrics by convenience — the vanishing-metric tell reads louder than any bad number
- [ ] Do not celebrate through a hard month — the floor already knows; festivity reads as distance
- [ ] Do not thank "the whole team" generically — names or it's wallpaper
- [ ] Do not soften Q&A by selection — cherry-picked softballs teach people to stop submitting
- [ ] Do not leave commits unhonored — one forgotten "we'll get back to you" discounts every future one
ai-ethics-reviewSkill

Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.

ai-product-canvasSkill

Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.

design-handoff-briefSkill

Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context, success criteria, constraints, edge cases, and out-of-scope boundaries.

experiment-designerSkill

Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation.

multi-source-signal-synthesiserSkill

Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.

data-analysis-standardSkill

Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data change to stakeholders, or find the root cause of a metric movement. Produces a structured analysis with question, root cause, confidence level, and recommended action.

product-health-analysisSkill

Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.

retention-analysisSkill

Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.