What do I need to use Deck Outline First?

The deck's job; The audience and the time slot; The material; The reviewer.

Is Deck Outline First free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Deck Outline First

Q: How do I know the Deck Outline First output is good?

The skill verifies itself against its own quality checks: Every slide title is a disagreeable claim sentence; The headline sequence survives the skim test as a complete argument; Each headline's evidence exists and fits one slide; The slide count fits the time slot's arithmetic.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Outline a deck as headline sentences before opening the slide tool — each slide a claim that reads as an argument top to bottom, the audience-and-ask header, and the skim test that catches broken decks while they're still bullet points. Use when asked start this presentation, structure my deck, why does my deck feel like a data tour, or get sign-off before I build slides. Produces the headline outline, the per-slide evidence notes, the skim test result, and the build rules.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The deck's job — what the audience should decide or do at the end ([meeting-prep-pack](../meeting-prep-pack/SKILL.md) walk-away logic applies to the presenter too); decks without asks are documentaries

▸The audience and the time slot — 10 minutes with executives is 6–8 slides; the slot arithmetic caps ambition before the outline overcommits

▸The material — the findings/evidence available; headlines claim only what evidence can carry ([evidence-grading](../evidence-grading/SKILL.md) keeps the claims honest)

▸The reviewer — who would restructure this in review; they see the outline, not the finished deck

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every slide title is a disagreeable claim sentence

✓The headline sequence survives the skim test as a complete argument

✓Each headline's evidence exists and fits one slide

✓The slide count fits the time slot's arithmetic

✓The outline was reviewed before slideware opened

⚠️ What it refuses to do

Do not open the slide tool first — formatting is where broken arguments hide from their authors

Do not title slides with topics — topics defer the argument to the live room

Do not stack claims on one slide — one headline, one slide, or the skim test lies

Do not headline what evidence can't carry — the outline is where overclaims are cheap to fix

Do not let the build drift from the outline — every silent new slide re-breaks the tested argument

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="deck-outline-first"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Deck Outline First is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog