claude-code-deck
Skill145 starsChanged 6 months agoMITView on GitHub
Generate a complete, ready-to-share HTML presentation explaining Claude Code, Skills, Sub Agents, Hooks, and Multi-Agent Systems — designed for product managers. Outputs a single zero-dependency HTML file in Bold Signal style (dark, orange accents). Use when someone wants a polished explainer deck for Claude Code concepts.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 55
If the user wants to rebuild or customise the deck, use frontend-slides skill with these parameters:
- Distinctive: line 63
Follow the slide outline above as the content structure.
- Very specific: line 66
Use clamp() for all font sizes
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude Code Deck
Generate a production-ready, 11-slide HTML presentation on Claude Code's five core primitives — targeted at product managers and non-technical audiences.
What This Skill Produces
A single presentation.html file featuring:
- 11 slides covering Claude Code, Skills, Sub Agents, Hooks, Multi-Agent Systems, architecture, PM use cases, and next steps
- Bold Signal style: dark background (#080810), orange accents (#f5a623), geometric diagonal shapes, clean Helvetica typography
- Zero dependencies: fully self-contained, works offline
- Navigation: arrow keys, spacebar, click, swipe — progress bar, slide counter
- Speaker notes: press
Nto toggle per-slide notes
Slide Outline
| # | Title | Core Insight |
| 1 | Title | Ship with Claude Code |
| 2 | What is Claude Code? | AI pair programmer in your terminal — reads, edits, runs, ships |
| 3 | The PM Superpower | Hours vs. engineering weeks |
| 4 | Concept 01 — Skills | Reusable workflows triggered by a slash command |
| 5 | Skills in Action | 6 real examples from the course |
| 6 | Concept 02 — Sub Agents | Delegate to specialist AI workers with isolated context |
| 7 | Concept 03 — Hooks | PreToolUse / PostToolUse / Stop / Notification |
| 8 | Concept 04 — Multi-Agent | Parallel fleets, scale beyond a single context window |
| 9 | How It All Fits | Layered architecture: Multi-Agent → Sub Agents → Skills → Hooks |
| 10 | What PMs Are Building | 4 real course builds with time-to-ship |
| 11 | Your Next 3 Steps | Install → run a skill → build a multi-agent workflow |
Instructions
- Copy the full HTML from
presentation.htmlin the repo root (or regenerate it using the template below). - Save as
presentation.htmlin the working directory. - Open with
open presentation.htmlor deploy to Vercel:mkdir -p /tmp/claude-deck cp presentation.html /tmp/claude-deck/index.html cd /tmp/claude-deck && vercel deploy --yes - Share the Vercel URL. The deck is live in under 60 seconds.
Regeneration Template
If the user wants to rebuild or customise the deck, use frontend-slides skill with these parameters:
- Topic: Claude Code — Skills, Sub Agents, Hooks, Multi-Agent Systems
- Audience: Product managers and non-engineers
- Slides: 11
- Style: Bold Signal (dark bg #080810, orange accent #f5a623, diagonal geometric shapes, Helvetica)
- Vibe: Impressed / Confident
Follow the slide outline above as the content structure. Every slide must:
- Have a one-insight headline (not a topic label)
- Fit entirely within
100vh— no scrolling - Use
clamp()for all font sizes - Include speaker notes in
data-notesattribute
Bold Signal Design Reference
/* Core palette */
--bg: #080810;
--accent: #f5a623;
--accent2: #f04e23;
--text: #ffffff;
--muted: rgba(255,255,255,0.5);
/* Background shape (right diagonal) */
position: absolute; top: -25%; right: -8%; width: 52%; height: 140%;
background: linear-gradient(145deg, #f5a623, #f04e23);
clip-path: polygon(22% 0%, 100% 0%, 100% 100%, 0% 100%);
opacity: 0.09;
/* Typography */
h1: clamp(2.4rem, 5.5vw, 5.2rem) — weight 900 — tracking -0.035em
h2: clamp(1.6rem, 3vw, 2.8rem) — weight 800 — tracking -0.025em
body: clamp(0.9rem, 1.5vw, 1.15rem) — weight 300 — muted white
kicker: clamp(0.55rem, 1vw, 0.75rem) — all-caps — letter-spacing 0.32em — orangeLive Demo
Deployed at: https://claude-deck.vercel.app
In this repository53 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- beautiful-htmlSkill
- boris-planSkill
- brandkitSkill
- industrial-brutalist-uiSkill
- business-caseSkill
- changelog-writerSkill
- competitor-researchSkill
- content-repurposerSkill
- customer-personaSkill
- deploy-checklistSkill
- dockerfile-generatorSkill
- email-writerSkill
- exec-summarySkill
- feature-prioritizerSkill
- frontend-slidesSkill
- gpt-tasteSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- karpathy-reviewSkill
- launch-checklistSkill
- linkedin-postSkill
- market-sizingSkill
- md-to-pdfSkill
- meeting-analyzerSkill
- minimalist-uiSkill
- newsletter-ideatorSkill
- okr-writerSkill
- full-output-enforcementSkill
- prd-generatorSkill
- proposal-writerSkill
- redesign-existing-projectsSkill
- retro-facilitatorSkill
- seo-optimizerSkill
- sharpenSkill
- skill-evaluatorSkill
- skill-to-sdkSkill
- slides-builderSkill
- high-end-visual-designSkill
- sprint-plannerSkill
- stakeholder-updateSkill
- stitch-design-tasteSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- test-writerSkill
- trend-spotterSkill
- ui-ux-pro-maxSkill
- user-story-writerSkill
- verify-workSkill
- voice-dnaSkill
- youtube-deepdiveSkill
- youtube-researcherSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

