Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/thatrebeccarae/claude-marketingnpx agentmods add skills/thatrebeccarae/claude-marketing/pro-deck-builderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thatrebeccarae/claude-marketing/pro-deck-builder)<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/pro-deck-builder"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/pro-deck-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/pro-deck-builder"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/pro-deck-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.07167 |
| Opus 5 | $0.00037 | $0.03583 |
| Sonnet 5 | $0.00015 | $0.01433 |
| Haiku 4.5 | $0.00007 | $0.00717 |
Grade A, and why
pro-deck-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Designer
VC-backed SaaS design quality for PowerPoint. Think Linear, Attio, Vercel, Raycast — not corporate clip art.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/pro-deck-builder ~/.claude/skills/
Quick Reference
| Task | Approach |
|---|---|
| Create from scratch | Read REFERENCE.md, use PptxGenJS |
| Edit existing / use template | Read editing.md |
| Read/extract content | python -m markitdown presentation.pptx |
| Visual overview | python scripts/thumbnail.py presentation.pptx |
Before You Start (Required Steps)
Step 1: Ask the User
Before writing any code, ask:
- Light or dark mode? Dark = premium/keynote feel. Light = reports/data-heavy decks.
- Palette preference? Show the palette table below, or ask if they have brand colors.
- Logo? Ask if they have a logo file to include (PNG/SVG path).
Step 2: Discover Fonts
Check what's installed — premium fonts make a massive difference:
# macOS — list all installed font families
fc-list : family | sort -u
# Search for premium fonts first
fc-list : family | grep -iE "inter|dm.sans|poppins|avenir|futura|geist|sf.pro|sf.mono|jetbrains|fira.code|montserrat|playfair|source.sans"
# Check macOS Font Book directories directly
ls ~/Library/Fonts/ /Library/Fonts/ /System/Library/Fonts/Supplemental/ 2>/dev/null
Priority order for font selection:
- Inter — the gold standard for SaaS UI (if installed, use it for everything)
- DM Sans — geometric, startup-friendly
- Poppins — rounded, approachable
- Avenir / Avenir Next — ships with macOS, Apple-adjacent elegance
- Calibri — safe fallback, always available
For data/mono: JetBrains Mono > Fira Code > SF Mono > Consolas
Design Language: VC-Backed SaaS
Aesthetic Principles
- Depth through layering — Surfaces float above backgrounds. Cards and panels have subtle elevation via shadows and fine borders, not flat colored boxes.
- Bold typography, minimal decoration — Let type hierarchy do the work. No accent lines, no decorative shapes, no clip art.
- Restrained color — One accent color used sparingly (10%). Mostly neutrals. Color = signal, not decoration.
- Generous whitespace — Empty space signals confidence. If a slide feels sparse, make the content bigger, don't add more.
- Every element earns its place — Before adding anything: what does it communicate? If removing it changes nothing, remove it.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 558 lines · 75 tokens per session scan A ba28ec4faccf
pro-deck-builder is a skill published in the GitHub repository thatrebeccarae/claude-marketing (136 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 7,167 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
yt-dlp-downloader
Generate and run yt-dlp download commands with probe-driven format selection, safe output naming, retry defaults, and structured execution reports. Use when users want to download videos, extract audio, fetch playlists, grab subtitles, handle authenticated/age-gated content, or download live streams. Covers single…
presentation-builder
Création de présentations percutantes avec structure, storytelling, visuels et delivery. Se déclenche avec "présentation", "slides", "PowerPoint", "Keynote", "présenter", "pitch deck". Also triggers on "build a presentation", "slide deck structure", "present my project".
music-composer
Komponiert video-synchronisierte Hintergrundmusik aus einem Storyline-JSON per lokaler Waveform-Synthese (numpy + ffmpeg). Stile: Chiptune, Ambient, Electronic. Deterministisch, offline, kein Cloud-Dienst.
video-transcriber
Fetch video transcripts (subtitles) and metadata from online video sources and output them as Markdown, JSON, or plain text. Currently supported: YouTube. Prefers manually created subtitles, falls back to auto-generated ones.
transkription
Transcribes audio/video files to text. Uses Whisper (openai-whisper) or Vosk (offline) as optional backend — both are detected via presence check. Without backend: placeholder mode with dummy output (dry-run).
brainstorm
Structured creativity methods for idea generation: SCAMPER, Six Thinking Hats, Mind Mapping, Reverse Brainstorming, TRIZ, and Rapid Ideation.