automating-keynote

5 stars 1 forks
96
A

Automates Apple Keynote using JXA with AppleScript dictionary discovery. Use when asked to "create Keynote presentations", "automate slide decks", "JXA Keynote scripting", or "generate presentations programmatically". Covers document lifecycle, slides, text, shapes, images, tables, charts, transitions, and UI scripting fallback.

Marketplace
#excel#notes#console.log#claude-code-plugins#numbers#mac-automation#keynote.documents#doc.masterSlides

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install SpillwaveSolutions/automating-mac-apps-plugin/automating-keynote
skilz install SpillwaveSolutions/automating-mac-apps-plugin/automating-keynote --agent opencode
skilz install SpillwaveSolutions/automating-mac-apps-plugin/automating-keynote --agent codex
skilz install SpillwaveSolutions/automating-mac-apps-plugin/automating-keynote --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/SpillwaveSolutions/automating-mac-apps-plugin
2. Copy the agent skill directory:
cp -r automating-mac-apps-plugin/plugins/automating-mac-apps-plugin/skills/automating-keynote ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Stars
5
Forks
1
Type
Other
Meta-Domain
Primary Domain
Market Score
96

Agent Skill Grade

A
Score: 96/100 Click to see breakdown

Score Breakdown

Spec Compliance
14/15
PDA Architecture
26/30
Ease of Use
21/25
Writing Style
8/10
Utility
17/20
Modifiers: +10

Areas to Improve

  • Redundant Quick Examples
  • Missing TOC in mid-size references
  • PyXA API reference verbosity

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your automating-keynote skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 96/100, A-grade territory – this is solid production-ready work. This is based on Anthropic's skill best practices rubric. Your strongest area is Spec Compliance (14/15), and you're also crushing it on Progressive Disclosure Architecture (26/30). The areas with room to grow are Writing Style (8/10) and Utility (17/20) – but honestly, we're talking small refinements here.

What's Working Well

  • Clear scope boundaries – Your "When Not to Use" section actually helps people understand what this skill isn't for. That's rare and valuable.
  • Smart two-path approach – Offering both JXA and PyXA gives people real flexibility depending on their constraints. The fallback to GUI scripting for chart creation shows you've thought through edge cases.
  • Well-organized reference architecture – 7 focused reference files (basics, deck-generator, recipes, advanced, etc.) is textbook Progressive Disclosure. Each file sits exactly one level deep from SKILL.md – no nested rabbit holes.
  • Practical examples with templates – Your deck generator and batch processing examples aren't theoretical – they're actually useful patterns someone could copy-paste and adapt.

The Big One

Your Quick Examples section in SKILL.md is duplicating content that's already fully explained in keynote-basics.md and keynote-recipes.md. Lines 39-72 walk through "create slide, add image" patterns that are rehashed later. Here's why this matters: it's wasting token budget in your main entry point and making the skill feel bloated on firs...

AI-Detected Topics

Extracted using NLP analysis

excel notes console.log claude-code-plugins numbers mac-automation keynote.documents doc.masterSlides chrome claude-code-plugins-marketplace

Report Security Issue

Found a security vulnerability in this agent skill?