CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Powerpoint Automation

aktsmm/agent-skills
1.5k installs17 stars
Summary

This is a full pipeline for turning web articles, blog posts, or existing PowerPoint files into polished slide decks. It uses an orchestrator-workers pattern with a content.json file as the single source of truth, keeping extraction, translation, generation, and review separate. It handles COM Automation for editing open PowerPoint files directly, includes validation scripts for overflow and consistency checks, and comes with detailed implementation patterns for things like shape-based architecture diagrams and hyperlink auditing. The workflow is structured around phases with human-in-the-loop checkpoints, and it enforces rules like verifying technical content with MCP and keeping operational notes out of slides. If you need to automate presentation creation from source material or manage existing decks programmatically, this gives you the scaffolding and guardrails to do it consistently.

Install to Claude Code

npx -y skills add aktsmm/agent-skills --skill powerpoint-automation --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

PowerPoint Automation

AI-powered PPTX generation using Orchestrator-Workers pattern.

When to Use

  • Web 記事やブログをスライド化したいとき
  • 既存 PPTX を翻訳・再構成したいとき
  • 開いている PPTX を COM Automation で直接編集したいとき
  • テンプレートベースで PPTX を生成したいとき
  • content.json を SSOT にして、抽出・翻訳・生成・レビューを分離したいとき

Quick Start

From Web Article

Create a 15-slide presentation from: https://zenn.dev/example/article

From Existing PPTX

Translate this presentation to Japanese: input/presentation.pptx

Edit Open PPTX with COM

Edit the currently open PowerPoint deck with COM Automation and verify RefURL, notes, overflow, and hyperlinks.

Workflow

TRIAGE → PLAN → PREPARE_TEMPLATE → EXTRACT → TRANSLATE → BUILD → REVIEW → DONE
PhaseMain ActorPurpose
EXTRACTextract_images.pySource -> content.json
BUILDcreate_from_template.pycontent.json -> PPTX
REVIEWPPTX ReviewerOverflow / consistency / quality

Core Assets

Scripts

ScriptPurpose
create_from_template.pycontent.json から PPTX を生成するメインスクリプト
reconstruct_analyzer.py既存 PPTX を content.json に戻す
extract_images.pyPPTX / Web から画像を抽出する
validate_content.pycontent.json のスキーマ検証
validate_pptx.pyoverflow などの検証

詳細は references/SCRIPTS.md を参照。

content.json

content.json はこの skill の SSOT。抽出、翻訳、生成、レビューの間は常にこれを基準にする。

{
  "slides": [
    { "type": "title", "title": "Title", "subtitle": "Sub" },
    { "type": "content", "title": "Topic", "items": ["Point 1"] }
  ]
}

スキーマ詳細は references/schemas/content.schema.json を参照。

Template

標準テンプレートは assets/template.pptx。レイアウトや用途の詳細は template 側で管理し、main SKILL には最小限だけ残す。

python scripts/create_from_template.py assets/template.pptx content.json output.pptx --config assets/template_layouts.json

Agents

AgentPurpose
OrchestratorPipeline coordination
LocalizerTranslation (EN <-> JA)
PPTX ReviewerFinal quality check

定義詳細は references/agents/ を参照。

Operating Rules

  • SSOT: content.json を正とする
  • One phase, one purpose: 抽出・翻訳・生成・レビューを混ぜない
  • Fail fast: 問題が出たら次フェーズへ無理に進めない
  • Human in loop: PLAN でユーザー確認を入れる
  • Technical content is verified content: Azure / Microsoft の内容は MCP で一次情報確認してから入れる
  • PowerPoint lock first: 開いている PPTX に対して python-pptx で上書きしない
  • COM for open decks: 開いている PPTX や既存 deck の直接編集は references/instructions/com-automation.instructions.md を参照する
  • Operational text stays in notes: 運営メモはスライド面に出さない
  • Customer-facing surface only: 顧客向け deck のスライド面には内部向け話法、避ける表現、作業メモ、検証メモ、ファイル用途ラベルを混ぜない。話者向け情報は speaker notes へ分離する
  • Template means template: ユーザー指定テンプレートがある場合、特に表紙はテンプレートの既存プレースホルダー/レイアウトを使い、上から別図形を重ねて隠さない
  • Rendered QA before handoff: COM で開いている deck を直接 touch-up した後も、対象 deck から実レンダー画像を書き出し、重なり・フォントばらつき・表の可読性を個別 slide で確認する
  • Review like a critic, not a generator: ユーザーに見せる前に、レンダー画像で「スカスカ・文字が小さい・アイコンが雑・テンプレ踏襲不足・旧文言残り」を自分で探して直す。詳しくは references/instructions/deck-iteration-review.instructions.md
  • Media restore gate: slide insertion/deletion/recovery after a user review must re-check expected slide count and embedded video/media positions before continuing
  • Architecture diagrams use shapes: ASCII art ではなく図形で組む
  • Appendix URLs use Title - URL: 参考 URL の表示形式は統一する
  • Review content and visuals separately: 生成後は見た目レビューだけでなく、公式情報との正確性レビュー、URL hyperlink 数、notes 数、placeholder/internal wording を確認する

Reference Map

Frequently Needed

  • references/SCRIPTS.md
  • references/USE_CASES.md
  • references/content-guidelines.md
  • references/IMPLEMENTATION_PATTERNS.md
  • references/instructions/com-automation.instructions.md
  • references/instructions/template.instructions.md
  • references/instructions/customer-facing-deck.instructions.md
  • references/instructions/deck-iteration-review.instructions.md

Go to Implementation Patterns For

  • technical content verification workflow
  • shape-based architecture diagrams
  • template-based slide XML editing order
  • COM SlideMaster / CustomLayouts edits for reusable templates
  • rendered-slide visual QA loop
  • PptxGenJS hardening pitfalls
  • hyperlink batch processing
  • customer-facing deck surface / notes separation
  • font theme token resolution
  • section / layout XML manipulation
  • hidden slide cleanup
  • COM Automation editing rules
  • RefURL placement and hyperlink auditing
  • file-lock workaround and post-processing
  • 16:9 centering issues
  • template corruption recovery
  • video embedding via ZIP direct manipulation

Done Criteria

  • source と goal が固定されている
  • content.json を正として各フェーズが分離されている
  • template / layout の前提が確認できている
  • technical content は一次情報確認が済んでいる
  • operational text がスライド面に出ていない
  • template 利用時は単調な同一レイアウト反復と余剰 placeholder を確認している
  • visual QA はレンダー画像で行い、修正後に該当スライドを再確認している
  • 表は本文 16pt 以上を原則とし、header は中央揃え・中段揃えで視認性を確認している
  • build 後に overflow / consistency / hyperlink をレビューできている
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
AI & Agent BuildingAutomation & WorkflowsOffice & Documents
View on GitHub

Recommended

More AI & Agent Building →
agent-memory-mcp

sickn33/antigravity-awesome-skills

agent memory mcp
954
39.4k
agent-memory-mcp

davila7/claude-code-templates

agent memory mcp
521
27.7k
llm-application-dev-langchain-agent

sickn33/antigravity-awesome-skills

llm application dev langchain agent
306
39.4k
llm-application-dev

moizibnyousaf/ai-agent-skills

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
1.1k
ai-prompt-engineering-safety-review

github/awesome-copilot

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.
9.4k
34.3k
emblem-ai-prompt-examples

emblemcompany/agent-skills

emblem ai prompt examples
8.7k
10