Skills for Real Engineers. Straight from my .agents directory.
huashu-slides
Agent skill fromalchaincyf/huashu-skills
从内容到成品PPTX的端到端演示文稿制作,含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
How to install huashu-slides
npx skills add alchaincyf/huashu-skills# or add only this skill to Claude Code: copy the folder
huashu-slides/
# into
~/.claude/skills/huashu-slides/ (all projects)
.claude/skills/huashu-slides/ (one project)
1# AI Presentation Workflow23Create professional presentations: Content → Design → Build → Assembly → Polish.45## Step 0: Choose Workflow Settings67**At the start of every presentation task, ask the user TWO choices:**89### 0-A. Collaboration Mode1011| Mode | Description | Checkpoints |12|------|-------------|-------------|13| **Full Auto** | Minimal interaction. Confirm topic only, deliver final PPTX. | 1 checkpoint |14| **Guided** (recommended) | Confirm outline, pick design, preview before assembly. | 3 checkpoints |15| **Collaborative** | Review every slide, approve every illustration, full control. | Per-slide |1617If the user doesn't specify, default to **Guided** mode.1819### 0-B. Assembly Method2021| Method | How it works | Best for |22|--------|-------------|----------|23| **Editable HTML** (Path A) | HTML slides + selective AI illustrations → html2pptx → editable PPTX | Need to edit text later, precise layout, corporate decks |24| **Full AI Visual** (Path B) | Every slide as a complete AI-generated image → create_slides.py → image PPTX | Maximum visual impact, artistic presentations, quick drafts |2526**Trade-offs:**2728| | Path A: Editable HTML | Path B: Full AI Visual |29|---|---|---|30| Text | Editable in PPT | Baked into image (not editable) |31| Visual quality | Good with illustrations | Excellent — cohesive design |32| Layout control | Pixel-precise | AI-interpreted |33| File size | Smaller (~5-25MB) | Larger (~30-80MB) |34…
Excerpt shown under the repository's MIT license.
More skills in huashu-skills
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
