creating-presentations
Processes PowerPoint presentation files (.pptx). Creates slides, rewrites templates, converts HTML to presentations, validates thumbnails, swaps layouts, and performs deep OOXML editing. Use when working with presentation files or slide decks. Do NOT use for Word documents, spreadsheets, or PDF files.
git clone --depth 1 https://github.com/telagod/code-abyss /tmp/creating-presentations && cp -r /tmp/creating-presentations/skills/creating-presentations ~/.claude/skills/creating-presentationsSKILL.md
# PPTX Processing
`.pptx` is a ZIP archive of XML and resources. Choose workflow by intent.
## Workflow Decision
| Intent | Workflow | Reference |
|--------|----------|-----------|
| **Read text** | markitdown → markdown | [thumbnails-and-conversion.md](references/thumbnails-and-conversion.md) |
| **Analyze layout / comments / theme** | unpack → raw XML | [thumbnails-and-conversion.md](references/thumbnails-and-conversion.md) |
| **Create new from scratch** | html2pptx | [html2pptx.md](html2pptx.md) + [design-patterns.md](references/design-patterns.md) |
| **Create using template** | rearrange + inventory + replace | [template-workflow.md](references/template-workflow.md) |
| **Edit existing slides** | unpack → OOXML → pack | [ooxml.md](ooxml.md) |
| **Visual review** | thumbnail grids | [thumbnails-and-conversion.md](references/thumbnails-and-conversion.md) |
## Iron Rules
- **Color choice is design** — see [palettes.md](references/palettes.md), state your approach BEFORE code.
- **Web-safe fonts only** — Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact.
- **Layout matches content count** — 2 items → 2 columns; 3 → 3; never force.
- **Validate visually** — always generate thumbnails after creation, inspect for cutoff/overlap/contrast.
## Create New (without template) — html2pptx
1. **MANDATORY — READ ENTIRE FILE**: `html2pptx.md`. NEVER set range limits.
2. Create HTML per slide (e.g., 720pt × 405pt for 16:9)
- Use `<p>`, `<h1>`–`<h6>`, `<ul>`, `<ol>`
- `class="placeholder"` for chart/table areas (gray bg for visibility)
- **CRITICAL**: Rasterize gradients & icons as PNG via Sharp first, then reference in HTML
- Use full-slide or two-column layout for charts/tables — never vertical stack
3. Run `scripts/html2pptx.js` to convert
- `html2pptx()` per HTML file
- Charts/tables via PptxGenJS API on placeholders
- `pptx.writeFile()` to save
4. **Visual validation** — `python scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4`
- Inspect for: text cutoff, overlap, positioning, contrast
- Adjust HTML margins/spacing/colors, regenerate, repeat
## Create with Template
See [template-workflow.md](references/template-workflow.md) for full 7-step workflow (extract → inventory → outline → rearrange → inventory text → generate replacements → apply).
## Edit Existing Presentation
1. **MANDATORY — READ ENTIRE FILE**: `ooxml.md` (~500 lines). NEVER set range limits.
2. `python ooxml/scripts/unpack.py <file> <dir>`
3. Edit XML (primarily `ppt/slides/slide{N}.xml`)
4. **CRITICAL** — validate after each edit: `python ooxml/scripts/validate.py <dir> --original <file>`
5. `python ooxml/scripts/pack.py <dir> <file>`
## Code Style
Concise code, no verbose names, no unnecessary print statements.
## Dependencies
| Package | Install | Purpose |
|---------|---------|---------|
| markitdown | `pip install "markitdown[pptx]"` | Text extraction |
| pptxgenjs | `npm i -g pptxgenjs` | Create via html2pptx |
| playwright | `npm i -g playwright` | HTML rendering |
| react-icons | `npm i -g react-icons react react-dom` | Icons |
| sharp | `npm i -g sharp` | SVG rasterization |
| LibreOffice | `apt install libreoffice` | PDF conversion |
| Poppler | `apt install poppler-utils` | `pdftoppm` |
| defusedxml | `pip install defusedxml` | Secure XML |Analyzes code changes, detects documentation drift, and evaluates change impact scope. Use when reviewing diffs, checking doc sync, or running pre-commit analysis. Automatically triggered after design-level changes or refactoring.
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
Processes Excel spreadsheet files (.xlsx, .xlsm, .csv). Creates workbooks, builds formulas, preserves formatting, analyzes tabular data, and validates financial models with zero-formula-error delivery. Use when working with spreadsheet files or tabular data analysis. Do NOT use for Word documents, PDFs, presentations, or database pipelines.
Frontend UI design system selector and implementation guide covering Glassmorphism, Liquid Glass (Apple-style), Neubrutalism, and Claymorphism. Use when building UI components, choosing a visual aesthetic, implementing design tokens, or auditing accessibility/contrast on themed surfaces. Provides per-style tokens, component patterns, dark mode, and a11y constraints.
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
DevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml, multi-arch images, cosign integration), CI/CD pipelines, database management, observability, and performance optimization. Use when working with Git, CI/CD, release pipelines, ghcr image publishing, testing, monitoring, or infrastructure automation.
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge). Use when building AI agents, designing RAG pipelines, orchestrating multi-agent workflows, hardening LLM apps, or writing prompts.
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.