myaiforone 1.0.0

package/registry/skills/platform/sop_mcpbuilder.md

@@ -0,0 +1,133 @@
+---
+name: sop_mcpbuilder
+description: Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers for any API or service integration.
+---
+
+# MCP Server Development Guide
+
+Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
+
+## High-Level Workflow
+
+Creating a high-quality MCP server involves four main phases:
+
+### Phase 1: Deep Research and Planning
+
+#### 1.1 Understand Modern MCP Design
+
+**API Coverage vs. Workflow Tools:**
+Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. When uncertain, prioritize comprehensive API coverage.
+
+**Tool Naming and Discoverability:**
+Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming.
+
+**Context Management:**
+Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data.
+
+**Actionable Error Messages:**
+Error messages should guide agents toward solutions with specific suggestions and next steps.
+
+#### 1.2 Study MCP Protocol Documentation
+
+**Navigate the MCP specification:**
+Start with the sitemap: `https://modelcontextprotocol.io/sitemap.xml`
+Then fetch specific pages with `.md` suffix for markdown format.
+
+Key pages to review:
+- Specification overview and architecture
+- Transport mechanisms (streamable HTTP, stdio)
+- Tool, resource, and prompt definitions
+
+#### 1.3 Study Framework Documentation
+
+**Recommended stack:**
+- **Language**: TypeScript (high-quality SDK support)
+- **Transport**: Streamable HTTP for remote servers, stdio for local servers
+
+**SDK Documentation:**
+- **TypeScript SDK**: `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
+- **Python SDK**: `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
+
+#### 1.4 Plan Your Implementation
+
+**Understand the API:**
+Review the service's API documentation to identify key endpoints, authentication requirements, and data models.
+
+**Tool Selection:**
+Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.
+
+### Phase 2: Implementation
+
+#### 2.1 Set Up Project Structure
+
+Create shared utilities:
+- API client with authentication
+- Error handling helpers
+- Response formatting (JSON/Markdown)
+- Pagination support
+
+#### 2.2 Implement Tools
+
+For each tool:
+
+**Input Schema:**
+- Use Zod (TypeScript) or Pydantic (Python)
+- Include constraints and clear descriptions
+- Add examples in field descriptions
+
+**Output Schema:**
+- Define `outputSchema` where possible for structured data
+- Use `structuredContent` in tool responses
+
+**Tool Description:**
+- Concise summary of functionality
+- Parameter descriptions
+- Return type schema
+
+**Implementation:**
+- Async/await for I/O operations
+- Proper error handling with actionable messages
+- Support pagination where applicable
+
+**Annotations:**
+- `readOnlyHint`: true/false
+- `destructiveHint`: true/false
+- `idempotentHint`: true/false
+- `openWorldHint`: true/false
+
+### Phase 3: Review and Test
+
+#### 3.1 Code Quality
+
+Review for:
+- No duplicated code (DRY principle)
+- Consistent error handling
+- Full type coverage
+- Clear tool descriptions
+
+#### 3.2 Build and Test
+
+**TypeScript:**
+- Run `npm run build` to verify compilation
+- Test with MCP Inspector: `npx @modelcontextprotocol/inspector`
+
+**Python:**
+- Verify syntax: `python -m py_compile your_server.py`
+- Test with MCP Inspector
+
+### Phase 4: Create Evaluations
+
+Create comprehensive evaluations to test effectiveness:
+
+1. **Tool Inspection**: List available tools and understand their capabilities
+2. **Content Exploration**: Use READ-ONLY operations to explore available data
+3. **Question Generation**: Create 10 complex, realistic questions
+4. **Answer Verification**: Solve each question yourself to verify answers
+
+Ensure each question is:
+- **Independent**: Not dependent on other questions
+- **Read-only**: Only non-destructive operations required
+- **Complex**: Requiring multiple tool calls
+- **Realistic**: Based on real use cases
+- **Verifiable**: Single, clear answer
+- **Stable**: Answer won't change over time

package/registry/skills/platform/sop_pdf.md

@@ -0,0 +1,172 @@
+---
+name: sop_pdf
+description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Use when processing, generating, or analyzing PDF documents.
+---
+
+# PDF Processing Guide
+
+## Quick Start
+
+```python
+from pypdf import PdfReader, PdfWriter
+
+# Read a PDF
+reader = PdfReader("document.pdf")
+print(f"Pages: {len(reader.pages)}")
+
+# Extract text
+text = ""
+for page in reader.pages:
+    text += page.extract_text()
+```
+
+## Python Libraries
+
+### pypdf - Basic Operations
+
+#### Merge PDFs
+```python
+from pypdf import PdfWriter, PdfReader
+
+writer = PdfWriter()
+for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
+    reader = PdfReader(pdf_file)
+    for page in reader.pages:
+        writer.add_page(page)
+
+with open("merged.pdf", "wb") as output:
+    writer.write(output)
+```
+
+#### Split PDF
+```python
+reader = PdfReader("input.pdf")
+for i, page in enumerate(reader.pages):
+    writer = PdfWriter()
+    writer.add_page(page)
+    with open(f"page_{i+1}.pdf", "wb") as output:
+        writer.write(output)
+```
+
+#### Extract Metadata
+```python
+reader = PdfReader("document.pdf")
+meta = reader.metadata
+print(f"Title: {meta.title}")
+print(f"Author: {meta.author}")
+```
+
+#### Rotate Pages
+```python
+reader = PdfReader("input.pdf")
+writer = PdfWriter()
+page = reader.pages[0]
+page.rotate(90)  # 90 degrees clockwise
+writer.add_page(page)
+with open("rotated.pdf", "wb") as output:
+    writer.write(output)
+```
+
+### pdfplumber - Text and Table Extraction
+
+#### Extract Text with Layout
+```python
+import pdfplumber
+
+with pdfplumber.open("document.pdf") as pdf:
+    for page in pdf.pages:
+        text = page.extract_text()
+        print(text)
+```
+
+#### Extract Tables
+```python
+import pandas as pd
+
+with pdfplumber.open("document.pdf") as pdf:
+    all_tables = []
+    for page in pdf.pages:
+        tables = page.extract_tables()
+        for table in tables:
+            if table:
+                df = pd.DataFrame(table[1:], columns=table[0])
+                all_tables.append(df)
+
+if all_tables:
+    combined_df = pd.concat(all_tables, ignore_index=True)
+    combined_df.to_excel("extracted_tables.xlsx", index=False)
+```
+
+### reportlab - Create PDFs
+
+```python
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+
+c = canvas.Canvas("hello.pdf", pagesize=letter)
+width, height = letter
+c.drawString(100, height - 100, "Hello World!")
+c.save()
+```
+
+## Command-Line Tools
+
+### pdftotext (poppler-utils)
+```bash
+pdftotext input.pdf output.txt           # Extract text
+pdftotext -layout input.pdf output.txt   # Preserve layout
+pdftotext -f 1 -l 5 input.pdf output.txt # Pages 1-5
+```
+
+### qpdf
+```bash
+qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf  # Merge
+qpdf input.pdf --pages . 1-5 -- pages1-5.pdf            # Split
+qpdf input.pdf output.pdf --rotate=+90:1                # Rotate page 1
+qpdf --password=pwd --decrypt encrypted.pdf decrypted.pdf
+```
+
+## Common Tasks
+
+### OCR Scanned PDFs
+```python
+import pytesseract
+from pdf2image import convert_from_path
+
+images = convert_from_path('scanned.pdf')
+text = ""
+for i, image in enumerate(images):
+    text += pytesseract.image_to_string(image)
+```
+
+### Add Watermark
+```python
+watermark = PdfReader("watermark.pdf").pages[0]
+reader = PdfReader("document.pdf")
+writer = PdfWriter()
+
+for page in reader.pages:
+    page.merge_page(watermark)
+    writer.add_page(page)
+
+with open("watermarked.pdf", "wb") as output:
+    writer.write(output)
+```
+
+### Password Protection
+```python
+writer.encrypt("userpassword", "ownerpassword")
+with open("encrypted.pdf", "wb") as output:
+    writer.write(output)
+```
+
+## Quick Reference
+
+| Task | Best Tool | Method |
+|------|-----------|--------|
+| Merge PDFs | pypdf | `writer.add_page(page)` |
+| Split PDFs | pypdf | One page per file |
+| Extract text | pdfplumber | `page.extract_text()` |
+| Extract tables | pdfplumber | `page.extract_tables()` |
+| Create PDFs | reportlab | Canvas or Platypus |
+| OCR scanned | pytesseract | Convert to image first |

package/registry/skills/platform/sop_pptx.md

@@ -0,0 +1,133 @@
+---
+name: sop_pptx
+description: PowerPoint creation, editing, and analysis toolkit. Use for creating presentations, modifying existing slides, extracting content, and working with templates.
+---
+
+# PPTX Processing Guide
+
+## Reading and Analyzing Content
+
+### Text Extraction
+```bash
+python -m markitdown presentation.pptx
+```
+
+### Raw XML Access
+For comments, speaker notes, layouts, animations:
+
+```bash
+python ooxml/scripts/unpack.py presentation.pptx output_dir/
+```
+
+Key file structures:
+- `ppt/presentation.xml` - Main metadata
+- `ppt/slides/slide{N}.xml` - Individual slides
+- `ppt/notesSlides/notesSlide{N}.xml` - Speaker notes
+- `ppt/slideMasters/` - Master templates
+- `ppt/theme/` - Theme and styling
+
+## Creating Presentations (html2pptx)
+
+### Design Principles
+
+**CRITICAL**: Before creating, analyze content and choose appropriate design:
+1. Consider subject matter - tone, industry, mood
+2. Check for branding requirements
+3. Match palette to content
+4. State your approach before writing code
+
+**Requirements**:
+- Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact
+- Create clear visual hierarchy
+- Ensure readability with strong contrast
+- Be consistent across slides
+
+### Color Palette Examples
+
+1. **Classic Blue**: Navy #1C2833, Slate #2E4053, Silver #AAB7B8
+2. **Teal & Coral**: Teal #5EA8A7, Coral #FE4447
+3. **Warm Blush**: Mauve #A49393, Blush #EED6D3, Rose #E8B4B8
+4. **Black & Gold**: Gold #BF9A4A, Black #000000
+5. **Forest Green**: Green #4E9F3D, Dark Green #1E5128
+
+### Workflow
+
+1. Read `html2pptx.md` completely
+2. Create HTML file for each slide (720pt x 405pt for 16:9)
+3. Run JavaScript with html2pptx.js library
+4. Validate with thumbnails:
+   ```bash
+   python scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4
+   ```
+
+## Editing Existing Presentations (OOXML)
+
+### Workflow
+
+1. Read `ooxml.md` completely
+2. Unpack: `python ooxml/scripts/unpack.py presentation.pptx output_dir/`
+3. Edit XML files
+4. Validate: `python ooxml/scripts/validate.py output_dir/ --original presentation.pptx`
+5. Pack: `python ooxml/scripts/pack.py output_dir/ edited.pptx`
+
+## Using Templates
+
+### Workflow
+
+1. **Extract and visualize**:
+   ```bash
+   python -m markitdown template.pptx > template-content.md
+   python scripts/thumbnail.py template.pptx
+   ```
+
+2. **Create template inventory** - document all slides with indices
+
+3. **Plan outline** - map content to template slides
+
+4. **Rearrange slides**:
+   ```bash
+   python scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52
+   ```
+
+5. **Extract text inventory**:
+   ```bash
+   python scripts/inventory.py working.pptx text-inventory.json
+   ```
+
+6. **Create replacement JSON** with new content
+
+7. **Apply replacements**:
+   ```bash
+   python scripts/replace.py working.pptx replacement-text.json output.pptx
+   ```
+
+## Creating Thumbnails
+
+```bash
+python scripts/thumbnail.py presentation.pptx [output_prefix]
+```
+
+Options:
+- `--cols 4` - Adjust columns (3-6)
+- Custom prefix for output naming
+
+## Converting to Images
+
+```bash
+# PPTX to PDF
+soffice --headless --convert-to pdf presentation.pptx
+
+# PDF to JPEG
+pdftoppm -jpeg -r 150 presentation.pdf slide
+```
+
+## Quick Reference
+
+| Task | Tool | Command |
+|------|------|---------|
+| Extract text | markitdown | `python -m markitdown file.pptx` |
+| Create new | html2pptx | HTML -> JS -> PPTX |
+| Edit existing | OOXML | Unpack, edit XML, repack |
+| Use template | rearrange.py | Duplicate/reorder slides |
+| Thumbnails | thumbnail.py | Visual grid of all slides |
+| To images | LibreOffice | PPTX -> PDF -> JPEG |

package/registry/skills/platform/sop_skillcreator.md

@@ -0,0 +1,104 @@
+---
+name: sop_skillcreator
+description: Guide for building modular skill packages that extend Claude's capabilities through specialized knowledge, workflows, and tool integrations. Use when creating new custom skills.
+---
+
+# Skill Creator Guide
+
+Build modular packages that extend Claude's capabilities through specialized knowledge, workflows, and tool integrations.
+
+## Key Principles
+
+**Concise Design**: The context window is a public good. Only include information Claude doesn't already possess, challenging each piece's necessity.
+
+**Appropriate Freedom Levels**: Match specificity to task fragility:
+- High freedom for flexible approaches
+- Low freedom for fragile operations requiring exact sequences
+
+**Progressive Disclosure**: Load content in three levels:
+1. Metadata (always loaded)
+2. SKILL.md body (on trigger)
+3. Bundled resources (as needed)
+
+## Skill Structure
+
+Every skill requires:
+
+### SKILL.md
+```markdown
+---
+name: my-skill
+description: "Description that triggers skill selection - detail functionality AND usage contexts"
+---
+
+# Skill Instructions
+
+Your instructions here...
+```
+
+### Optional Bundled Resources
+
+```
+my-skill/
+├── SKILL.md           # Required - main instructions
+├── scripts/           # Executable code for deterministic tasks
+├── references/        # Documentation loaded as needed
+└── assets/            # Output files like templates or icons
+```
+
+## Creation Process
+
+1. **Understand** - Gather concrete usage examples
+2. **Plan** - Identify reusable contents (scripts, references, assets)
+3. **Initialize** - Use `init_skill.py` to scaffold
+4. **Edit** - Write SKILL.md and create resources
+5. **Package** - Use `package_skill.py` (validates before creating .skill file)
+6. **Iterate** - Refine based on real usage feedback
+
+## Best Practices
+
+### Description Field
+The description is critical - it triggers skill selection. Include:
+- What the skill does
+- When to use it (specific contexts)
+- Example use cases
+
+### SKILL.md Content
+- Keep under 500 lines
+- Split complex content into reference files
+- Organize references one level deep from SKILL.md
+- Use clear section headers
+
+### Scripts
+- Make deterministic tasks executable
+- Include error handling
+- Document inputs/outputs
+
+### References
+- Load only when needed
+- Keep focused on single topics
+- Cross-reference sparingly
+
+## Example Skill Structure
+
+```
+code-review/
+├── SKILL.md
+│   ---
+│   name: code-review
+│   description: Review code for bugs, security issues, and best practices.
+│                Use when asked to review PRs, audit code, or check for issues.
+│   ---
+│   # Code Review Skill
+│   ...instructions...
+│
+├── scripts/
+│   └── analyze.py      # Static analysis helper
+│
+├── references/
+│   ├── security.md     # Security checklist
+│   └── patterns.md     # Common anti-patterns
+│
+└── assets/
+    └── report-template.md
+```

package/registry/skills/platform/sop_themefactory.md

@@ -0,0 +1,128 @@
+---
+name: sop_themefactory
+description: Toolkit for styling artifacts with professional themes. Apply curated color palettes and font pairings to slides, docs, reports, HTML pages, and more. 10 pre-set themes or generate custom themes.
+---
+
+# Theme Factory
+
+Apply consistent, professional styling to presentation slide decks and other artifacts with curated themes.
+
+## Usage Instructions
+
+1. **Show theme showcase**: Display `theme-showcase.pdf` for visual reference
+2. **Ask for choice**: Let user select a theme
+3. **Wait for selection**: Get explicit confirmation
+4. **Apply theme**: Apply selected colors and fonts
+
+## Available Themes
+
+### 1. Ocean Depths
+Professional, calming maritime theme
+- Deep blues and teals
+- Clean, corporate feel
+
+### 2. Sunset Boulevard
+Warm and vibrant sunset colors
+- Oranges, pinks, purples
+- Energetic, creative mood
+
+### 3. Forest Canopy
+Natural and grounded earth tones
+- Greens and browns
+- Organic, sustainable feel
+
+### 4. Modern Minimalist
+Clean and contemporary grayscale
+- Black, white, grays
+- Professional, sleek
+
+### 5. Golden Hour
+Rich and warm autumnal palette
+- Golds, ambers, deep reds
+- Luxurious, sophisticated
+
+### 6. Arctic Frost
+Cool and crisp winter-inspired
+- Icy blues and whites
+- Fresh, clean aesthetic
+
+### 7. Desert Rose
+Soft and sophisticated dusty tones
+- Muted pinks, tans, terracotta
+- Elegant, refined
+
+### 8. Tech Innovation
+Bold and modern tech aesthetic
+- Electric blues, neon accents
+- Cutting-edge, dynamic
+
+### 9. Botanical Garden
+Fresh and organic garden colors
+- Leafy greens, floral accents
+- Natural, lively
+
+### 10. Midnight Galaxy
+Dramatic and cosmic deep tones
+- Deep purples, blues, starlight accents
+- Bold, mysterious
+
+## Theme Structure
+
+Each theme includes:
+- **Color palette**: Cohesive hex codes
+- **Font pairings**: Header and body fonts
+- **Visual identity**: Specific character/mood
+
+## Application Process
+
+After theme selection:
+1. Read theme file from `themes/` directory
+2. Apply colors consistently throughout
+3. Apply font pairings to headers and body
+4. Ensure proper contrast and readability
+5. Maintain visual identity across all elements
+
+## Custom Themes
+
+When no existing theme fits:
+
+1. Gather requirements (brand colors, mood, industry)
+2. Generate custom palette with 4-6 colors
+3. Select complementary font pairing
+4. Name theme descriptively
+5. Show for review before applying
+
+### Custom Theme Template
+
+```yaml
+name: "Theme Name"
+description: "What the theme represents"
+
+colors:
+  primary: "#XXXXXX"
+  secondary: "#XXXXXX"
+  accent: "#XXXXXX"
+  background: "#XXXXXX"
+  text: "#XXXXXX"
+
+fonts:
+  heading: "Font Name"
+  body: "Font Name"
+
+mood: "Professional | Creative | Playful | Elegant | Bold"
+```
+
+## Quick Reference
+
+| Theme | Mood | Best For |
+|-------|------|----------|
+| Ocean Depths | Professional | Corporate, finance |
+| Sunset Boulevard | Energetic | Creative, marketing |
+| Forest Canopy | Natural | Sustainability, wellness |
+| Modern Minimalist | Sleek | Tech, startups |
+| Golden Hour | Luxurious | Premium brands |
+| Arctic Frost | Fresh | Healthcare, clean tech |
+| Desert Rose | Elegant | Fashion, lifestyle |
+| Tech Innovation | Dynamic | Technology, innovation |
+| Botanical Garden | Lively | Food, nature, organic |
+| Midnight Galaxy | Bold | Entertainment, gaming |