daemora 1.0.0-alpha.0

package/skills/lead-research-assistant.md

@@ -0,0 +1,199 @@
+---
+name: lead-research-assistant
+description: Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
+---
+
+# Lead Research Assistant
+
+This skill helps you identify and qualify potential leads for your business by analyzing your product/service, understanding your ideal customer profile, and providing actionable outreach strategies.
+
+## When to Use This Skill
+
+- Finding potential customers or clients for your product/service
+- Building a list of companies to reach out to for partnerships
+- Identifying target accounts for sales outreach
+- Researching companies that match your ideal customer profile
+- Preparing for business development activities
+
+## What This Skill Does
+
+1. **Understands Your Business**: Analyzes your product/service, value proposition, and target market
+2. **Identifies Target Companies**: Finds companies that match your ideal customer profile based on:
+   - Industry and sector
+   - Company size and location
+   - Technology stack and tools they use
+   - Growth stage and funding
+   - Pain points your product solves
+3. **Prioritizes Leads**: Ranks companies based on fit score and relevance
+4. **Provides Contact Strategies**: Suggests how to approach each lead with personalized messaging
+5. **Enriches Data**: Gathers relevant information about decision-makers and company context
+
+## How to Use
+
+### Basic Usage
+
+Simply describe your product/service and what you're looking for:
+
+```
+I'm building [product description]. Find me 10 companies in [location/industry] 
+that would be good leads for this.
+```
+
+### With Your Codebase
+
+For even better results, run this from your product's source code directory:
+
+```
+Look at what I'm building in this repository and identify the top 10 companies 
+in [location/industry] that would benefit from this product.
+```
+
+### Advanced Usage
+
+For more targeted research:
+
+```
+My product: [description]
+Ideal customer profile:
+- Industry: [industry]
+- Company size: [size range]
+- Location: [location]
+- Current pain points: [pain points]
+- Technologies they use: [tech stack]
+
+Find me 20 qualified leads with contact strategies for each.
+```
+
+## Instructions
+
+When a user requests lead research:
+
+1. **Understand the Product/Service**
+   - If in a code directory, analyze the codebase to understand the product
+   - Ask clarifying questions about the value proposition
+   - Identify key features and benefits
+   - Understand what problems it solves
+
+2. **Define Ideal Customer Profile**
+   - Determine target industries and sectors
+   - Identify company size ranges
+   - Consider geographic preferences
+   - Understand relevant pain points
+   - Note any technology requirements
+
+3. **Research and Identify Leads**
+   - Search for companies matching the criteria
+   - Look for signals of need (job postings, tech stack, recent news)
+   - Consider growth indicators (funding, expansion, hiring)
+   - Identify companies with complementary products/services
+   - Check for budget indicators
+
+4. **Prioritize and Score**
+   - Create a fit score (1-10) for each lead
+   - Consider factors like:
+     - Alignment with ICP
+     - Signals of immediate need
+     - Budget availability
+     - Competitive landscape
+     - Timing indicators
+
+5. **Provide Actionable Output**
+   
+   For each lead, provide:
+   - **Company Name** and website
+   - **Why They're a Good Fit**: Specific reasons based on their business
+   - **Priority Score**: 1-10 with explanation
+   - **Decision Maker**: Role/title to target (e.g., "VP of Engineering")
+   - **Contact Strategy**: Personalized approach suggestions
+   - **Value Proposition**: How your product solves their specific problem
+   - **Conversation Starters**: Specific points to mention in outreach
+   - **LinkedIn URL**: If available, for easy connection
+
+6. **Format the Output**
+
+   Present results in a clear, scannable format:
+
+   ```markdown
+   # Lead Research Results
+   
+   ## Summary
+   - Total leads found: [X]
+   - High priority (8-10): [X]
+   - Medium priority (5-7): [X]
+   - Average fit score: [X]
+   
+   ---
+   
+   ## Lead 1: [Company Name]
+   
+   **Website**: [URL]
+   **Priority Score**: [X/10]
+   **Industry**: [Industry]
+   **Size**: [Employee count/revenue range]
+   
+   **Why They're a Good Fit**:
+   [2-3 specific reasons based on their business]
+   
+   **Target Decision Maker**: [Role/Title]
+   **LinkedIn**: [URL if available]
+   
+   **Value Proposition for Them**:
+   [Specific benefit for this company]
+   
+   **Outreach Strategy**:
+   [Personalized approach - mention specific pain points, recent company news, or relevant context]
+   
+   **Conversation Starters**:
+   - [Specific point 1]
+   - [Specific point 2]
+   
+   ---
+   
+   [Repeat for each lead]
+   ```
+
+7. **Offer Next Steps**
+   - Suggest saving results to a CSV for CRM import
+   - Offer to draft personalized outreach messages
+   - Recommend prioritization based on timing
+   - Suggest follow-up research for top leads
+
+## Examples
+
+### Example 1: From Lenny's Newsletter
+
+**User**: "I'm building a tool that masks sensitive data in AI coding assistant queries. Find potential leads."
+
+**Output**: Creates a prioritized list of companies that:
+- Use AI coding assistants (Copilot, Cursor, etc.)
+- Handle sensitive data (fintech, healthcare, legal)
+- Have evidence in their GitHub repos of using coding agents
+- May have accidentally exposed sensitive data in code
+- Includes LinkedIn URLs of relevant decision-makers
+
+### Example 2: Local Business
+
+**User**: "I run a consulting practice for remote team productivity. Find me 10 companies in the Bay Area that recently went remote."
+
+**Output**: Identifies companies that:
+- Recently posted remote job listings
+- Announced remote-first policies
+- Are hiring distributed teams
+- Show signs of remote work challenges
+- Provides personalized outreach strategies for each
+
+## Tips for Best Results
+
+- **Be specific** about your product and its unique value
+- **Run from your codebase** if applicable for automatic context
+- **Provide context** about your ideal customer profile
+- **Specify constraints** like industry, location, or company size
+- **Request follow-up** research on promising leads for deeper insights
+
+## Related Use Cases
+
+- Drafting personalized outreach emails after identifying leads
+- Building a CRM-ready CSV of qualified prospects
+- Researching specific companies in detail
+- Analyzing competitor customer bases
+- Identifying partnership opportunities

package/skills/link-understanding.md

@@ -0,0 +1,21 @@
+---
+name: link-understanding
+description: Auto-detect and summarize URLs in user messages
+triggers: url, link, http, website, article, page, read this
+---
+
+# Link Understanding
+
+When the user's message contains URLs:
+
+1. Detect all HTTP/HTTPS URLs in the message
+2. For each URL, use `webFetch` to retrieve the page content
+3. Summarize the key information from each page
+4. Incorporate the summaries into your response
+
+Rules:
+- Fetch URLs before answering — don't guess what a link contains
+- If a URL fails to load, mention it and proceed with what you have
+- For very long pages, focus on the main content (first 2000 chars usually sufficient)
+- Don't fetch URLs that are clearly file downloads (.zip, .tar, .exe) — just note the filename
+- If the user asks about a specific part of the page, focus your summary on that

package/skills/macos-automation.md

@@ -0,0 +1,62 @@
+---
+name: macos-automation
+description: macOS automation via AppleScript/osascript — window management, app control, system prefs, Finder
+triggers: macos, applescript, osascript, window, finder, system preferences, notification, clipboard, screenshot, spotlight, automator, open app, close app, resize window
+---
+
+## Running AppleScript
+- Via executeCommand: `executeCommand("osascript -e 'tell application \"Finder\" to activate'")`
+- Multi-line: `writeFile("/tmp/script.scpt", script)` then `executeCommand("osascript /tmp/script.scpt")`
+- JavaScript (JXA): `executeCommand("osascript -l JavaScript -e 'Application(\"Finder\").activate()'")`
+
+## App Control
+- Open: `osascript -e 'tell application "Safari" to activate'`
+- Quit: `osascript -e 'tell application "Safari" to quit'`
+- Quit all: `osascript -e 'tell application "System Events" to set quitApps to name of every application process whose background only is false'`
+- Launch with file: `open -a "Preview" /path/to/file.pdf`
+- Check running: `osascript -e 'tell application "System Events" to (name of processes) contains "Safari"'`
+
+## Window Management
+- List windows: `osascript -e 'tell application "System Events" to tell process "AppName" to get {name, position, size} of every window'`
+- Move window: `osascript -e 'tell application "System Events" to tell process "AppName" to set position of window 1 to {0, 0}'`
+- Resize: `osascript -e 'tell application "System Events" to tell process "AppName" to set size of window 1 to {1200, 800}'`
+- Minimize: `osascript -e 'tell application "System Events" to tell process "AppName" to set miniaturized of window 1 to true'`
+- Fullscreen: `osascript -e 'tell application "System Events" to tell process "AppName" to set value of attribute "AXFullScreen" of window 1 to true'`
+
+## Finder Operations
+- Open folder: `osascript -e 'tell application "Finder" to open folder "Documents" of home'`
+- Get selection: `osascript -e 'tell application "Finder" to get selection as alias list'`
+- New folder: `osascript -e 'tell application "Finder" to make new folder at desktop with properties {name:"NewFolder"}'`
+- Reveal file: `open -R /path/to/file`
+- Trash file: `osascript -e 'tell application "Finder" to delete POSIX file "/path/to/file"'`
+
+## System
+- Notification: `osascript -e 'display notification "Body" with title "Title" sound name "Glass"'`
+- Dialog: `osascript -e 'display dialog "Question?" buttons {"No","Yes"} default button "Yes"'`
+- Clipboard get: `executeCommand("pbpaste")`
+- Clipboard set: `executeCommand("echo 'text' | pbcopy")`
+- Screenshot: `executeCommand("screencapture -x /tmp/screen.png")` — silent full screen
+- Screenshot region: `executeCommand("screencapture -ix /tmp/region.png")` — interactive select
+- Volume: `osascript -e 'set volume output volume 50'` (0-100)
+- Mute: `osascript -e 'set volume output muted true'`
+- Dark mode: `osascript -e 'tell application "System Events" to tell appearance preferences to set dark mode to true'`
+
+## Keyboard & Mouse
+- Keystroke: `osascript -e 'tell application "System Events" to keystroke "a" using command down'`
+- Key code: `osascript -e 'tell application "System Events" to key code 36'` (return)
+- Common key codes: 36 (return), 48 (tab), 49 (space), 51 (delete), 53 (escape), 123-126 (arrows)
+
+## Spotlight / Open
+- Open URL: `executeCommand("open https://example.com")`
+- Open file: `executeCommand("open /path/to/file")`
+- Open with app: `executeCommand("open -a 'Visual Studio Code' /path")`
+- Search Spotlight: `executeCommand("mdfind 'query'")`
+- Find by name: `executeCommand("mdfind -name 'filename'")`
+
+## Rules
+- Always use `executeCommand` — never run osascript directly
+- Quote inner AppleScript strings with `\"` (escaped within the command string)
+- For complex multi-line scripts, write to `/tmp/` first then execute
+- Test scripts before chaining destructive operations
+- Some actions require Accessibility permissions (System Settings > Privacy)
+- Prefer `open` CLI over AppleScript for simple file/URL/app launches

package/skills/mcp-builder/SKILL.md

@@ -0,0 +1,328 @@
+---
+name: mcp-builder
+description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
+license: Complete terms in LICENSE.txt
+---
+
+# MCP Server Development Guide
+
+## Overview
+
+To create high-quality MCP (Model Context Protocol) servers that enable LLMs to effectively interact with external services, use this skill. An MCP server provides tools that allow LLMs to access external services and APIs. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks using the tools provided.
+
+---
+
+# Process
+
+## 🚀 High-Level Workflow
+
+Creating a high-quality MCP server involves four main phases:
+
+### Phase 1: Deep Research and Planning
+
+#### 1.1 Understand Agent-Centric Design Principles
+
+Before diving into implementation, understand how to design tools for AI agents by reviewing these principles:
+
+**Build for Workflows, Not Just API Endpoints:**
+- Don't simply wrap existing API endpoints - build thoughtful, high-impact workflow tools
+- Consolidate related operations (e.g., `schedule_event` that both checks availability and creates event)
+- Focus on tools that enable complete tasks, not just individual API calls
+- Consider what workflows agents actually need to accomplish
+
+**Optimize for Limited Context:**
+- Agents have constrained context windows - make every token count
+- Return high-signal information, not exhaustive data dumps
+- Provide "concise" vs "detailed" response format options
+- Default to human-readable identifiers over technical codes (names over IDs)
+- Consider the agent's context budget as a scarce resource
+
+**Design Actionable Error Messages:**
+- Error messages should guide agents toward correct usage patterns
+- Suggest specific next steps: "Try using filter='active_only' to reduce results"
+- Make errors educational, not just diagnostic
+- Help agents learn proper tool usage through clear feedback
+
+**Follow Natural Task Subdivisions:**
+- Tool names should reflect how humans think about tasks
+- Group related tools with consistent prefixes for discoverability
+- Design tools around natural workflows, not just API structure
+
+**Use Evaluation-Driven Development:**
+- Create realistic evaluation scenarios early
+- Let agent feedback drive tool improvements
+- Prototype quickly and iterate based on actual agent performance
+
+#### 1.3 Study MCP Protocol Documentation
+
+**Fetch the latest MCP protocol documentation:**
+
+Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt`
+
+This comprehensive document contains the complete MCP specification and guidelines.
+
+#### 1.4 Study Framework Documentation
+
+**Load and read the following reference files:**
+
+- **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines for all MCP servers
+
+**For Python implementations, also load:**
+- **Python SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
+- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Python-specific best practices and examples
+
+**For Node/TypeScript implementations, also load:**
+- **TypeScript SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
+- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Node/TypeScript-specific best practices and examples
+
+#### 1.5 Exhaustively Study API Documentation
+
+To integrate a service, read through **ALL** available API documentation:
+- Official API reference documentation
+- Authentication and authorization requirements
+- Rate limiting and pagination patterns
+- Error responses and status codes
+- Available endpoints and their parameters
+- Data models and schemas
+
+**To gather comprehensive information, use web search and the WebFetch tool as needed.**
+
+#### 1.6 Create a Comprehensive Implementation Plan
+
+Based on your research, create a detailed plan that includes:
+
+**Tool Selection:**
+- List the most valuable endpoints/operations to implement
+- Prioritize tools that enable the most common and important use cases
+- Consider which tools work together to enable complex workflows
+
+**Shared Utilities and Helpers:**
+- Identify common API request patterns
+- Plan pagination helpers
+- Design filtering and formatting utilities
+- Plan error handling strategies
+
+**Input/Output Design:**
+- Define input validation models (Pydantic for Python, Zod for TypeScript)
+- Design consistent response formats (e.g., JSON or Markdown), and configurable levels of detail (e.g., Detailed or Concise)
+- Plan for large-scale usage (thousands of users/resources)
+- Implement character limits and truncation strategies (e.g., 25,000 tokens)
+
+**Error Handling Strategy:**
+- Plan graceful failure modes
+- Design clear, actionable, LLM-friendly, natural language error messages which prompt further action
+- Consider rate limiting and timeout scenarios
+- Handle authentication and authorization errors
+
+---
+
+### Phase 2: Implementation
+
+Now that you have a comprehensive plan, begin implementation following language-specific best practices.
+
+#### 2.1 Set Up Project Structure
+
+**For Python:**
+- Create a single `.py` file or organize into modules if complex (see [🐍 Python Guide](./reference/python_mcp_server.md))
+- Use the MCP Python SDK for tool registration
+- Define Pydantic models for input validation
+
+**For Node/TypeScript:**
+- Create proper project structure (see [⚡ TypeScript Guide](./reference/node_mcp_server.md))
+- Set up `package.json` and `tsconfig.json`
+- Use MCP TypeScript SDK
+- Define Zod schemas for input validation
+
+#### 2.2 Implement Core Infrastructure First
+
+**To begin implementation, create shared utilities before implementing tools:**
+- API request helper functions
+- Error handling utilities
+- Response formatting functions (JSON and Markdown)
+- Pagination helpers
+- Authentication/token management
+
+#### 2.3 Implement Tools Systematically
+
+For each tool in the plan:
+
+**Define Input Schema:**
+- Use Pydantic (Python) or Zod (TypeScript) for validation
+- Include proper constraints (min/max length, regex patterns, min/max values, ranges)
+- Provide clear, descriptive field descriptions
+- Include diverse examples in field descriptions
+
+**Write Comprehensive Docstrings/Descriptions:**
+- One-line summary of what the tool does
+- Detailed explanation of purpose and functionality
+- Explicit parameter types with examples
+- Complete return type schema
+- Usage examples (when to use, when not to use)
+- Error handling documentation, which outlines how to proceed given specific errors
+
+**Implement Tool Logic:**
+- Use shared utilities to avoid code duplication
+- Follow async/await patterns for all I/O
+- Implement proper error handling
+- Support multiple response formats (JSON and Markdown)
+- Respect pagination parameters
+- Check character limits and truncate appropriately
+
+**Add Tool Annotations:**
+- `readOnlyHint`: true (for read-only operations)
+- `destructiveHint`: false (for non-destructive operations)
+- `idempotentHint`: true (if repeated calls have same effect)
+- `openWorldHint`: true (if interacting with external systems)
+
+#### 2.4 Follow Language-Specific Best Practices
+
+**At this point, load the appropriate language guide:**
+
+**For Python: Load [🐍 Python Implementation Guide](./reference/python_mcp_server.md) and ensure the following:**
+- Using MCP Python SDK with proper tool registration
+- Pydantic v2 models with `model_config`
+- Type hints throughout
+- Async/await for all I/O operations
+- Proper imports organization
+- Module-level constants (CHARACTER_LIMIT, API_BASE_URL)
+
+**For Node/TypeScript: Load [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) and ensure the following:**
+- Using `server.registerTool` properly
+- Zod schemas with `.strict()`
+- TypeScript strict mode enabled
+- No `any` types - use proper types
+- Explicit Promise<T> return types
+- Build process configured (`npm run build`)
+
+---
+
+### Phase 3: Review and Refine
+
+After initial implementation:
+
+#### 3.1 Code Quality Review
+
+To ensure quality, review the code for:
+- **DRY Principle**: No duplicated code between tools
+- **Composability**: Shared logic extracted into functions
+- **Consistency**: Similar operations return similar formats
+- **Error Handling**: All external calls have error handling
+- **Type Safety**: Full type coverage (Python type hints, TypeScript types)
+- **Documentation**: Every tool has comprehensive docstrings/descriptions
+
+#### 3.2 Test and Build
+
+**Important:** MCP servers are long-running processes that wait for requests over stdio/stdin or sse/http. Running them directly in your main process (e.g., `python server.py` or `node dist/index.js`) will cause your process to hang indefinitely.
+
+**Safe ways to test the server:**
+- Use the evaluation harness (see Phase 4) - recommended approach
+- Run the server in tmux to keep it outside your main process
+- Use a timeout when testing: `timeout 5s python server.py`
+
+**For Python:**
+- Verify Python syntax: `python -m py_compile your_server.py`
+- Check imports work correctly by reviewing the file
+- To manually test: Run server in tmux, then test with evaluation harness in main process
+- Or use the evaluation harness directly (it manages the server for stdio transport)
+
+**For Node/TypeScript:**
+- Run `npm run build` and ensure it completes without errors
+- Verify dist/index.js is created
+- To manually test: Run server in tmux, then test with evaluation harness in main process
+- Or use the evaluation harness directly (it manages the server for stdio transport)
+
+#### 3.3 Use Quality Checklist
+
+To verify implementation quality, load the appropriate checklist from the language-specific guide:
+- Python: see "Quality Checklist" in [🐍 Python Guide](./reference/python_mcp_server.md)
+- Node/TypeScript: see "Quality Checklist" in [⚡ TypeScript Guide](./reference/node_mcp_server.md)
+
+---
+
+### Phase 4: Create Evaluations
+
+After implementing your MCP server, create comprehensive evaluations to test its effectiveness.
+
+**Load [✅ Evaluation Guide](./reference/evaluation.md) for complete evaluation guidelines.**
+
+#### 4.1 Understand Evaluation Purpose
+
+Evaluations test whether LLMs can effectively use your MCP server to answer realistic, complex questions.
+
+#### 4.2 Create 10 Evaluation Questions
+
+To create effective evaluations, follow the process outlined in the evaluation guide:
+
+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
+
+#### 4.3 Evaluation Requirements
+
+Each question must be:
+- **Independent**: Not dependent on other questions
+- **Read-only**: Only non-destructive operations required
+- **Complex**: Requiring multiple tool calls and deep exploration
+- **Realistic**: Based on real use cases humans would care about
+- **Verifiable**: Single, clear answer that can be verified by string comparison
+- **Stable**: Answer won't change over time
+
+#### 4.4 Output Format
+
+Create an XML file with this structure:
+
+```xml
+<evaluation>
+  <qa_pair>
+    <question>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?</question>
+    <answer>3</answer>
+  </qa_pair>
+<!-- More qa_pairs... -->
+</evaluation>
+```
+
+---
+
+# Reference Files
+
+## 📚 Documentation Library
+
+Load these resources as needed during development:
+
+### Core MCP Documentation (Load First)
+- **MCP Protocol**: Fetch from `https://modelcontextprotocol.io/llms-full.txt` - Complete MCP specification
+- [📋 MCP Best Practices](./reference/mcp_best_practices.md) - Universal MCP guidelines including:
+  - Server and tool naming conventions
+  - Response format guidelines (JSON vs Markdown)
+  - Pagination best practices
+  - Character limits and truncation strategies
+  - Tool development guidelines
+  - Security and error handling standards
+
+### SDK Documentation (Load During Phase 1/2)
+- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
+- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
+
+### Language-Specific Implementation Guides (Load During Phase 2)
+- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Complete Python/FastMCP guide with:
+  - Server initialization patterns
+  - Pydantic model examples
+  - Tool registration with `@mcp.tool`
+  - Complete working examples
+  - Quality checklist
+
+- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Complete TypeScript guide with:
+  - Project structure
+  - Zod schema patterns
+  - Tool registration with `server.registerTool`
+  - Complete working examples
+  - Quality checklist
+
+### Evaluation Guide (Load During Phase 4)
+- [✅ Evaluation Guide](./reference/evaluation.md) - Complete evaluation creation guide with:
+  - Question creation guidelines
+  - Answer verification strategies
+  - XML format specifications
+  - Example questions and answers
+  - Running an evaluation with the provided scripts