gkt-node 3.3.0

package/assets/.agent/skills/computer-use-agents/SKILL.md

@@ -0,0 +1,315 @@
+---
+name: computer-use-agents
+description: "Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation."
+source: vibeship-spawner-skills (Apache 2.0)
+---
+
+# Computer Use Agents
+
+## Patterns
+
+### Perception-Reasoning-Action Loop
+
+The fundamental architecture of computer use agents: observe screen,
+reason about next action, execute action, repeat. This loop integrates
+vision models with action execution through an iterative pipeline.
+
+Key components:
+1. PERCEPTION: Screenshot captures current screen state
+2. REASONING: Vision-language model analyzes and plans
+3. ACTION: Execute mouse/keyboard operations
+4. FEEDBACK: Observe result, continue or correct
+
+Critical insight: Vision agents are completely still during "thinking"
+phase (1-5 seconds), creating a detectable pause pattern.
+
+
+**When to use**: ['Building any computer use agent from scratch', 'Integrating vision models with desktop control', 'Understanding agent behavior patterns']
+
+```python
+from anthropic import Anthropic
+from PIL import Image
+import base64
+import pyautogui
+import time
+
+class ComputerUseAgent:
+    """
+    Perception-Reasoning-Action loop implementation.
+    Based on Anthropic Computer Use patterns.
+    """
+
+    def __init__(self, client: Anthropic, model: str = "claude-sonnet-4-20250514"):
+        self.client = client
+        self.model = model
+        self.max_steps = 50  # Prevent runaway loops
+        self.action_delay = 0.5  # Seconds between actions
+
+    def capture_screenshot(self) -> str:
+        """Capture screen and return base64 encoded image."""
+        screenshot = pyautogui.screenshot()
+        # Resize for token efficiency (1280x800 is good balance)
+        screenshot = screenshot.resize((1280, 800), Image.LANCZOS)
+
+        import io
+        buffer = io.BytesIO()
+        screenshot.save(buffer, format="PNG")
+        return base64.b64encode(buffer.getvalue()).decode()
+
+    def execute_action(self, action: dict) -> dict:
+        """Execute mouse/keyboard action on the computer."""
+        action_type = action.get("type")
+
+        if action_type == "click":
+            x, y = action["x"], action["y"]
+            button = action.get("button", "left")
+            pyautogui.click(x, y, button=button)
+            return {"success": True, "action": f"clicked at ({x}, {y})"}
+
+        elif action_type == "type":
+            text = action["text"]
+            pyautogui.typewrite(text, interval=0.02)
+            return {"success": True, "action": f"typed {len(text)} chars"}
+
+        elif action_type == "key":
+            key = action["key"]
+            pyautogui.press(key)
+            return {"success": True, "action": f"pressed {key}"}
+
+        elif action_type == "scroll":
+            direction = action.get("direction", "down")
+            amount = action.get("amount", 3)
+            scroll = -amount if direction == "down" else amount
+            pyautogui.scroll(scroll)
+            return {"success": True, "action": f"scrolled {dir
+```
+
+### Sandboxed Environment Pattern
+
+Computer use agents MUST run in isolated, sandboxed environments.
+Never give agents direct access to your main system - the security
+risks are too high. Use Docker containers with virtual desktops.
+
+Key isolation requirements:
+1. NETWORK: Restrict to necessary endpoints only
+2. FILESYSTEM: Read-only or scoped to temp directories
+3. CREDENTIALS: No access to host credentials
+4. SYSCALLS: Filter dangerous system calls
+5. RESOURCES: Limit CPU, memory, time
+
+The goal is "blast radius minimization" - if the agent goes wrong,
+damage is contained to the sandbox.
+
+
+**When to use**: ['Deploying any computer use agent', 'Testing agent behavior safely', 'Running untrusted automation tasks']
+
+```python
+# Dockerfile for sandboxed computer use environment
+# Based on Anthropic's reference implementation pattern
+
+FROM ubuntu:22.04
+
+# Install desktop environment
+RUN apt-get update && apt-get install -y \
+    xvfb \
+    x11vnc \
+    fluxbox \
+    xterm \
+    firefox \
+    python3 \
+    python3-pip \
+    supervisor
+
+# Security: Create non-root user
+RUN useradd -m -s /bin/bash agent && \
+    mkdir -p /home/agent/.vnc
+
+# Install Python dependencies
+COPY requirements.txt /tmp/
+RUN pip3 install -r /tmp/requirements.txt
+
+# Security: Drop capabilities
+RUN apt-get install -y --no-install-recommends libcap2-bin && \
+    setcap -r /usr/bin/python3 || true
+
+# Copy agent code
+COPY --chown=agent:agent . /app
+WORKDIR /app
+
+# Supervisor config for virtual display + VNC
+COPY supervisord.conf /etc/supervisor/conf.d/
+
+# Expose VNC port only (not desktop directly)
+EXPOSE 5900
+
+# Run as non-root
+USER agent
+
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+
+---
+
+# docker-compose.yml with security constraints
+version: '3.8'
+
+services:
+  computer-use-agent:
+    build: .
+    ports:
+      - "5900:5900"  # VNC for observation
+      - "8080:8080"  # API for control
+
+    # Security constraints
+    security_opt:
+      - no-new-privileges:true
+      - seccomp:seccomp-profile.json
+
+    # Resource limits
+    deploy:
+      resources:
+        limits:
+          cpus: '2'
+          memory: 4G
+        reservations:
+          cpus: '0.5'
+          memory: 1G
+
+    # Network isolation
+    networks:
+      - agent-network
+
+    # No access to host filesystem
+    volumes:
+      - agent-tmp:/tmp
+
+    # Read-only root filesystem
+    read_only: true
+    tmpfs:
+      - /run
+      - /var/run
+
+    # Environment
+    environment:
+      - DISPLAY=:99
+      - NO_PROXY=localhost
+
+networks:
+  agent-network:
+    driver: bridge
+    internal: true  # No internet by default
+
+volumes:
+  agent-tmp:
+
+---
+
+# Python wrapper with additional runtime sandboxing
+import subprocess
+import os
+from dataclasses im
+```
+
+### Anthropic Computer Use Implementation
+
+Official implementation pattern using Claude's computer use capability.
+Claude 3.5 Sonnet was the first frontier model to offer computer use.
+Claude Opus 4.5 is now the "best model in the world for computer use."
+
+Key capabilities:
+- screenshot: Capture current screen state
+- mouse: Click, move, drag operations
+- keyboard: Type text, press keys
+- bash: Run shell commands
+- text_editor: View and edit files
+
+Tool versions:
+- computer_20251124 (Opus 4.5): Adds zoom action for detailed inspection
+- computer_20250124 (All other models): Standard capabilities
+
+Critical limitation: "Some UI elements (like dropdowns and scrollbars)
+might be tricky for Claude to manipulate" - Anthropic docs
+
+
+**When to use**: ['Building production computer use agents', 'Need highest quality vision understanding', 'Full desktop control (not just browser)']
+
+```python
+from anthropic import Anthropic
+from anthropic.types.beta import (
+    BetaToolComputerUse20241022,
+    BetaToolBash20241022,
+    BetaToolTextEditor20241022,
+)
+import subprocess
+import base64
+from PIL import Image
+import io
+
+class AnthropicComputerUse:
+    """
+    Official Anthropic Computer Use implementation.
+
+    Requires:
+    - Docker container with virtual display
+    - VNC for viewing agent actions
+    - Proper tool implementations
+    """
+
+    def __init__(self):
+        self.client = Anthropic()
+        self.model = "claude-sonnet-4-20250514"  # Best for computer use
+        self.screen_size = (1280, 800)
+
+    def get_tools(self) -> list:
+        """Define computer use tools."""
+        return [
+            BetaToolComputerUse20241022(
+                type="computer_20241022",
+                name="computer",
+                display_width_px=self.screen_size[0],
+                display_height_px=self.screen_size[1],
+            ),
+            BetaToolBash20241022(
+                type="bash_20241022",
+                name="bash",
+            ),
+            BetaToolTextEditor20241022(
+                type="text_editor_20241022",
+                name="str_replace_editor",
+            ),
+        ]
+
+    def execute_tool(self, name: str, input: dict) -> dict:
+        """Execute a tool and return result."""
+
+        if name == "computer":
+            return self._handle_computer_action(input)
+        elif name == "bash":
+            return self._handle_bash(input)
+        elif name == "str_replace_editor":
+            return self._handle_editor(input)
+        else:
+            return {"error": f"Unknown tool: {name}"}
+
+    def _handle_computer_action(self, input: dict) -> dict:
+        """Handle computer control actions."""
+        action = input.get("action")
+
+        if action == "screenshot":
+            # Capture via xdotool/scrot
+            subprocess.run(["scrot", "/tmp/screenshot.png"])
+
+            with open("/tmp/screenshot.png", "rb") as f:
+            
+```
+
+## ⚠️ Sharp Edges
+
+| Issue | Severity | Solution |
+|-------|----------|----------|
+| Issue | critical | ## Defense in depth - no single solution works |
+| Issue | medium | ## Add human-like variance to actions |
+| Issue | high | ## Use keyboard alternatives when possible |
+| Issue | medium | ## Accept the tradeoff |
+| Issue | high | ## Implement context management |
+| Issue | high | ## Monitor and limit costs |
+| Issue | critical | ## ALWAYS use sandboxing |

package/assets/.agent/skills/content-creator/SKILL.md

@@ -0,0 +1,248 @@
+---
+name: content-creator
+description: Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy.
+license: MIT
+metadata:
+  version: 1.0.0
+  author: Alireza Rezvani
+  category: marketing
+  domain: content-marketing
+  updated: 2025-10-20
+  python-tools: brand_voice_analyzer.py, seo_optimizer.py
+  tech-stack: SEO, social-media-platforms
+---
+
+# Content Creator
+
+Professional-grade brand voice analysis, SEO optimization, and platform-specific content frameworks.
+
+## Keywords
+content creation, blog posts, SEO, brand voice, social media, content calendar, marketing content, content strategy, content marketing, brand consistency, content optimization, social media marketing, content planning, blog writing, content frameworks, brand guidelines, social media strategy
+
+## Quick Start
+
+### For Brand Voice Development
+1. Run `scripts/brand_voice_analyzer.py` on existing content to establish baseline
+2. Review `references/brand_guidelines.md` to select voice attributes
+3. Apply chosen voice consistently across all content
+
+### For Blog Content Creation
+1. Choose template from `references/content_frameworks.md`
+2. Research keywords for topic
+3. Write content following template structure
+4. Run `scripts/seo_optimizer.py [file] [primary-keyword]` to optimize
+5. Apply recommendations before publishing
+
+### For Social Media Content
+1. Review platform best practices in `references/social_media_optimization.md`
+2. Use appropriate template from `references/content_frameworks.md`
+3. Optimize based on platform-specific guidelines
+4. Schedule using `assets/content_calendar_template.md`
+
+## Core Workflows
+
+### Establishing Brand Voice (First Time Setup)
+
+When creating content for a new brand or client:
+
+1. **Analyze Existing Content** (if available)
+   ```bash
+   python scripts/brand_voice_analyzer.py existing_content.txt
+   ```
+   
+2. **Define Voice Attributes**
+   - Review brand personality archetypes in `references/brand_guidelines.md`
+   - Select primary and secondary archetypes
+   - Choose 3-5 tone attributes
+   - Document in brand guidelines
+
+3. **Create Voice Sample**
+   - Write 3 sample pieces in chosen voice
+   - Test consistency using analyzer
+   - Refine based on results
+
+### Creating SEO-Optimized Blog Posts
+
+1. **Keyword Research**
+   - Identify primary keyword (search volume 500-5000/month)
+   - Find 3-5 secondary keywords
+   - List 10-15 LSI keywords
+
+2. **Content Structure**
+   - Use blog template from `references/content_frameworks.md`
+   - Include keyword in title, first paragraph, and 2-3 H2s
+   - Aim for 1,500-2,500 words for comprehensive coverage
+
+3. **Optimization Check**
+   ```bash
+   python scripts/seo_optimizer.py blog_post.md "primary keyword" "secondary,keywords,list"
+   ```
+
+4. **Apply SEO Recommendations**
+   - Adjust keyword density to 1-3%
+   - Ensure proper heading structure
+   - Add internal and external links
+   - Optimize meta description
+
+### Social Media Content Creation
+
+1. **Platform Selection**
+   - Identify primary platforms based on audience
+   - Review platform-specific guidelines in `references/social_media_optimization.md`
+
+2. **Content Adaptation**
+   - Start with blog post or core message
+   - Use repurposing matrix from `references/content_frameworks.md`
+   - Adapt for each platform following templates
+
+3. **Optimization Checklist**
+   - Platform-appropriate length
+   - Optimal posting time
+   - Correct image dimensions
+   - Platform-specific hashtags
+   - Engagement elements (polls, questions)
+
+### Content Calendar Planning
+
+1. **Monthly Planning**
+   - Copy `assets/content_calendar_template.md`
+   - Set monthly goals and KPIs
+   - Identify key campaigns/themes
+
+2. **Weekly Distribution**
+   - Follow 40/25/25/10 content pillar ratio
+   - Balance platforms throughout week
+   - Align with optimal posting times
+
+3. **Batch Creation**
+   - Create all weekly content in one session
+   - Maintain consistent voice across pieces
+   - Prepare all visual assets together
+
+## Key Scripts
+
+### brand_voice_analyzer.py
+Analyzes text content for voice characteristics, readability, and consistency.
+
+**Usage**: `python scripts/brand_voice_analyzer.py <file> [json|text]`
+
+**Returns**:
+- Voice profile (formality, tone, perspective)
+- Readability score
+- Sentence structure analysis
+- Improvement recommendations
+
+### seo_optimizer.py
+Analyzes content for SEO optimization and provides actionable recommendations.
+
+**Usage**: `python scripts/seo_optimizer.py <file> [primary_keyword] [secondary_keywords]`
+
+**Returns**:
+- SEO score (0-100)
+- Keyword density analysis
+- Structure assessment
+- Meta tag suggestions
+- Specific optimization recommendations
+
+## Reference Guides
+
+### When to Use Each Reference
+
+**references/brand_guidelines.md**
+- Setting up new brand voice
+- Ensuring consistency across content
+- Training new team members
+- Resolving voice/tone questions
+
+**references/content_frameworks.md**
+- Starting any new content piece
+- Structuring different content types
+- Creating content templates
+- Planning content repurposing
+
+**references/social_media_optimization.md**
+- Platform-specific optimization
+- Hashtag strategy development
+- Understanding algorithm factors
+- Setting up analytics tracking
+
+## Best Practices
+
+### Content Creation Process
+1. Always start with audience need/pain point
+2. Research before writing
+3. Create outline using templates
+4. Write first draft without editing
+5. Optimize for SEO
+6. Edit for brand voice
+7. Proofread and fact-check
+8. Optimize for platform
+9. Schedule strategically
+
+### Quality Indicators
+- SEO score above 75/100
+- Readability appropriate for audience
+- Consistent brand voice throughout
+- Clear value proposition
+- Actionable takeaways
+- Proper visual formatting
+- Platform-optimized
+
+### Common Pitfalls to Avoid
+- Writing before researching keywords
+- Ignoring platform-specific requirements
+- Inconsistent brand voice
+- Over-optimizing for SEO (keyword stuffing)
+- Missing clear CTAs
+- Publishing without proofreading
+- Ignoring analytics feedback
+
+## Performance Metrics
+
+Track these KPIs for content success:
+
+### Content Metrics
+- Organic traffic growth
+- Average time on page
+- Bounce rate
+- Social shares
+- Backlinks earned
+
+### Engagement Metrics
+- Comments and discussions
+- Email click-through rates
+- Social media engagement rate
+- Content downloads
+- Form submissions
+
+### Business Metrics
+- Leads generated
+- Conversion rate
+- Customer acquisition cost
+- Revenue attribution
+- ROI per content piece
+
+## Integration Points
+
+This skill works best with:
+- Analytics platforms (Google Analytics, social media insights)
+- SEO tools (for keyword research)
+- Design tools (for visual content)
+- Scheduling platforms (for content distribution)
+- Email marketing systems (for newsletter content)
+
+## Quick Commands
+
+```bash
+# Analyze brand voice
+python scripts/brand_voice_analyzer.py content.txt
+
+# Optimize for SEO
+python scripts/seo_optimizer.py article.md "main keyword"
+
+# Check content against brand guidelines
+grep -f references/brand_guidelines.md content.txt
+
+# Create monthly calendar
+cp assets/content_calendar_template.md this_month_calendar.md
+```

package/assets/.agent/skills/content-creator/assets/content_calendar_template.md

@@ -0,0 +1,99 @@
+# Content Calendar Template - [Month Year]
+
+## Monthly Goals
+- **Traffic Goal**: 
+- **Lead Generation Goal**: 
+- **Engagement Goal**: 
+- **Key Campaign**: 
+
+## Week 1: [Date Range]
+
+### Monday [Date]
+**Platform**: Blog
+**Topic**: 
+**Keywords**: 
+**Status**: [ ] Planned [ ] Written [ ] Reviewed [ ] Published
+**Owner**: 
+**Notes**: 
+
+**Platform**: LinkedIn
+**Type**: Article Share
+**Caption**: 
+**Hashtags**: 
+**Time**: 10:00 AM
+
+### Tuesday [Date]
+**Platform**: Instagram
+**Type**: Carousel
+**Topic**: 
+**Visuals**: [ ] Created [ ] Approved
+**Caption**: 
+**Hashtags**: 
+**Time**: 12:00 PM
+
+### Wednesday [Date]
+**Platform**: Email Newsletter
+**Subject Line**: 
+**Segment**: 
+**CTA**: 
+**Status**: [ ] Drafted [ ] Designed [ ] Scheduled
+
+### Thursday [Date]
+**Platform**: Twitter/X
+**Type**: Thread
+**Topic**: 
+**Thread Length**: 
+**Media**: [ ] Images [ ] GIFs [ ] None
+**Time**: 2:00 PM
+
+### Friday [Date]
+**Platform**: Multi-channel
+**Campaign**: 
+**Assets Needed**:
+- [ ] Blog post
+- [ ] Social graphics
+- [ ] Email
+- [ ] Video
+
+## Week 2: [Date Range]
+[Repeat structure]
+
+## Week 3: [Date Range]
+[Repeat structure]
+
+## Week 4: [Date Range]
+[Repeat structure]
+
+## Content Bank (Ideas for Future)
+1. 
+2. 
+3. 
+4. 
+5. 
+
+## Performance Review (End of Month)
+
+### Top Performing Content
+1. **Title/Topic**: 
+   - **Metric**: 
+   - **Why it worked**: 
+
+2. **Title/Topic**: 
+   - **Metric**: 
+   - **Why it worked**: 
+
+### Lessons Learned
+- 
+- 
+- 
+
+### Adjustments for Next Month
+- 
+- 
+- 
+
+## Resource Links
+- Brand Guidelines: [Link]
+- Asset Library: [Link]
+- Analytics Dashboard: [Link]
+- Team Calendar: [Link]