SKILL.md working - tested with smiley creator gif

Author: mkagenius

Dockerfile

@@ -41,6 +41,16 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libgbm1 \
     libxshmfence1 \
     libasound2 \
+    unzip \
+    p7zip-full \
+    bc \
+    ripgrep \
+    fd-find \
+    sqlite3 \
+    libsqlite3-dev \
+    wkhtmltopdf \
+    poppler-utils \
+    default-jre \
  && apt-get clean && rm -rf /var/lib/apt/lists/*
 
 
@@ -64,6 +74,12 @@ COPY ./server.py /app/server.py
 # Create application/jupyter directories
 RUN mkdir -p /app/uploads /app/jupyter_runtime
 
+# Copy skills directory structure into the container
+# Public skills are baked into the image
+# User skills directory is created as mount point for user-added skills
+COPY ./skills/public /app/uploads/skills/public
+RUN mkdir -p /app/uploads/skills/user
+
 # # Generate SSH host keys
 # RUN ssh-keygen -A
 

README.md

@@ -178,11 +178,77 @@ Code runs in an isolated container with VM-level isolation. Your host system and
 From [@apple/container](https://github.com/apple/container/blob/main/docs/technical-overview.md):
 >Each container has the isolation properties of a full VM, using a minimal set of core utilities and dynamic libraries to reduce resource utilization and attack surface.
 
+## Skills System
+
+CodeRunner includes a built-in skills system that provides pre-packaged tools for common tasks. Skills are organized into two categories:
+
+### Built-in Public Skills
+
+The following skills are included in every CodeRunner installation:
+
+- **pdf-text-replace** - Replace text in fillable PDF forms
+- **image-crop-rotate** - Crop and rotate images
+
+### Using Skills
+
+Skills are accessed through MCP tools:
+
+```python
+# List all available skills
+result = await list_skills()
+
+# Get documentation for a specific skill
+info = await get_skill_info("pdf-text-replace")
+
+# Execute a skill's script
+code = """
+import subprocess
+subprocess.run([
+    'python',
+    '/app/uploads/skills/public/pdf-text-replace/scripts/replace_text_in_pdf.py',
+    '/app/uploads/input.pdf',
+    'OLD TEXT',
+    'NEW TEXT',
+    '/app/uploads/output.pdf'
+])
+"""
+result = await execute_python_code(code)
+```
+
+### Adding Custom Skills
+
+Users can add their own skills to the `~/.coderunner/assets/skills/user/` directory:
+
+1. Create a directory for your skill (e.g., `my-custom-skill/`)
+2. Add a `SKILL.md` file with documentation
+3. Add your scripts in a `scripts/` subdirectory
+4. Skills will be automatically discovered by the `list_skills()` tool
+
+**Skill Structure:**
+```
+~/.coderunner/assets/skills/user/my-custom-skill/
+├── SKILL.md              # Documentation with usage examples
+└── scripts/              # Your Python/bash scripts
+    └── process.py
+```
+
+### Example: Using the PDF Text Replace Skill
+
+```bash
+# Inside the container, execute:
+python /app/uploads/skills/public/pdf-text-replace/scripts/replace_text_in_pdf.py \
+    /app/uploads/tax_form.pdf \
+    "John Doe" \
+    "Jane Smith" \
+    /app/uploads/tax_form_updated.pdf
+```
+
 ## Architecture
 
 CodeRunner consists of:
 - **Sandbox Container:** Isolated execution environment with Jupyter kernel
 - **MCP Server:** Handles communication between AI models and the sandbox
+- **Skills System:** Pre-packaged tools for common tasks (PDF manipulation, image processing, etc.)
 
 ## Examples
 

install.sh

@@ -19,7 +19,7 @@ else
   echo "✅ macOS system detected."
 fi
 
-download_url="https://github.com/apple/container/releases/download/0.3.0/container-0.3.0-installer-signed.pkg"
+download_url="https://github.com/apple/container/releases/download/0.5.0/container-0.5.0-installer-signed.pkg"
 
 # Check if container is installed and display its version
 if command -v container &> /dev/null

requirements.txt

@@ -38,3 +38,44 @@ fastmcp
 openai-agents
 
 playwright==1.53.0
+
+# Data Science Libraries
+pandas
+numpy
+scipy
+scikit-learn
+statsmodels
+
+# Visualization Libraries
+matplotlib
+seaborn
+
+# File Processing Libraries
+pyarrow
+openpyxl
+xlsxwriter
+xlrd
+pillow
+python-pptx
+python-docx
+pypdf
+pdfplumber
+pypdfium2
+pdf2image
+pdfkit
+tabula-py
+reportlab[pycairo]
+img2pdf
+
+# Math & Computing Libraries
+sympy
+mpmath
+
+# Utilities
+tqdm
+python-dateutil
+pytz
+joblib
+
+# Beautiful Soup for HTML parsing (already used in server.py)
+beautifulsoup4

server.py

@@ -5,6 +5,7 @@
 import json
 import logging
 import os
+import zipfile
 import pathlib
 import time
 import uuid
@@ -53,6 +54,11 @@
 SHARED_DIR.mkdir(exist_ok=True)
 KERNEL_ID_FILE_PATH = SHARED_DIR / "python_kernel_id.txt"
 
+# Skills directory configuration
+SKILLS_DIR = SHARED_DIR / "skills"
+PUBLIC_SKILLS_DIR = SKILLS_DIR / "public"
+USER_SKILLS_DIR = SKILLS_DIR / "user"
+
 def resolve_with_system_dns(hostname):
     try:
         return socket.gethostbyname(hostname)
@@ -530,5 +536,149 @@ async def navigate_and_get_all_visible_text(url: str) -> str:
         return f"Error: Failed to retrieve all visible text: {str(e)}"
 
 
+# --- SKILLS MANAGEMENT TOOLS ---
+
+
+async def _parse_skill_frontmatter(skill_md_path):
+    try:
+        async with aiofiles.open(skill_md_path, mode='r') as f:
+            content = await f.read()
+            frontmatter = []
+            in_frontmatter = False
+            for line in content.splitlines():
+                if line.strip() == '---':
+                    if in_frontmatter:
+                        break
+                    else:
+                        in_frontmatter = True
+                        continue
+                if in_frontmatter:
+                    frontmatter.append(line)
+            
+            metadata = {}
+            for line in frontmatter:
+                if ':' in line:
+                    key, value = line.split(':', 1)
+                    metadata[key.strip()] = value.strip()
+            return metadata
+    except Exception:
+        return {}
+
+@mcp.tool()
+async def list_skills() -> str:
+    """
+    Lists all available skills in the CodeRunner container.
+
+    Returns a list of available skills organized by category (public/user).
+    Public skills are built into the container, while user skills are added by users.
+
+    Returns:
+        JSON string with skill names organized by category.
+    """
+    try:
+        # Unzip any user-provided skills
+        if USER_SKILLS_DIR.exists():
+            for item in USER_SKILLS_DIR.iterdir():
+                if item.is_file() and item.suffix == '.zip':
+                    with zipfile.ZipFile(item, 'r') as zip_ref:
+                        zip_ref.extractall(USER_SKILLS_DIR)
+                    os.remove(item)
+
+        skills = {
+            "public": [],
+            "user": []
+        }
+
+        # Helper to process a skills directory
+        async def process_skill_dir(directory, category):
+            if directory.exists():
+                for skill_dir in directory.iterdir():
+                    if skill_dir.is_dir():
+                        skill_md_path = skill_dir / "SKILL.md"
+                        if skill_md_path.exists():
+                            metadata = await _parse_skill_frontmatter(skill_md_path)
+                            skills[category].append({
+                                "name": metadata.get("name", skill_dir.name),
+                                "description": metadata.get("description", "No description available.")
+                            })
+
+        await process_skill_dir(PUBLIC_SKILLS_DIR, "public")
+        await process_skill_dir(USER_SKILLS_DIR, "user")
+
+        # Sort for consistent output
+        skills["public"].sort(key=lambda x: x['name'])
+        skills["user"].sort(key=lambda x: x['name'])
+
+        result = f"Available Skills:\n\n"
+        result += f"Public Skills ({len(skills['public'])}):\n"
+        if skills["public"]:
+            for skill in skills["public"]:
+                result += f"  - {skill['name']}: {skill['description']}\n"
+        else:
+            result += "  (none)\n"
+
+        result += f"\nUser Skills ({len(skills['user'])}):\n"
+        if skills["user"]:
+            for skill in skills["user"]:
+                result += f"  - {skill['name']}: {skill['description']}\n"
+        else:
+            result += "  (none)\n"
+
+        result += f"\nUse get_skill_info(skill_name) to read documentation for a specific skill."
+
+        return result
+
+    except Exception as e:
+        logger.error(f"Failed to list skills: {e}")
+        return f"Error: Failed to list skills: {str(e)}"
+
+
+@mcp.tool()
+async def get_skill_info(skill_name: str) -> str:
+    """
+    Retrieves the documentation (SKILL.md) for a specific skill.
+
+    Args:
+        skill_name: The name of the skill (e.g., 'pdf-text-replace', 'image-crop-rotate')
+
+    Returns:
+        The content of the skill's SKILL.md file with usage instructions and examples.
+    """
+    try:
+        # Check public skills first
+        public_skill_path = PUBLIC_SKILLS_DIR / skill_name / "SKILL.md"
+        user_skill_path = USER_SKILLS_DIR / skill_name / "SKILL.md"
+
+        skill_path = None
+        skill_type = None
+
+        if public_skill_path.exists():
+            skill_path = public_skill_path
+            skill_type = "public"
+        elif user_skill_path.exists():
+            skill_path = user_skill_path
+            skill_type = "user"
+        else:
+            return f"Error: Skill '{skill_name}' not found. Use list_skills() to see available skills."
+
+        # Read the SKILL.md content
+        async with aiofiles.open(skill_path, mode='r') as f:
+            content = await f.read()
+
+        # Replace all occurrences of /mnt/user-data with /app/uploads
+        content = content.replace('/mnt/user-data', '/app/uploads')
+
+        # Add header with skill type
+        header = f"Skill: {skill_name} ({skill_type})\n"
+        header += f"Location: /app/uploads/skills/{skill_type}/{skill_name}/\n"
+        header += "=" * 80 + "\n\n"
+
+        return header + content
+
+    except Exception as e:
+        logger.error(f"Failed to get skill info for '{skill_name}': {e}")
+        return f"Error: Failed to get skill info: {str(e)}"
+
+
 # Use the streamable_http_app as it's the modern standard
 app = mcp.streamable_http_app()