Skip to main content
Glama
fkesheh

Skill Management MCP Server

by fkesheh

skill_crud

Create, list, search, get, validate, and delete reusable skills stored locally for the Skill Management MCP Server.

Instructions

Unified CRUD tool for skill management.

IMPORTANT NOTES:

  • Skills are stored in ~/.skill-mcp/skills directory

  • All file paths in responses are relative to the skill directory (e.g., 'main.py', not full paths)

  • To execute scripts, use the 'run_skill_script' tool, NOT external bash/shell tools

Operations:

  • create: Create a new skill with templates (basic, python, bash, nodejs)

  • list: List all skills with optional search (supports text and regex)

  • search: Search for skills by pattern (text or regex)

  • get: Get detailed information about a specific skill

  • validate: Validate skill structure and get diagnostics

  • delete: Delete a skill directory (requires confirm=true)

  • list_templates: List all available skill templates with descriptions

Examples:

// List available templates
{"operation": "list_templates"}

// Create a Python skill
{"operation": "create", "skill_name": "my-skill", "description": "My skill", "template": "python"}

// List all skills
{"operation": "list"}

// Search skills by text
{"operation": "search", "search": "weather"}

// Search skills by regex pattern
{"operation": "search", "search": "^api-"}

// Get skill details
{"operation": "get", "skill_name": "my-skill", "include_content": true}

// Validate skill
{"operation": "validate", "skill_name": "my-skill"}

// Delete skill
{"operation": "delete", "skill_name": "my-skill", "confirm": true}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation to perform: 'create', 'list', 'get', 'validate', 'delete'
skill_nameNoName of the skill (required for get, validate, delete, create)
descriptionNoSkill description (optional for create)
templateNoTemplate to use for create: 'basic', 'python', 'bash', 'nodejs'basic
searchNoSearch pattern for list (text or regex)
include_contentNoInclude SKILL.md content in get operation
confirmNoConfirm delete operation (required for delete)

Implementation Reference

  • Main handler `skill_crud` dispatching to operation-specific private methods.
    async def skill_crud(input_data: SkillCrudInput) -> list[types.TextContent]:
        """Handle skill CRUD operations."""
        operation = input_data.operation
    
        try:
            if operation == "list":
                return await SkillCrud._handle_list(input_data)
            elif operation == "search":
                return await SkillCrud._handle_search(input_data)
            elif operation == "get":
                return await SkillCrud._handle_get(input_data)
            elif operation == "validate":
                return await SkillCrud._handle_validate(input_data)
            elif operation == "delete":
                return await SkillCrud._handle_delete(input_data)
            elif operation == "create":
                return await SkillCrud._handle_create(input_data)
            elif operation == "list_templates":
                return await SkillCrud._handle_list_templates(input_data)
            else:
                return [
                    types.TextContent(
                        type="text",
                        text=f"Unknown operation: {operation}. Valid operations: create, list, search, get, validate, delete, list_templates",
                    )
                ]
        except Exception as e:
            return [types.TextContent(type="text", text=f"Error: {str(e)}")]
  • Pydantic input schema `SkillCrudInput` used by the tool.
    class SkillCrudInput(BaseModel):
        """Unified input for skill CRUD operations."""
    
        operation: str = Field(
            description="Operation to perform: 'create', 'list', 'get', 'validate', 'delete'"
        )
        skill_name: Optional[str] = Field(
            default=None, description="Name of the skill (required for get, validate, delete, create)"
        )
        description: Optional[str] = Field(
            default=None, description="Skill description (optional for create)"
        )
        template: Optional[str] = Field(
            default="basic",
            description="Template to use for create: 'basic', 'python', 'bash', 'nodejs'",
        )
        search: Optional[str] = Field(
            default=None, description="Search pattern for list (text or regex)"
        )
        include_content: bool = Field(
            default=False, description="Include SKILL.md content in get operation"
        )
        confirm: bool = Field(
            default=False, description="Confirm delete operation (required for delete)"
        )
  • Tool definition including name, description, and inputSchema reference.
        def get_tool_definition() -> list[types.Tool]:
            """Get tool definition."""
            return [
                types.Tool(
                    name="skill_crud",
                    description="""Unified CRUD tool for skill management.
    
    IMPORTANT NOTES:
    - Skills are stored in ~/.skill-mcp/skills directory
    - All file paths in responses are relative to the skill directory (e.g., 'main.py', not full paths)
    - To execute scripts, use the 'run_skill_script' tool, NOT external bash/shell tools
    
    **Operations:**
    - **create**: Create a new skill with templates (basic, python, bash, nodejs)
    - **list**: List all skills with optional search (supports text and regex)
    - **search**: Search for skills by pattern (text or regex)
    - **get**: Get detailed information about a specific skill
    - **validate**: Validate skill structure and get diagnostics
    - **delete**: Delete a skill directory (requires confirm=true)
    - **list_templates**: List all available skill templates with descriptions
    
    **Examples:**
    ```json
    // List available templates
    {"operation": "list_templates"}
    
    // Create a Python skill
    {"operation": "create", "skill_name": "my-skill", "description": "My skill", "template": "python"}
    
    // List all skills
    {"operation": "list"}
    
    // Search skills by text
    {"operation": "search", "search": "weather"}
    
    // Search skills by regex pattern
    {"operation": "search", "search": "^api-"}
    
    // Get skill details
    {"operation": "get", "skill_name": "my-skill", "include_content": true}
    
    // Validate skill
    {"operation": "validate", "skill_name": "my-skill"}
    
    // Delete skill
    {"operation": "delete", "skill_name": "my-skill", "confirm": true}
    ```""",
                    inputSchema=SkillCrudInput.model_json_schema(),
                )
            ]
  • MCP server registration: adds skill_crud to list_tools via get_tool_definition()
    @app.list_tools()  # type: ignore[misc]
    async def list_tools() -> list[types.Tool]:
        """List available tools."""
        tools = []
        tools.extend(SkillCrud.get_tool_definition())
        tools.extend(SkillFilesCrud.get_tool_definition())
        tools.extend(SkillEnvCrud.get_tool_definition())
        tools.extend(ScriptTools.get_script_tools())
        return tools
  • MCP server call_tool dispatch: handles calls to skill_crud tool.
    if name == "skill_crud":
        skill_input = SkillCrudInput(**arguments)
        return await SkillCrud.skill_crud(skill_input)
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden of behavioral disclosure. It successfully describes key behaviors: skills are stored in a specific directory (~/.skill-mcp/skills), file paths in responses are relative, delete requires confirmation, and it distinguishes between operations like list vs search. However, it doesn't mention rate limits, error handling, or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (unified purpose, important notes, operations list, examples). While comprehensive, it's appropriately sized for a multi-operation tool. The examples section is extensive but necessary to demonstrate the various operation patterns. Some redundancy exists between the operations list and examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 7-parameter tool with no annotations and no output schema, the description does a good job covering operations, usage guidelines, and examples. It explains the tool's scope and relationship to siblings. However, without output schema, it doesn't describe return values or error formats, leaving some uncertainty about what to expect from operations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds some value by grouping parameters under operations in the examples section, showing which parameters are used together. However, it doesn't provide additional semantic context beyond what's already documented in the schema descriptions for each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this is a 'Unified CRUD tool for skill management' and enumerates seven specific operations (create, list, search, get, validate, delete, list_templates). It distinguishes itself from sibling tools by explicitly mentioning 'run_skill_script' as the alternative for execution and not using external bash/shell tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool versus alternatives ('To execute scripts, use the 'run_skill_script' tool, NOT external bash/shell tools'). It also includes important notes about file path conventions and storage location, and the examples section demonstrates proper usage patterns for each operation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fkesheh/skill-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server