local-skills-mcp and skill-mcp

These are ecosystem siblings, as the "local-skills-mcp" server (A) enables agents to use skills from the local filesystem via the MCP protocol, which is then leveraged by the "skill-mcp" platform (B) to programmatically manage and execute skills for LLMs through any MCP-compatible client.

local-skills-mcp
55
Established
skill-mcp
48
Emerging
Maintenance 10/25
Adoption 11/25
Maturity 18/25
Community 16/25
Maintenance 6/25
Adoption 11/25
Maturity 18/25
Community 13/25
Stars: 20
Forks: 6
Downloads: 140
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 25
Forks: 4
Downloads: 63
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No risk flags

About local-skills-mcp

kdpa-llc/local-skills-mcp

Universal MCP server enabling any LLM or AI agent to utilize expert skills from your local filesystem. Reduces context consumption through lazy loading. Works with Claude, Cline, and any MCP-compatible client.

Implements stdio transport with automatic skill discovery across multiple configurable directories, aggregating skills from built-in sources, global paths, project-specific locations, and custom environment variables. Features hot-reload capability for instant skill updates without server restart, and uses lazy-loaded YAML frontmatter metadata (~50 tokens per skill) to minimize context overhead while deferring full skill content retrieval on-demand. Exposes a single `get_skill` tool to any MCP-compatible client, enabling skill reuse across Claude, Cline, Continue.dev, and custom AI agents regardless of underlying LLM.

About skill-mcp

fkesheh/skill-mcp

LLM-managed skills platform using MCP - create, edit, and execute skills programmatically in Claude, Cursor, and any MCP-compatible client without manual file uploads.

# Technical Summary Provides a 22-module MCP server that enables LLMs to unify multiple skills in single code executions through cross-skill imports and automatic dependency/environment aggregation—achieving 98.7% token efficiency gains by following Anthropic's MCP code-execution pattern. Features CRUD operations for skill management stored in `~/.skill-mcp/skills/`, with support for Python/Bash script execution using PEP 723 inline dependencies and per-skill `.env` files. Architecture remains client-agnostic via standard MCP protocol, compatible with Claude Desktop, Cursor, claude.ai, and any MCP-compatible application without vendor lock-in.

Related comparisons

local-skills-mcp and skillz local-skills-mcp and skillboss-skills local-skills-mcp and skillboss-skills local-skills-mcp and mdskills local-skills-mcp and pm-skills-mcp local-skills-mcp and cookiy-skill

Scores updated daily from GitHub, PyPI, and npm data. How scores work