local-skills-mcp and pm-skills-mcp
These two tools are complements, as the universal MCP server (A) provides the infrastructure to enable LLMs to utilize expert skills, while the open-source MCP with pre-packaged product management skills (B) offers a specific set of skills that could be served by such an infrastructure.
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 pm-skills-mcp
product-on-purpose/pm-skills-mcp
Open-source MCP with /pm-skills included 24 best-practice product management skills plus workflows, instantly accessible to any AI via Model Context Protocol.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work