Skill Management
This skill management server by fkesheh provides a complete system for organizing and executing Claude skills with per-skill environment variables and automatic dependency management. Built with Python and the MCP protocol, it stores skills in a structured directory format with SKILL.md metadata files, supports Python scripts with PEP 723 inline dependencies that auto-install via uv, and includes comprehensive file management tools for creating, reading, updating, and deleting skill files. The server features script execution with environment variable injection, security measures like path traversal prevention, and support for multiple script types including Python and shell scripts, making it useful for developers who want to build reusable automation workflows and maintain organized collections of executable skills.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/fkesheh/skill-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Skill Management from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.