Skill Loader MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SKILLS_SH_API_KEY | No | API key for skills.sh authenticated endpoints. Required only for list_skills and get_leaderboard. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_skillsA | List all available skills from skills.sh with pagination |
| search_skillsB | Search for skills by keyword |
| get_leaderboardB | Get trending or top-installed skills |
| fetch_skillA | Fetch raw skill content from GitHub |
| validate_skillB | Validate skill content for security issues |
| convert_to_steeringB | Convert skill to Kiro steering file format |
| convert_to_powerC | Convert skill to Kiro power format |
| import_skillB | Complete import workflow (fetch + validate + convert) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct action: listing, searching, fetching, validating, converting to specific formats, and importing. Even the two conversion tools are clearly separated by their output format. The import tool is a higher-level workflow that subsumes fetch/validate/convert, but its purpose is distinct and well-described.
All tool names follow a consistent verb_noun pattern with snake_case (list_skills, search_skills, get_leaderboard, fetch_skill, validate_skill, convert_to_steering, convert_to_power, import_skill). The pattern is uniform and predictable.
With 8 tools, the server is well-scoped for its purpose of discovering, fetching, validating, converting, and importing skills. Each tool has a clear role, and the count is within the ideal range for a focused utility server.
The tool surface covers the full workflow: discovery (list, search, leaderboard), retrieval (fetch), validation, conversion (both formats), and a combined import path. No obvious gaps exist for the domain of loading and transforming skills from an external registry.