agentskill-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_skillsC | Search for AI agent skills on agentskill.sh. Returns matching skills with name, description, rating, and install count. |
| get_skillB | Get full details for a specific skill including its SKILL.md content, security info, and metadata. |
| install_skillC | Install a skill from agentskill.sh to the local skills directory. Downloads the SKILL.md file and any associated files. |
| get_trendingC | Get trending and popular skills on agentskill.sh. |
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 4 tools
Each tool has a clearly distinct purpose with no overlap: get_skill retrieves detailed information for a specific skill, get_trending lists popular skills, install_skill handles installation, and search_skills performs keyword-based searches. The descriptions reinforce these distinct roles, making misselection unlikely.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., get_skill, install_skill). The verbs (get, get, install, search) are appropriate and predictable, creating a coherent naming convention throughout the set.
With 4 tools, this server is well-scoped for its purpose of managing AI agent skills. Each tool serves a clear and necessary function (discovery, retrieval, installation), and none feel redundant or missing, making the count appropriate for the domain.
The tool set covers core workflows for skill discovery and installation effectively, including search, trending, detailed retrieval, and installation. A minor gap exists in lifecycle management, such as updating or uninstalling skills, but agents can work around this with the provided tools for most use cases.