$ loading_
Match tasks to skills, track performance, detect gaps, and discover new skills.
The available material is sparse, but this MCP tool is open-source under Apache 2.0, requires no credentials, and declares no remote endpoints, with no clear high-risk red flags. Caution is still warranted because it is flagged as code-executing, and its description mentions discovering skills from external sources, so actual runtime boundaries and data flows should be verified.
The material explicitly states that no keys or environment variables are required. No API tokens, account credentials, or other sensitive authentication requirements are disclosed, so credential exposure risk appears low.
Although no remote endpoints are declared, the feature description includes 'discover new skills from external sources,' which suggests possible external retrieval or network use not detailed in the material. There is no clear evidence of data exfiltration to unknown endpoints, but network behavior lacks transparency.
The objective checks flag this tool as executes-code, indicating it may run code or processes locally; this is a common capability for MCP tools. The material does not show requests for unusual system privileges or execution unrelated to its stated purpose, so no high-risk red flag is evident.
The description references task matching, effectiveness tracking, and skill discovery, suggesting it may process task content, skill metadata, or local configuration, but the missing README prevents confirmation of the exact read/write scope. No explicit overbroad authorization or sensitive directory access is disclosed, but data boundaries are not clear.
Positive factors include being open-source, auditable, and licensed under Apache 2.0, which materially lowers supply-chain risk. However, it comes from a third-party registry, has 0 stars, and shows unknown maintenance status, indicating limited evidence of maturity and ongoing upkeep.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "skill-curator-mcp" yet — see the docs or source repo.
Based on the following task description, semantically match the most suitable skill from the existing skill library and explain why: Automatically categorize customer feedback, summarize it, and generate a weekly report.
A ranked list of relevant skill candidates with match scores and reasons for fit.
Analyze the past month's task execution data for each skill, including success rates, failure reasons, and coverage blind spots, then identify the skill types most urgently needed.
An effectiveness analysis, key gap summary, and recommended new or improved skill areas.
Discover new automation testing skills from specified public repositories, documentation sites, and community resources, and shortlist candidates worth adding to the skill library.
A shortlist of new skill candidates with source links, use cases, and adoption recommendations.
Search, discover, and recommend skills, tools, agents, and MCP servers.
Discover, install, and manage curated skills for any MCP-compatible agent.
Search, retrieve, and evolve AI skill capsules across many domains.
Expose Agent Skills as MCP tools for coding agents to discover and activate instructions.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Discover, install, and manage skills.sh skills directly through AI agents.