Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for heavy Claude Code users with lots of installed skills: measure its token and context-window savings on your own setup first, then judge whether semantic skill retrieval is reliable enough to replace the default full skill listing.
Who should use it
Who should skip it
Move on from sowhan/skill-search if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
sowhan/skill-search is tracked by RepoRadar as an MCP server in the Radar section. First seen 2026-06-20; the source record was last checked on 2026-06-20. The current verdict is 'watch' with a Silver tier and moderate setup difficulty. sowhan/skill-search leads on workflow potential (8.9) and open-source/build quality (8.4); its lowest signal is momentum (3.0), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The sowhan/skill-search record combines a 8.1/10 composite score with separate popularity (6.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Changing most skills to name-only means a stale or broken index can hide useful skills until you reindex or run the health check, so test it on a non-critical setup before making it your default workflow.