skills-registry
MCP Servernikships/skills-registry
An integrated skill management ecosystem consisting of a Go CLI with a Charmbracelet TUI and a hosted Python MCP server for syncing and discovering AI skills across repositories.
Overview
The skills-registry tool bridges the gap between local AI agent skills and remote registries through a dual architecture. It features a Go-based CLI that provides an interactive terminal user interface, first-run wizard, and fast local git-mirror caching, alongside a hosted FastMCP server on Railway that provides read-only skill search and retrieval via OAuth and GitHub Apps.
Capabilities
- ▸First-run onboarding wizard with Charmbracelet TUI
- ▸Returning-user dashboard hub with card grid
- ▸Local shallow-clone git mirroring for fast registry reads
- ▸Headless commands and persistent JSON output flag
- ▸Hosted MCP server providing remote search and retrieval tools
Best for
Bootstrapping a new AI skill repository and publishing local dot-folder skills via a single git push., Interactively managing, syncing, and publishing AI agent skills using a terminal user interface., Connecting AI coding assistants like Codex to a remote skill registry using a streamable HTTP MCP server.
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Uses installation-scoped GitHub App tokens for secure API access and validates webhooks against delivery stores, avoiding local shell state exposure during remote operations.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.