linkly-ai-skills
MCP ServerLinklyAI/linkly-ai-skills
This skill enables AI agents to search, browse, read, and take notes across local and cloud documents indexed by Linkly AI using either a CLI or MCP tools.
Overview
The Linkly AI document search skill provides a robust interface for querying, locating, and reading various file formats (including PDFs, Markdown, Word, PowerPoint, and media) stored locally or in connected cloud libraries. It features progressive disclosure workflows—such as path finding, directory listing, full-text searching, structural outlining, and local Markdown note-taking—adapted to either CLI or Model Context Protocol (MCP) environments with connection mode management.
Capabilities
- ▸Full-text document search
- ▸Container and folder enumeration
- ▸Fuzzy path finding for local and cloud targets
- ▸Document structural outlining and paginated reading
- ▸Local Markdown note capture and listing
- ▸Multi-mode environment detection (CLI vs MCP, local vs remote endpoints)
Best for
Searching user local and cloud documents for specific topics or keywords, Listing and exploring files within specific folders, knowledge libraries, or notes, Reading and extracting outlines from indexed documents like PDFs, text files, and presentations, Capturing and managing quick local Markdown notes
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
Interacts with local file systems and external cloud endpoints through configured API tokens and local ports. Connection state determines access privileges to local vs. cloud data.
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.