ard-connectors
ards-project/ard-connectors
Enables AI assistants to search decentralized Agentic Resource Discovery (ARD) catalogs for tools, skills, and MCP servers. It presents ranked search results without automatically installing any resources.
14 10No licenseUpdated 2026-07-09
60
GoodOverview
This skill acts as a client-side interface for querying ARD-compliant discovery services like GitHub Agent Finder or Hugging Face Discover. It manages a persistent configuration file to remember the user's preferred search catalog, queries the remote endpoint via POST requests, and presents a curated list of relevant agentic capabilities with explicit installation instructions rather than performing automatic installations.
Capabilities
- ▸Persistent configuration management for discovery endpoints
- ▸Interactive menu for selecting and switching agent search providers
- ▸HTTP-based querying of ARD search APIs
- ▸Presentation of ranked resource results with manual installation guidance
Best for
Searching for specialized MCP servers to add to an AI development environment, Discovering community-built skills and tools for specific coding or automation tasks, Switching between different public and private agent discovery services
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
60Task usefulness20%77 → +15.4
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
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
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
Documentation12%38 → +4.6
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
Security15%80 → +12.0
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
Originality10%85 → +8.5
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
Popularity8%39 → +3.1
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
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
Weighted total71.1 / 100
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
The skill enforces explicit user consent before installing or connecting any discovered resources, mitigating risks associated with malicious code execution. Relevance scores are explicitly noted as non-trust indicators.
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.