AI agents の
Skill layer.
AI agent が適切な再利用可能 Skill を自動で発見、比較、インストールできるようにします。
Daily leaderboards
Skills moving now, ranked with evidence.
Daily snapshots combine capped activity signals, quality, trust, GitHub adoption, and real agent outcomes.
- 1web-automation
Scrapling
32 views, 2 install copies, and excellent quality signals.
70K stars507 events - 2data-analysis
Data Science For Beginners
3 views, 0 install copies, and 4 compares across 1 active days, with capped anti-spam weighting and 1 agent outcomes.
36K stars7 events / 1d - 3coding-agents
Gpt Pilot
30 views, 0 install copies, and excellent quality signals.
34K stars97 events - 4agent-frameworks
Claude Code Best Practice
23 views, 3 install copies, and excellent quality signals.
61K stars76 events - 5ml-automation
Ray
34 views, 1 install copies, and excellent quality signals.
43K stars81 events
Agent resolve
タスクを説明し、安全な Skill プランを得る。
API は Agent が動く前に、選択 Skill、代替案、ポリシー判断、監査メモ、インストール手順を返します。
タスク適合
96/100
Web 抽出ワークフローに推奨
メンテナンス
Active
Stars、更新、メタデータ、リポジトリ健全性
インストール確認
Ready
Agent 実行前の安全な次ステップ
Why OpenAgentSkill
Agent をランダムなディレクトリに送らない。
Skill レジストリは Agent が信頼できて初めて役に立ちます。OpenAgentSkill は散らばった GitHub プロジェクトを、ランキング、監査、インストール可能な能力に変換します。
- 01
タスクから Skill へ
Agent はカテゴリではなく意図から始めます。レジストリはジョブを選択 Skill、代替案、適合理由へ変換します。
- 02
インストール前の安全性
Stars、鮮度、品質スコア、リスク、準備状況を実行コマンドと並べて確認できます。
- 03
人は閲覧、Agent は API
人は索引を閲覧し、Agent は resolve、recommend、skill endpoints から同じ登録表を呼び出せます。
Registry response
一度の呼び出しで、順位付きのインストール経路。
{
"task": "analyze stock news",
"agent_decision": {
"recommended_skill": "Last30days Skill",
"install_command": "npx skills add ...",
"why_recommended": [
"matches research workflow",
"strong Trust Score",
"audit warnings included"
],
"risk_summary": {
"safety": "review before install",
"notes": ["network access", "verify sources"]
}
}
}Architecture
意図からインストールまでの 4 層。
OpenAgentSkill は静的リストではなく、Agent がファイル作成、ブラウザ操作、外部コード導入の前に呼べるレジストリループです。
Indexed
21,510
Signals
Fit · Risk
Surface
API · UI
- 01
Intent capture
A human or upstream agent describes the job in natural language.
Task · Agent · ContextIntent - 02
Recommendation engine
rankerSkills are ranked by workflow fit, maintenance, stars, and audit signals.
Fit · Quality · FreshnessRank - 03
Skill trust profile
Each candidate gets readiness notes, install commands, and review prompts.
Risk · Install · EvidenceAudit - 04
Agent install path
The registry returns the next action an agent can safely execute.
Codex · Claude Code · CursorInstall
Quickstart
From task description to install command.
- 01
Ask for a skill path
Resolve the task into one selected skill, alternatives, safety score, and install plan.
POST /api/agent/resolve - 02
Inspect the trust profile
Review fit, repository health, risks, and install readiness.
GET /api/agent/skills/crawl4ai - 03
Install in an agent workflow
Copy the command or hand it to Codex, Claude Code, Cursor, or a custom agent.
GET /api/skills/crawl4ai/install?format=text - 04
Automate discovery
Use the API as the registry layer behind your own agent runtime.
curl "https://www.openagentskill.com/api/agent/resolve?task=review+pull+requests&agent=codex"
Compare
OpenAgentSkill と他の Skill プラットフォームの違い。
普通のディレクトリは人が閲覧するものです。OpenAgentSkill は AI Agent が正しい Skill を自動で発見、比較、インストールするために作られています。
| Feature | OpenAgentSkill | skills.sh | agentskills.io | Native docs |
|---|---|---|---|---|
| Primary job | Recommend, compare, and install skills from one registry | Browse and install reusable agent skills | Define the open skill format and learning path | Explain skills inside each native agent platform |
| Agent-facing API | Yes - task-to-skill recommendations for agents | Directory and install workflow | Spec and documentation first | Platform-specific APIs and docs |
| Cross-agent positioning | Codex, Claude Code, Cursor, MCP-compatible agents, and custom tools | Open agent skills ecosystem | Open format for extending agents | Best for the vendor platform |
| Trust and audit signals | Stars, quality score, readiness notes, install review | Directory metadata | Metadata guidance in SKILL.md | Native platform controls |
| Best for | Letting an agent find the right skill automatically | Finding installable skills quickly | Learning or authoring the standard | Using skills in one product |
Comparison is based on each project's public positioning and documentation. The point is not that one project replaces another; OpenAgentSkill focuses on the registry and recommendation layer agents can call.
Workflow starts
Start from the job your agent needs to do.
Web scraping
Monitor pricing and extract tables
Coding agents
Inspect repos, patch bugs, verify changes
RAG workflows
Turn documents into grounded answers
Workflow automation
Connect repeated ops across tools
Skill layer
Registry for humans. Skill layer for agents.
Browse when you are exploring. Call the recommendation API when your agent needs to pick, compare, and install a skill automatically.