Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Design enterprise-grade agent systems with Microsoft's agent framework patterns: role separation, workflow control, policy boundaries, and observability. Use when users need robust organizational agen
Imported from akillness/jeo-skills (.agent-skills/microsoft-agent-framework/SKILL.md). Install upstream with npx skills add akillness/jeo-skills --skill microsoft-agent-framework. Copyright stays with the author.
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install microsoft-agent-framework and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "akillness-jeo-skills-microsoft-agent-framework",
"kind": "skill",
"name": "microsoft-agent-framework",
"description": "Design enterprise-grade agent systems with Microsoft's agent framework patterns: role separation, workflow control, policy boundaries, and observability. Use when users need robust organizational agent workflows, governance, and maintainable multi-agent architecture.",
"publisher": "akillness",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"agentic-ai",
"microsoft",
"enterprise",
"governance",
"orchestration",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Design enterprise-grade agent systems with Microsoft's agent framework patterns: role separation, workflow control, policy boundaries, and observability. Use when users need robust organizational agent workflows, governance, and maintainable multi-agent architecture."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/akillness/jeo-skills",
"path": ".agent-skills/microsoft-agent-framework/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/akillness/jeo-skills/blob/HEAD/.agent-skills/microsoft-agent-framework/SKILL.md",
"key": "akillness/jeo-skills/.agent-skills/microsoft-agent-framework/SKILL.md"
},
"allowed_tools": [
"Bash",
"Read",
"Write",
"Edit",
"Grep",
"Glob"
]
},
"instructions": "# Microsoft Agent Framework\n\n## When to use this skill\n- 조직/팀 단위로 유지되는 에이전트 시스템 설계가 필요할 때\n- 책임분리, 거버넌스, 감사 가능한 실행로그가 필요할 때\n- 단발성 데모가 아니라 운영/확장 가능한 구조가 필요할 때\n\n## Instructions\n\n### Step 1) 역할 분리 모델 확정\n- Planner / Executor / Reviewer / Approver 역할을 분리\n- 역할 간 입력/출력 계약(스키마) 먼저 정의\n- 승인 단계(Approver)가 필요한 작업군을 선별\n\n### Step 2) 제어흐름 정의\n- 동기/비동기 경로 구분\n- 실패 시 보상 트랜잭션 또는 롤백 전략 설정\n- SLA(응답시간/재시도/중단조건) 명문화\n\n### Step 3) 정책 경계 설정\n- 데이터 접근 범위(읽기/쓰기/외부전송) 역할별 제한\n- 민감정보 마스킹/로그 보존 정책 적용\n- 자동 실행 범위와 인간 승인 범위를 분리\n\n### Step 4) 운영 관측성 구축\n- 단계별 trace id 부여\n- 실패 원인 분류(정책,도구,모델,입력)\n- 주기적 회귀 점검용 시나리오 유지\n\n## Examples\n- 요청:",
"cost": {
"context_tokens": 225
}
}
Fetch it by URL: GET /api/v1/registry/akillness-jeo-skills-microsoft-agent-framework/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
