원클릭으로 Manus에서 모든 스킬 실행

agentic-rag-router

스타0

포크0

업데이트2026년 6월 10일 18:38

Choose the cheapest sufficient retrieval strategy for a query before answering. Use whenever the system has multiple retrievers (vector, hybrid, graph, metadata, summary) and needs to decide how to fetch evidence for a question. Trigger on any retrieval/QA task where query types are mixed.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

agentmc15

agentmc15/aesop

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

agentic-rag-router

The point of agentic RAG isn't "more agents" — it's adaptive retrieval: use the cheapest sufficient behavior for the query at hand. This skill is the router.

Routing rules

exact names / IDs / error codes / config keys / quoted strings → hybrid_search
simple conceptual / single-hop lookup → vector_search
relationship / dependency / impact / lineage / "connected to" → graph_search
scoped by region / tenant / version / date / department → metadata_filtered_search
broad summary / theme → hierarchical_summary_search
ambiguous wording → multi-query expansion
weak evidence after retrieval → corrective retry (regrade, switch retriever, decompose)
high-risk answer → add a critic/verification pass

Output (JSON, user-safe — no hidden chain-of-thought)

{"query_type": "...", "selected_tool": "...", "tool_args": {}, "decision_reason": "brief", "needs_fallback": false}

Notes

Don't answer the user here; only return the routing decision.
This is the runtime cousin of the comparison harness in evals/python/rag_compare/, which measures which strategy actually wins per query class at what cost/latency.

이 저장소의 다른 Skills

같은 저장소

lessons-loop

agentmc15/aesop

Capture a durable lesson every time the human corrects the agent, so the same mistake doesn't recur. Use immediately after any user correction, course-correction, or "no, do it this way". Also use at session start to load relevant past lessons. Trigger on corrections and on session start.

2026-07-120

spec-first

agentmc15/aesop

Turn a feature request or task into a written spec before any code is written. Use whenever the user asks to build, add, or implement something non-trivial (3+ steps or an architectural decision), or says "let's design", "write the spec", or "plan this". Produces the spec the human approves and the agent executes against.

2026-07-120

verify-loop

agentmc15/aesop

Prove a change works before calling it done — build, test, lint, smoke-check, and report pass/fail. Use after any code change, before any commit/PR, and as the self-verify step inside an autonomous loop. Trigger whenever the agent is about to claim a task is complete.

2026-07-120

tdd-workflow

agentmc15/aesop

Write a failing test first, then the minimum code to pass it. Use for any bug fix or new behavior.

2026-06-110

context-compaction

agentmc15/aesop

Keep a long agent session inside its context window without losing the plot. Use when a session is getting long, tool outputs are large, the agent starts "going off the rails" late in a task, or context usage is high. Trigger on big logs, long transcripts, or before a context-heavy step.

2026-06-100

llm-wiki

agentmc15/aesop

Incrementally compile messy source documents into a persistent, cross-linked Markdown knowledge base instead of re-reading raw docs every time. Use when the user has a pile of documents/notes/tickets and wants durable understanding, a project wiki, an onboarding doc, or asks "summarize everything we know about X" across many sources.

2026-06-100

name	agentic-rag-router
description	Choose the cheapest sufficient retrieval strategy for a query before answering. Use whenever the system has multiple retrievers (vector, hybrid, graph, metadata, summary) and needs to decide how to fetch evidence for a question. Trigger on any retrieval/QA task where query types are mixed.

agentic-rag-router

The point of agentic RAG isn't "more agents" — it's adaptive retrieval: use the cheapest sufficient behavior for the query at hand. This skill is the router.

Routing rules

exact names / IDs / error codes / config keys / quoted strings → hybrid_search
simple conceptual / single-hop lookup → vector_search
relationship / dependency / impact / lineage / "connected to" → graph_search
scoped by region / tenant / version / date / department → metadata_filtered_search
broad summary / theme → hierarchical_summary_search
ambiguous wording → multi-query expansion
weak evidence after retrieval → corrective retry (regrade, switch retriever, decompose)
high-risk answer → add a critic/verification pass

Output (JSON, user-safe — no hidden chain-of-thought)

{"query_type": "...", "selected_tool": "...", "tool_args": {}, "decision_reason": "brief", "needs_fallback": false}

Notes

Don't answer the user here; only return the routing decision.
This is the runtime cousin of the comparison harness in evals/python/rag_compare/, which measures which strategy actually wins per query class at what cost/latency.