# Knowledge Source Router > Determines which region-specific knowledge source(s) to search based on the user's location. You MUST invoke this skill BEFORE calling the KnowledgeSearch tool, and pass the chosen source(s) as its `sources` parameter. - Skill: `kody-w/knowledge-source-router` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add kody-w/knowledge-source-router` - Raw SKILL.md: https://api.skillmd.com/api/skills/kody-w/knowledge-source-router/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: kody-w (https://skillmd.com/u/kody-w) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/kody-w/knowledge-source-router --- Pick the correct region-specific knowledge source(s) for a query based on the **user's location**, so answers are grounded in content that is accurate for where the user is. Always do this BEFORE calling the `KnowledgeSearch` tool, and pass the chosen source(s) as the `sources` parameter of that call — on every knowledge-grounded question. Policies, benefits, pricing, legal/compliance, support hours, and product availability frequently differ by country or region, so read from the source that matches the user's location before answering. ## Available sources | Source | Use when the user is located in... | | --- | --- | | `Global` | Any location, for content that is the same everywhere (fallback / default). | | `Americas` | United States, Canada, Mexico, Central & South America. | | `EMEA` | Europe, the Middle East, and Africa. | | `APAC` | Asia, Australia, and the Pacific. | ## Run this — do not improvise This capability's deterministic implementation is a RAPP single-file agent, linked beside this file as `knowledge_source_router_agent.py` and embedded as the fenced Python below (sha256 7852acf6808b8095…; a byte-exact copy is also vaulted in the capsule comment at the end of this file). On a host with sandbox execution, run the linked file directly — if it is missing, write the fence contents verbatim to `knowledge_source_router_agent.py` first: ```bash python3 knowledge_source_router_agent.py '{"key": "value"}' # arguments as one JSON object echo '{"key": "value"}' | python3 knowledge_source_router_agent.py # or on stdin python3 knowledge_source_router_agent.py --tool # emit the JSON tool contract ``` Treat stdout as a tool result. If it reports missing or unresolved inputs, stop and collect them. If it returns `steps`, execute those steps in order exactly as returned; if it returns `instructions`, follow them with the supplied inputs. Otherwise use the result verbatim. Do not invent behavior beyond that output. On a host without code execution, treat the Parameters schema and the code below as the exact specification and never paraphrase a step. Never edit inside the generated markers; a converter-equipped host can instead restore the original file checksum-verified with the installed `rapp-agent-converter/scripts/toast.py convert SKILL.md --to agent`. ```python # rapp:deterministic """KnowledgeSourceRouter -- Determines which region-specific knowledge source(s) to search based on the user's location. You MUST invoke this skill BEFORE calling the KnowledgeSearch tool, and pass the chosen source(s) as its `sources` parameter. Generated by the rapp skill from knowledge-source-router. The RCI capsule at the bottom of this file carries the full original; `toast.py convert` restores it byte-exact.""" import json import re import sys try: from agents.basic_agent import BasicAgent except ImportError: # running OUTSIDE a brainstem -- stay executable anyway. class BasicAgent: # noqa: D101 - minimal stand-in, same contract def __init__(self, name=None, metadata=None): if name: self.name = name if metadata: self.metadata = metadata def perform(self, **kwargs): return "Not implemented." def system_context(self): return None def to_tool(self): return {"type": "function", "function": { "name": self.name, "description": self.metadata.get("description", ""), "parameters": self.metadata.get("parameters", {})}} # The procedural layer, verbatim from the source capability. INSTRUCTIONS = "Pick the correct region-specific knowledge source(s) for a query based on the\n**user's location**, so answers are grounded in content that is accurate for\nwhere the user is. Always do this BEFORE calling the `KnowledgeSearch` tool, and\npass the chosen source(s) as the `sources` parameter of that call — on every\nknowledge-grounded question. Policies, benefits, pricing, legal/compliance,\nsupport hours, and product availability frequently differ by country or region,\nso read from the source that matches the user's location before answering.\n\n## Available sources\n| Source | Use when the user is located in... |\n| --- | --- |\n| `Global` | Any location, for content that is the same everywhere (fallback / default). |\n| `Americas` | United States, Canada, Mexico, Central & South America. |\n| `EMEA` | Europe, the Middle East, and Africa. |\n| `APAC` | Asia, Australia, and the Pacific. |" # Ordered commands lifted verbatim from the capability's own documentation. STEPS = [] class KnowledgeSourceRouterAgent(BasicAgent): def __init__(self): self.name = 'KnowledgeSourceRouter' self.metadata = { "name": "KnowledgeSourceRouter", "description": "Determines which region-specific knowledge source(s) to search based on the user's location. You MUST invoke this skill BEFORE calling the KnowledgeSearch tool, and pass the chosen source(s) as its `sources` parameter.", "parameters": { "type": "object", "properties": {}, "required": [] } } super().__init__(name=self.name, metadata=self.metadata) def perform(self, **kwargs): # toaster:generated-perform return json.dumps({"status": "ok", "instructions": INSTRUCTIONS, "inputs": kwargs, "note": "Prose-only capability: follow INSTRUCTIONS " "with the given inputs."}, indent=2) if __name__ == "__main__": # echo '{"arg": "value"}' | python3 knowledge_source_router_agent.py # python3 knowledge_source_router_agent.py '{"arg": "value"}' # python3 knowledge_source_router_agent.py --tool # emit the JSON tool contract _a = sys.argv[1:] if _a and _a[0] == "--tool": print(json.dumps(KnowledgeSourceRouterAgent().to_tool(), indent=2)) else: _raw = _a[0] if _a else (sys.stdin.read().strip() or "{}") print(KnowledgeSourceRouterAgent().perform(**json.loads(_raw))) # rci-capsule:v1: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 ```