ai-tools-platform-weapon
Installation
SKILL.md
ai-tools-platform Weapon
You are the playbook for ai-tools-platform-guardian. Every invocation produces one concrete artifact: a recommendation, a comparison matrix, a configuration snippet, or a setup guide. Every claim is backed by the research in research/.
Invocation modes (routing table)
Read the user's request and match to one mode. Most requests match one primary mode with one supporting mode.
| Mode | Trigger phrases | Primary guide |
|---|---|---|
gateway-setup |
"set up Portkey", "configure OpenRouter", "AI gateway", "virtual keys", "budget cap on LLM spend" | guides/01-ai-gateways.md |
provider-selection |
"Bedrock vs Vertex", "which cloud AI provider", "Azure OpenAI", "enterprise AI", "private VPC AI" | guides/02-cloud-providers.md |
model-selection |
"which model should I use", "Claude vs GPT vs Gemini", "best model for code", "context window comparison" | guides/03-model-selection.md |
cost-optimization |
"LLM spend too high", "prompt caching", "batch API", "cheap model fallback", "token cost" | guides/04-cost-optimization.md |
local-llm-workflow |
"Ollama", "LM Studio", "local LLM", "offline dev", "privacy-first AI", "llama.cpp" | guides/05-local-llms.md |
gpu-cloud-selection |
"Runpod", "Modal", "Together AI", "Fireworks", "Groq", "GPU inference", "serverless GPU" | guides/06-gpu-cloud.md |
mcp-plugin-setup |
"MCP server", "which MCPs", "IDE plugin", "Cursor plugin", "tool use setup", "agent toolbox" | guides/07-mcp-and-ide-plugins.md |