automation-shape-routing
FeaturedFront door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".
Install
Quality Score: 96/100
Skill Content
Details
- Author
- boshu2
- Repository
- boshu2/agentops
- Created
- 8 months ago
- Last Updated
- today
- Language
- Go
- License
- Apache-2.0
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
agent-routing
Decide which model (Haiku/Sonnet/Opus) and effort level each subagent gets, when to cascade cheap-first behind a verifier, and how to run improvement loops safely (evaluator-as-selector, stop on regression). Covers the Managed Agents effort mechanics (per-agent effort levels, cost lever) and how to watch a subagent fan-out stream live so loop and escalation gates have something to observe. Use when spawning subagents via the Agent or Workflow tools, when fanning out more than a handful of agents, or when the user asks which model or effort a task should route to. Routing heuristics grounded in measured calibration data (references/calibration-2026-07-15.md), not vibes; the Managed Agents API specifics are operational, not calibrated.
agent-runbook
Routing runbook for engineering tasks across the agent stack (ao spawn, GSD, OMC, /goal, /loop, /schedule, inline, codex, gemini, Claude Flow swarm). Use when uncertain which execution mode to choose, before any non-trivial action. Outputs a composed pipeline, not just one mode. Hard rules and gates live in global CLAUDE.md; this skill is the HOW for routing.
ai
Build model-powered behavior — model routing, context engineering, structured outputs, tools/MCP, agents, RAG, memory, evals, guardrails, and cost/observability — across chat, agent, RAG, batch, and multi-agent systems, any provider or language. Use to route a model, engineer context, build an agent or tool loop, add RAG or memory, write evals, or add guardrails. Not for system/threat design (→ architecture), serving or MCP hosting (→ backend), data pipelines (→ data), chat UI (→ frontend), independent QA (→ quality), deploy (→ operate), or deterministic workflows (→ automation).