What problem does it solve?
After routing decides which agent handles a task, a coordinator still needs to decide how much ceremony that task deserves. This Skill provides the complete decision table for choosing between Direct, Lightweight, Standard, and Full response modes, preventing both over-engineering simple requests and under-serving complex ones.
Core Features & Use Cases
- Four-tier decision table: Maps task complexity (status checks, single-file edits, normal tasks, multi-agent work) to Direct, Lightweight, Standard, or Full modes with target latency for each.
- Exemplar prompts per mode: Concrete example requests showing when to answer directly, spawn one lightweight agent, run full ceremony, or fan out in parallel.
- Lightweight spawn template: A ready-to-use minimal agent spawn prompt that skips charter, history, and decisions reads for fast scoped tasks.
- Upgrade rules: Explicit guidance to bias toward higher tiers when uncertain and never downgrade mid-task.
- Use Case: A user asks "fix the typo in README" — the coordinator loads this skill, classifies it as Lightweight, and spawns a single agent with the minimal template instead of full ceremony.
Quick Start
Load this skill after routing a task to an agent and use its decision table to pick the right response mode for the request.
