| name | native-agent-deliberation |
| description | Frame consequential or ambiguous decisions through distinct evidence-backed viewpoints, tradeoffs, and dissent. Use for brainstorming among competing strategies, architecture choices, risk review, or a decision whose assumptions should be challenged before execution. |
Native Agent Deliberation
Set The Decision
- State one decision question.
- List hard constraints, success criteria, and decision deadline.
- Separate known evidence from assumptions.
- Identify what would change the decision.
- Keep implementation outside scope unless the user also authorizes it.
Gather Viewpoints
Load native-subagents-first before using native agents. Follow it as the sole lifecycle, model, budget, resume, and tool contract.
Choose two to four genuinely distinct viewpoints, such as:
- evidence and constraints,
- viable options and tradeoffs,
- dissent and failure modes,
- reversibility and verification.
Give each viewpoint a bounded question and only the evidence it needs. Ask for:
- a concise recommendation,
- supporting evidence,
- the strongest counterargument,
- confidence and missing facts,
- a condition that would reverse the recommendation.
Use the tool's structured role controls when needed. Do not put role or agent_type markers in prompt text.
Synthesize
- Verify material claims against source evidence.
- Compare options against the same criteria.
- Preserve disagreements instead of manufacturing consensus.
- Distinguish evidence, inference, and preference.
- Recommend one path, defer, or ask for one blocking fact.
- Name the strongest dissent and what would change the decision.
- Give the next concrete action without starting unrequested implementation.
Return
- Decision and recommendation.
- Evidence that drove it.
- Strongest tradeoff or dissent.
- Uncertainty and reversal condition.
- Next action.
Do not use this skill for generic subagent execution, routine implementation fanout, or validation.
