Reasoning Protocols

Use this agent when executing the adversarial-cycle protocol to stress-test a claim or decision through structured conclusion, counter-claim, response cycles.

Use this agent when executing the assumption-surfacing protocol to audit the assumption foundation underlying a decision. Surfaces hidden assumptions, assesses fragility with quality gating, and builds an epistemic dependency graph.

Use this agent for targeted domain knowledge acquisition. Spawned by protocol agents (especially assumption-surfacing Phase 5) to fill domain knowledge gaps with source-traceable findings.

Use this agent when executing the downstream-forecasting protocol to trace cascade effects of a decision through downstream dependents with severity-gated termination and amplification detection.

Use this agent when executing the plan-review protocol to critique a plan, spec, or architecture decision before committing to implementation. Surfaces invalid assumptions, missing edge cases, underspecified integrations, and over-engineering.

Stress-test claims via structured conclusion, counter-claim, response cycles. Use when you need to validate a decision, challenge an argument, or verify that a conclusion survives scrutiny. Trigger phrases - "stress-test this", "challenge this claim", "validate this decision", "adversarial review".

Audit the assumption foundation underlying a decision. Surfaces hidden assumptions, assesses fragility with quality gating, builds an epistemic dependency graph, and produces a unified inventory tagged by epistemic status. Trigger phrases - "what assumptions are we making", "assumption audit", "what could break", "hidden dependencies", "fragility assessment".

Trace cascade effects of a decision through downstream dependents with severity-gated termination and amplification detection. Use when you need to forecast impact, trace consequences, or assess what breaks downstream. Trigger phrases - "what are the downstream effects", "impact analysis", "what breaks if we do this", "cascade effects".

Critique a plan, spec, or architecture decision before committing to implementation. Spawns an adversarial reviewer agent to surface invalid assumptions, missing edge cases, underspecified integrations, and over-engineering. Trigger phrases - "review this plan", "critique this spec", "challenge this design before I build it", "adversarial plan review", "stress-test this plan".

This skill should be used when deep analytical reasoning is required, particularaly when there are identifiable factor "groupings" that would benefit from scope isolation (signal clarity) or sequential ordering (dependent analysis).

3 hooks across 1 event