debate-protocol
Debate Protocol: Generic 5-Phase Adversarial Analysis
Execute this skill to run a structured adversarial analysis among domain experts and structural challengers, producing high-confidence findings through iterative challenge and synthesis.
What Debate Is For
Debate is NOT brainstorming and NOT round-table discussion. Debate is adversarial validation — the structured attempt to disprove each finding before accepting it as real.
The core problem debate solves: Domain experts find what they're looking for. A security expert finds security issues. A database expert finds schema problems. Left unchallenged, findings accumulate without any filter for whether they're actually real, actually severe, or actually the root cause. Debate applies that filter.
What debate produces that solo analysis cannot:
- Findings that survived an attack (higher confidence than ones that weren't challenged)
- Downgraded findings where the initial severity was an assumption, not evidence
- Withdrawn findings that were patterns, not problems
- New findings that only appear when you combine two domain experts' views
Brainstorm Is Related, But Not The Same
More from mikeng-io/agent-skills
perplexity
Optional AI-synthesized web search via Perplexity MCP. Returns AI-grounded answers with inline citations rather than raw search results — best for synthesis-heavy questions, current consensus queries, and cross-validation of research findings. Non-blocking — falls back to other search tools if unavailable.
10brave-search
Optional web search enrichment via Brave Search MCP. Provides web, news, and local search with an independent index (no Google dependency). Invokable standalone or called by deep-research, deep-explorer, or any skill needing web search. Non-blocking — falls back to other search tools if unavailable.
9deep-audit
Multi-agent standards and compliance auditing with pass/fail verdicts. Checks against security, accessibility, code standards, regulatory requirements, and performance benchmarks.
9deep-review
Multi-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.
8deep-research
Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform comprehensive research on any topic.
8context
Analyze conversation context to classify what is being discussed, detect relevant domains from domain-registry, and determine optimal routing (parallel-workflow vs debate-protocol vs deep-council). Can be invoked directly or called by other skills as a pre-flight step.
7