agent-council
Agent Council: Role-Diverse Local Council
Execute this skill to run a local expert council using one runtime/model family with multiple specialized roles. Unlike deep-council (which composes multiple bridge/runtime councils and may also include model diversity), agent-council uses role-diverse expert PERSPECTIVES to catch:
- Shared assumptions that a single viewpoint misses
- Integration gaps between components
- Hidden failure modes through adversarial challenge
- Cross-domain implications no single expert catches
When to Use Agent Council
| Scenario | Use Agent Council | Use Deep Council |
|---|---|---|
| Need fast local role-diverse review | ✓ | Optional |
| Need phase-end closure artifact | ✓ | Optional for high-risk phases |
| Need each bridge/runtime to run its own local council | As child council | ✓ |
| Need runtime/toolchain diversity (Codex vs Claude Code vs OpenCode) | ✗ alone | ✓ |
| Need model diversity inside a bridge | ✗ alone | ✓ if bridge supports Model Council |
| Need cross-council debate | ✗ alone | ✓ |
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