llm-council
SolidProvider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.
Install
Quality Score: 86/100
Skill Content
Details
- Author
- rohitg00
- Repository
- rohitg00/pro-workflow
- Created
- 5 months ago
- Last Updated
- today
- Language
- JavaScript
- License
- None
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
llm-council
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
llm-council
Convene an internal "council" of distinct senior-engineer personas to analyze a problem, stress-test an approach, and produce an implementation plan before writing code — grounding the decision in up-to-date online research (current library/API versions, vendor pricing and limits, regulatory rules) rather than stale training data. Use this whenever the user is analyzing a system, weighing architectural or design trade-offs, planning a non-trivial feature or refactor, evaluating a library/tool/vendor choice, debugging something whose root cause is unclear, or asks to "think through", "plan", "analyze", "research", "review the approach for", or "figure out how to build" something — even if they don't say the word "council". Trigger it especially for decisions that are expensive to reverse (data models, API contracts, infra, auth, migrations) or that depend on external facts that may have changed. Do NOT trigger for trivial one-liners, straightforward lookups, or when the user just wants code written for an alre
council
Gathers N independent, decorrelated perspectives across model families (external CLIs when present, subagents when not) and arbitrates inline. Use when a decision needs genuine debate — not same-model echo — for critique, review, or judge calls. Honest about degradation: never claims 'consensus' from a single model family.