← ClaudeAtlas

llm-councillisted

Use when a question is high-stakes, contested, open-ended, or benefits from more than one model's judgment and you want cross-model deliberation instead of a single answer. Triggers include the user asking for a "council", "panel", "multiple models", "second opinions", "ensemble", "deliberate", "have the models review each other", or wanting the most reliable answer to a hard question. Based on Andrej Karpathy's llm-council (github.com/karpathy/llm-council).
ssubbotin/kaggle-research-skills · ★ 0 · AI & Automation · score 69
Install: claude install-skill ssubbotin/kaggle-research-skills
# LLM Council ## Core principle One model answering alone has one set of blind spots. A **council** dispatches the same question to several independent models, has them **anonymously peer-review and rank** each other's answers, then a **chairman** synthesizes a single final response from the collected answers and rankings. The value comes from three things a single call can't give you: **independence** (answers formed without seeing each other), **anonymized cross-critique** (each model judges the substance, not the brand), and **synthesis** (the final answer is built from the best of all, not any one). Source pattern: Andrej Karpathy's `llm-council` (github.com/karpathy/llm-council) — a local app with the identical three-stage flow. This skill adapts it to run inside Claude Code using real agents and real model diversity. ## When to use / when NOT to use **Use for:** hard technical judgment calls, design trade-offs with no clear winner, factual questions where being wrong is costly, "which of these approaches is best", forecasts/estimates, anything where you'd want a second and third opinion. Also whenever the user explicitly asks for a council/panel/multiple models. **Do NOT use for:** simple lookups, mechanical edits, anything with one correct answer you can verify directly, or latency/cost-sensitive tasks. A council is 3–5× the tokens and wall-clock of a single answer — spend it only when the extra reliability is worth it. ## The three stages (do not skip or merge