Ross ROSS = Recommend OSS · open-source software intelligence for agents

aiwithremy/claude-skills-llm-council

LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review observed · 2026-08-28

github.com/aiwithremy/claude-skills-llm-council observed · 2026-08-28

Health v2 · maintenance only

50/100

  • Activity 79
  • Release rhythm 35
  • Longevity 9

Flags: no_releases young no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 130
  • days_rel: n/a
  • days_push: 130
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1741 stars · 161 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Claude Code skill that runs a user's question through five independent AI advisors who peer-review each other's answers, then synthesizes a final verdict via a chairman role. It is based on Andrej Karpathy's LLM Council methodology and installs as a SKILL.md instruction set for Claude Code and Claude Cowork.

Use cases

  • get multiple AI perspectives on a tough business decision
  • compare five expert opinions before launching a product or pricing a course
  • have AI advisors critique each other's reasoning on a strategic pivot
  • stress-test landing page copy or positioning angles
  • get a synthesized recommendation showing where advisors agree and disagree
  • avoid single-model bias when facing high-stakes judgment calls

When to choose

  • you use Claude Code or Claude Cowork and face genuinely uncertain decisions
  • you want multi-model-style deliberation without managing multiple API calls yourself
  • the cost of a bad call is high and you want peer-reviewed perspectives
  • you want a zero-terminal, copy-paste skill installation

When to avoid

  • you need a factual answer with one correct response
  • the task is content creation or summarization rather than judgment
  • you don't use Claude Code or Claude Cowork
  • you need a production software library with an API rather than a prompt-based skill
  • you require a permissively licensed or formally maintained package (no license is specified)

Facets

plugin · maturity active

agent-framework prompt-engineering llm-inference artificial-intelligence large-language-models developer-tools cli claude-code claude-skill llm-council decision-support peer-review multi-perspective no-code-install ai-agents web-server

1 source

Member repositories

RepositoryRoleHealth v2
aiwithremy/claude-skills-llm-councilmain50

For agents

markdown · JSON · MCP: product_card(name="aiwithremy/claude-skills-llm-council")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem