Agent skill · Workflow & Productivity

llm-council

Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.

Nick44,086★ · +407/wk · 1 repos on radarProfile →
claude-codecodexcursorcan modify filesMIT
Install
npx skills add sickn33/agentic-awesome-skills --skill llm-council --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 20 KB
Bundled scripts: none
Declared author: DAIR.AI
Allowed tools: ReadWriteBashAskUserQuestion
Path: skills/llm-council/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 44,414 · +328 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# LLM Council (Fireworks AI) ## When to Use Use when this workflow matches the user request: Use this skill for its documented workflow. _Source: [dair-ai/dair-academy-plugins](https://github.com/dair-ai/dair-academy-plugins) (MIT)._ This skill implements Karpathy's LLM Council concept where multiple open-weight LLMs deliberate on a query, powered entirely by Fireworks AI: 1. **Phase 1**: All models respond to the query independently (parallel) 2. **Phase 2**: Models rank each other's anonymized responses 3. **Phase 3**: A Chairman LLM synthesizes the final answer All inference runs through **Fireworks AI** using open-weight models. The speed and pricing of Fireworks makes it practical to run multi-model deliberation that would be slow or expensive on other providers. ## CRITICAL RULES 1. **ALWAYS use AskUserQuestion** to let the user select council models (multiselect) and the Chairman model 2. **ALWAYS save raw responses to files** - never summarize or truncate API outputs 3. **ALWAYS show full transparency** - display all individual responses, all rankings, AND the final synthesis 4. **NEVER skip the ranking phase** - it is essential to the council deliberation process 5. **Read

What's inside
Steps it walks through
  1. When to Use
  2. CRITICAL RULES
  3. Pre-flight Check
  4. Available Models
  5. Workflow
  6. Step 1: Gather User Input
  7. Model Name to ID Mapping
  8. Step 2: Run Phase 1 - Individual Responses
  9. Step 3: Run Phase 2 - Cross-Model Ranking
  10. Step 4: Run Phase 3 - Chairman Synthesis
  11. Step 5: Display Full Results
  12. Important Notes
  13. Setup
  14. Limitations
Ships with 1 file
  • .env.example
Commands it runs
if [ -z "$FIREWORKS_API_KEY" ]; then
echo "ERROR: FIREWORKS_API_KEY is not set."
echo "Create a Fireworks AI account at: https://fireworks.ai/"
echo "Then export it in your shell profile (~/.zshrc or ~/.bashrc):"
echo '  read -rsp "Fireworks API key: " FIREWORKS_API_KEY; echo; export FIREWORKS_API_KEY'
exit 1
fi
echo "FIREWORKS_API_KEY is set."
python3 << 'PYEOF'
read -rsp "Fireworks API key: " FIREWORKS_API_KEY
More from agentic-awesome-skills
All skills →
About this skill
What does the llm-council skill do?

Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.

How do I install it?

Run `npx skills add sickn33/agentic-awesome-skills --skill llm-council --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going