tenfoldmarc/llm-council-skill on GitHub: AI Engineering, Give agent knowledge, Build agent workflow (SDK), Agent society, Memory management, Prompt engineering, Summarization.
tenfoldmarc/llm-council-skill is ranked 13,390 with 830 stars.
Same-category comparison
tenfoldmarc/llm-council-skill is ranked 13,390 among these 8 peers; jonigl/mcp-client-for-ollama is ranked 13,388.
Same-category comparison| Name | Rank | Metrics |
|---|
| Azure-Samples/aoai-realtime-audio-sdk | 13,379 | - Language:
- TypeScript
- Stars:
- 830
- Forks:
- 188
- Description:
- Azure OpenAI code resources for using gpt-4o-realtime capabilities.
|
|---|
| SomeOddCodeGuy/WilmerAI | 13,382 | - Language:
- Python
- Stars:
- 830
- Forks:
- 51
- Description:
- WilmerAI is one of the oldest LLM semantic routers. It uses multi-layer prompt routing and complex workflows to allow you to not only create practical chatbots, but to extend any kind of application that connects to an LLM via REST API. Wilmer sits between your app and your many LLM APIs, so that you can manipulate prompts as needed.
|
|---|
| heurist-network/heurist-agent-framework | 13,387 | - Language:
- Python
- Stars:
- 830
- Forks:
- 90
- Description:
- A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.
|
|---|
| jonigl/mcp-client-for-ollama | 13,388 | - Language:
- Python
- Stars:
- 830
- Forks:
- 126
- Description:
- Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.
|
|---|
| ZHO-ZHO-ZHO/ComfyUI-BRIA_AI-RMBG | 13,396 | - Language:
- Python
- Stars:
- 829
- Forks:
- 65
- Description:
- Unofficial implementation of BRIA RMBG Model for ComfyUI.
|
|---|
| jacksteamdev/obsidian-mcp-tools | 13,399 | - Language:
- TypeScript
- Stars:
- 829
- Forks:
- 121
- Description:
- Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
|
|---|
| mco-org/squad | 13,403 | - Language:
- Rust
- Stars:
- 829
- Forks:
- 92
- Description:
- Multi-AI agent terminal collaboration tool.
|
|---|
| AgnosticUI/agnosticui | 13,406 | - Language:
- TypeScript
- Stars:
- 828
- Forks:
- 46
- Description:
- AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Category | AI Engineering |
|---|
| Subcategory | Give agent knowledge, Build agent workflow (SDK) |
|---|
| Keywords | Agent society, Memory management, Prompt engineering, Summarization |
|---|
| Stars | 830 |
|---|
| Forks | 161 |
|---|
| Contributors | 0 |
|---|
| Created date | 2026-04-18 |
|---|
| Updated date | 2026-10-15 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | 8 |
|---|
| Rank | 13,390 |
|---|
| Previous rank | 6,346 |
|---|
| Rank change | -7,044 |
|---|
| 7-day stars rank | 4,549 |
|---|
| Previous 7-day stars rank | 3,853 |
|---|
| 7-day stars rank change | -696 |
|---|
| Total stars rank | 12,939 |
|---|
| Previous total stars rank | 12,908 |
|---|
| Total stars rank change | -31 |
|---|
README summary
Run any decision through 5 AI advisors who argue, peer-review each other anonymously, and hand you a verdict you can actually trust. Based on Andrej Karpathy's LLM Council methodology, adapted to run entirely inside Claude Code using sub-agents with different thinking styles. " and it'll find 5 reasons why you should. Same product, different framing, opposite answers. How It Works When you say **"council this"**, the skill: 1. **Scans your workspace** for relevant context (CLAUDE. **Frames your question** into
a neutral prompt 3. **Chairman synthesizes** the verdict: where the council agrees, where it clashes, blind spots it caught, a clear recommendation, and one concrete next step 6. **Generates a visual HTML report** + full markdown transcript All in one session. " "Which of these 3 positioning angles is strongest? " "I'm thinking of pivoting from X to Y. " "Should I hire a VA or build an automation first? " **Skip the council for:** Factual questions with one right answer Pure creation tasks ("write
me a tweet") Summaries or processing tasks Validation-seeking when you already know the answer The council tells you things you don't want to hear.
Frequently asked questions
How many stars and forks are recorded?
tenfoldmarc/llm-council-skill has 830 stars and 161 forks.
What is the repository rank?
tenfoldmarc/llm-council-skill is ranked 13,390.
Which repository is closest in rank?
tenfoldmarc/llm-council-skill is compared with jonigl/mcp-client-for-ollama, ranked 13,388 with 830 stars.
LLM Council — A Claude Code Skill
Stop trusting Claude's first answer. Run any decision through 5 AI advisors who argue, peer-review each other anonymously, and hand you a verdict you can actually trust.
Based on Andrej Karpathy's LLM Council methodology, adapted to run entirely inside Claude Code using sub-agents with different thinking styles.
The Problem
Claude is incredibly agreeable. Ask it "should I launch this product?" and it'll find 5 reasons why you should. Ask "is this product a bad idea?" and it'll find 5 reasons why it is. Same product, different framing, opposite answers.
That's fine for writing emails. It's dangerous for making decisions.
How It Works
When you say "council this", the skill:
- Scans your workspace for relevant context (CLAUDE.md, memory files, etc.)
- Frames your question into a neutral prompt
- Spawns 5 advisors in parallel, each with a different thinking style:
- The Contrarian — hunts for what will fail
- The First Principles Thinker — asks if you're solving the right problem
- The Expansionist — looks for upside you're missing
- The Outsider — responds with zero context (catches curse of knowledge)
- The Executor — only cares what you do Monday morning
- Anonymizes their responses and runs a peer review — advisors review each other without knowing who said what
- Chairman synthesizes the verdict: where the council agrees, where it clashes, blind spots it caught, a clear recommendation, and one concrete next step
- Generates a visual HTML report + full markdown transcript
All in one session. About 4 minutes.
Install
Option 1 — Git clone (recommended)
git clone https://github.com/tenfoldmarc/llm-council-skill ~/.claude/skills/llm-council
Then open Claude Code (claude in Terminal).
Option 2 — Manual
- Create folder
~/.claude/skills/llm-council/
- Drop
SKILL.md inside it
- Restart Claude Code
Use
Type any of these triggers followed by your question:
council thisrun the councilpressure-test thisstress-test thiswar room thisdebate this
Example:
council this: I'm thinking of pivoting from a $297 course to a $97 live workshop for my audience of non-technical solopreneurs. Is that the right move?
Give it context. The richer the input, the sharper the output.
You'll get:
- A visual HTML report that opens automatically
- A full markdown transcript saved alongside it
When To Use It
Good council questions:
- "Should I launch a $97 workshop or a $497 course?"
- "Which of these 3 positioning angles is strongest?"
- "I'm thinking of pivoting from X to Y. Am I crazy?"
- "Here's my landing page copy. What's weak?"
- "Should I hire a VA or build an automation first?"
Skip the council for:
- Factual questions with one right answer
- Pure creation tasks ("write me a tweet")
- Summaries or processing tasks
- Validation-seeking when you already know the answer
The council tells you things you don't want to hear. That's the feature, not a bug.
Credit
License
MIT — do whatever you want with it.