Executes a multi-agent council process to synthesize consensus from different AI models.
Install
mkdir -p .claude/skills/council-gokmensercan && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11588" && unzip -o skill.zip -d .claude/skills/council-gokmensercan && rm skill.zipInstalls to .claude/skills/council-gokmensercan
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
3 asamali LLM Council pipeline - gorusler, peer review, baskan senteziKey capabilities
- →Query Gemini, Codex, and Copilot in parallel
- →Evaluate responses from other models
- →Synthesize all responses and evaluations
How it works
The skill processes a user's question through a three-stage pipeline: parallel querying of three models, peer review of their responses, and a final synthesis by a president model.
Inputs & outputs
When to use council
- →Getting consensus from multiple models
- →Improving output quality via synthesis
- →Multi-model peer review
About council
Collects parallel responses from Gemini, Codex, and Copilot, performs peer review, and generates a final president-mode synthesis.
3 asamali LLM Council pipeline - gorusler, peer review, baskan sentezi
When not to use it
- →When a single model's response is sufficient
- →When peer review of model responses is not needed
- →When synthesis of multiple perspectives is not required
Limitations
- →Limited to the three specified models: Gemini, Codex, and Copilot
- →Requires a three-stage pipeline for every question
How it compares
This workflow integrates multiple LLMs and a peer review process to synthesize a final answer, unlike directly querying a single model.
Compared to similar skills
council side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| council (this skill) | 0 | 6mo | No flags | Beginner |
| sequential-thinking | 136 | 9mo | No flags | Intermediate |
| planning-with-files | 233 | 6mo | Review | Intermediate |
| ralph-plan | 14 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
sequential-thinking
mrgoonie
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
planning-with-files
davila7
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
ralph-plan
mastra-ai
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
autonomous-agents
davila7
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
ai-wrapper-product
davila7
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
token-budget
toonight
Manages token budget estimation and tracking to prevent context overflow