agent-council
Collects insights from multiple agents to create a unified answer. Useful when a single model perspective is insufficient.
Install
mkdir -p .claude/skills/agent-council && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7178" && unzip -o skill.zip -d .claude/skills/agent-council && rm skill.zipInstalls to .claude/skills/agent-council
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.
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.Key capabilities
- →Start multi-agent research jobs
- →Wait for job completion
- →Retrieve synthesized results
- →Clean up job artifacts
How it works
The skill manages a multi-agent job lifecycle through a CLI, where multiple agents contribute viewpoints that are then synthesized into a final answer.
Inputs & outputs
When to use agent-council
- →Getting diverse AI perspectives on code
- →Synthesizing research results
- →Brainstorming complex problems with multiple agents
About this skill
Agent Council
Collect multiple AI opinions and synthesize one answer.
Usage
Run a job and collect results:
JOB_DIR=$(./skills/agent-council/scripts/council.sh start "your question here")
./skills/agent-council/scripts/council.sh wait "$JOB_DIR"
./skills/agent-council/scripts/council.sh results "$JOB_DIR"
./skills/agent-council/scripts/council.sh clean "$JOB_DIR"
One-shot:
./skills/agent-council/scripts/council.sh "your question here"
References
references/overview.md— workflow and background.references/examples.md— usage examples.references/config.md— member configuration.references/requirements.md— dependencies and CLI checks.references/host-ui.md— host UI checklist guidance.references/safety.md— safety notes.
When not to use it
- →When a single AI perspective is sufficient
- →For tasks requiring immediate, real-time responses
Prerequisites
Limitations
- →Requires manual cleanup of job directories
How it compares
Unlike a standard single-agent query, this workflow orchestrates multiple independent agents to provide diverse perspectives on a single topic.
Compared to similar skills
agent-council side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agent-council (this skill) | 2 | 7mo | Review | Intermediate |
| deep-research | 35 | 9mo | Review | Advanced |
| scientific-brainstorming | 37 | 7mo | No flags | Intermediate |
| gpt-researcher | 14 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by team-attention
View all by team-attention →You might also like
deep-research
davidorex
Multi-agent parallel investigation for complex VCV Rack problems
scientific-brainstorming
davila7
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
gpt-researcher
assafelovic
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API, customizing research workflows, adding new retrievers, integrating MCP data sources, or troubleshooting research pipelines.
agent-scout-explorer
ruvnet
Agent skill for scout-explorer - invoke with $agent-scout-explorer
research-agent
parcadei
Research agent for external documentation, best practices, and library APIs via MCP tools
create-pattern
nibzard
Analyze sources (blog posts, PDFs, YouTube videos, codebases, pasted text) for agentic patterns, match against 105+ existing patterns, create new patterns or update existing with new sources and insights.