expert-panel — Claude Code skill: a panel of experts for analysis
The skill assembles 2–3 experts who examine a topic from different angles and return one synthesis with recommendations.
npx skills add OneWave-AI/claude-skills --skill expert-panel -a claude-codeWhat expert-panel does
The skill turns your agent into a panel moderator. It picks 2–3 experts from different fields, lets each one weigh in, then puts their conclusions against each other and merges everything into a single analysis. The flow runs in stages: initial analysis, cross-pollination of ideas, synthesis, integrated recommendations.
Output arrives in a fixed shape: a header with a timestamp, a results section, and a separate block of next steps. Experts build on each other's insights, so you get one coherent picture rather than three separate opinions.
The skill installs into Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. GitHub Copilot goes through gh, so that CLI has to be on your machine — the npx route won't work there.
What it helps with
- review an architecture decision from several expert angles
- get one agreed conclusion instead of a single agent opinion
- produce recommendations and next steps for a contested task
- look at a product idea through different specialists' eyes
Example prompts for the agent
- Assemble an expert panel and tell me whether this module should move to another framework
- Run expert-panel on the choice between two database schemas
- Put together three experts and give me recommendations on this architecture
How to install expert-panel
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill expert-panel -a claude-code2Manually: put the files in place
~/.claude/skills/expert-panel/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/expert-panel/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill expert-panel -a codex2Manually: put the files in place
.agents/skills/expert-panel/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill expert-panel -a cursor2Manually: put the files in place
.cursor/skills/expert-panel/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills expert-panel2Manually: put the files in place
.github/skills/expert-panel/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill expert-panel -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path expert-panelManually: put the files in place
.devin/skills/expert-panel/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill expert-panel -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about expert-panel
How do I install expert-panel in Claude?
Run npx skills add OneWave-AI/claude-skills --skill expert-panel -a claude-code. The skill file then lives at ~/.claude/skills/expert-panel/SKILL.md.
What does expert-panel do?
It assembles 2–3 experts who analyze a topic together from different angles. You get a synthesis of their findings plus actionable next steps.
Which platforms support expert-panel?
Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each platform has its own install command and skill file path.
Source text
SKILL.md · MIT
---
name: expert-panel
description: Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
---
# Expert Panel
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
## Instructions
You are a master panel moderator. Assemble 2-3 domain experts who collaboratively analyze topics. Structure: Initial analysis, cross-pollination of ideas, synthesis, and integrated recommendations. Experts build on each other's insights and create comprehensive analyses.
### Output Format
```markdown
# Expert Panel Output
**Generated**: {timestamp}
---
## Results
[Your formatted output here]
---
## Recommendations
[Actionable next steps]
```
### Best Practices
1. **Be Specific**: Focus on concrete, actionable outputs
2. **Use Templates**: Provide copy-paste ready formats
3. **Include Examples**: Show real-world usage
4. **Add Context**: Explain why recommendations matter
5. **Stay Current**: Use latest best practices for expert-simulation
### Common Use Cases
**Trigger Phrases**:
- "Help me with [use case]"
- "Generate [output type]"
- "Create [deliverable]"
**Example Request**:
> "[Sample user request here]"
**Response Approach**:
1. Understand user's context and goals
2. Generate comprehensive output
3. Provide actionable recommendations
4. Include examples and templates
5. Suggest next steps
Remember: Focus on delivering value quickly and clearly!
© OneWave-AI · MIT · OneWave-AI/claude-skills
