paseo-committee — Claude Code skill: root-cause analysis through
Spawns two agents with contrasting reasoning styles to diagnose a stuck problem, break out of repetitive loops, and synthesize a plan. Useful when you need a fresh perspective and deep root-cause analysis.
npx skills add getpaseo/paseo --skill paseo-committee -a claude-codeWhat paseo-committee does
The skill runs two high-reasoning agents in parallel. One is selected from your profiles for planning and analysis; the second is a contrasting profile from a different provider family. Both receive the same context, work independently, then resolve disagreements by trading arguments until they reach consensus.
Two hard rules apply inside the skill: agents only analyze—they do not edit or create files—and you do not interrupt them. Models may reason for 15–30 minutes. The skill requires that you first read the paseo profile and call list_profiles to choose committee members based on their notes.
Use it when you are tunnel-visioning on one approach, facing a complex planning problem, or unsure where to dig for the root cause. The result is an agreed analysis, noting where the agents diverged and how they resolved it.
What it helps with
- break out of a repetitive approach loop
- dissect the root cause of a complex problem from two angles
- assemble a plan for a tangled task
- gain deep analysis before implementation begins
Example prompts for the agent
- I am stuck in an endless refactor cycle. Form a committee to figure out what's actually broken.
- I have an architectural decision and I am tunnel-visioning on one solution. Call the committee to analyze it.
- I need to plan a database migration and don't know where to start. Invoke paseo-committee with this context.
How to install paseo-committee
1Skills CLI (Vercel)
npx skills add getpaseo/paseo --skill paseo-committee -a claude-code2Manually: put the files in place
~/.claude/skills/paseo-committee/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/paseo-committee/
1Skills CLI (Vercel)
npx skills add getpaseo/paseo --skill paseo-committee -a codex2Manually: put the files in place
.agents/skills/paseo-committee/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add getpaseo/paseo --skill paseo-committee -a cursor2Manually: put the files in place
.cursor/skills/paseo-committee/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install getpaseo/paseo paseo-committee2Manually: put the files in place
.github/skills/paseo-committee/SKILL.md1Skills CLI (Vercel)
npx skills add getpaseo/paseo --skill paseo-committee -a gemini-cli2Platform CLI
gemini skills install https://github.com/getpaseo/paseo --path skills/paseo-committeeManually: put the files in place
.devin/skills/paseo-committee/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add getpaseo/paseo --skill paseo-committee -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set4
The whole set →Similar
Questions about paseo-committee
How do I install paseo-committee in Claude Code?
Run npx skills add getpaseo/paseo --skill paseo-committee -a claude-code, then open ~/.claude/skills/paseo-committee/SKILL.md.
What does paseo-committee do?
It spawns two agents with different reasoning styles, gives them the same context of your problem, and waits for them to independently analyze it and converge on a plan. Use it when you need fresh thinking or deep diagnostic analysis.
How long does the committee take?
Models may reason for 15–30 minutes. The skill will send a notification when the agents finish—do not interrupt or rush them.
Source text
SKILL.md · Apache-2.0
--- name: paseo-committee description: Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem. user-invocable: true --- # Committee Skill Two agents from contrasting profiles, fresh context, planning a solution in parallel. **User's additional context:** $ARGUMENTS ## Prerequisites Read the **paseo** skill. Call `list_profiles` before choosing committee members. Do not create committee agents until you have read the configured profiles and their `notes`. Contrast is the point of a committee, so pick profiles from different provider families when possible. Materialize each profile into `create_agent`. ## Composition Two members with different reasoning styles, selected from configured Agent profiles: - one whose notes fit planning, research, or root-cause analysis - one contrasting high-reasoning profile from another provider family If the user names profiles, use those. If fewer than two suitable profiles are configured, use Paseo's provider discovery fallback for the missing member and tell the user. Override the selection only when the user explicitly asks for different members. ## Hard rules - **No edits.** Every prompt to a committee member ends with the no-edits suffix: ``` This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code. ``` - **Trust the finish notification.** Do not poll, send hurry-ups, or interrupt. Models can reason for 15–30 minutes. You can go idle and Paseo will notify you. ## Workflow 1. Write a problem-level prompt 2. Create both agents in parallel via Paseo with `[Committee] <task>` titles and the same prompt 3. Wait for both responses 4. Resolve disagreements by passing their arguments between each other 5. Keep going until they converge into a response Share the consensus with the user. Summarize where the agents diverged and how they resolved it.
© getpaseo · Apache-2.0 · getpaseo/paseo
