Paseo Advisor

Spins up a separate agent to give you a second opinion on whatever you're working on without handing off the actual work. You stay in control, the advisor just reads your situation and gives a judgment. Useful when you want a fresh perspective on architecture decisions, a sanity check on whether you missed something obvious, or to see what a different model family thinks about your approach. The skill automatically picks a contrasting provider from your preferences to avoid echo chamber thinking. You can keep the advisor around for a few questions or just use it once and move on. It enforces a no-edits rule so the advisor stays strictly advisory.

skills.sh installs: 4.1K
GitHub stars: 23.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add getpaseo/paseo --skill paseo-advisor --agent claude-code

Installs into .claude/skills of the current project.

Files

Paseo Advisor

Single agent. Reads the situation you're in. Gives a judgment. You decide what to do — the advisor doesn't drive the work.

Use the user's request and current conversation as input, including any arguments supplied with the skill invocation. Optional syntax: [--profile <name>] <question or topic>.

Prerequisites

Read the paseo skill. Call list_profiles before choosing the advisor. Do not create the advisor until you have read the configured profiles and their notes.

Picking the advisor

User named a profile (--profile UI Work) → select it by name.
Otherwise choose the profile whose notes best fit the question. Match the actual work: design and approach, audit and review, or research and root-cause analysis.
Contrast helps. When several profiles fit, prefer a different provider family from your own so the second opinion is genuinely fresh.

Materialize the selected profile into create_agent as described by the paseo skill. If no profile fits, use Paseo's provider discovery fallback.