Skill

Pass

Audit score 90

paseo-advisor

getpaseo/paseo

Spin up a single agent as an advisor for a second opinion on your current task.

What is paseo-advisor?

Paseo Advisor creates a temporary agent that reads your situation and gives judgment without driving the work itself. Use it when you need an outside perspective, fresh take, or review—the advisor informs your decision but doesn't execute changes.

Creates a single advisor agent with zero context of your work
Reads your situation and provides reasoned judgment
Supports forwarded skill invocations (e.g., /unslop, /diagnose) run by the advisor
Allows persistent advisors for ongoing input across multiple decisions
Matches advisor profile to the type of work (design, audit, research)

How to install paseo-advisor

npx skills add https://github.com/getpaseo/paseo --skill paseo-advisor

Prerequisites

Paseo skill installed and configured
Configured advisor profiles available (check via list_profiles)

Claude Code

Cursor

Windsurf

Cline

How to use paseo-advisor

1.Call list_profiles to see available advisor profiles and their notes
2.Invoke the skill with your question: npx skills add ... --skill paseo-advisor
3.Specify a profile by name (--profile <name>) or let the skill match based on the question type
4.Provide a self-contained briefing: the question, what you've considered, relevant file paths, and your explicit ask
5.Include the no-edits suffix to prevent the advisor from modifying files
6.Wait for the advisor's response and synthesize the verdict with your own recommendation

Use cases

Good for

Get a second opinion on a design or architecture decision before committing
Have an advisor review a diff or code change for issues you might have missed
Ask an advisor to run a diagnostic skill (/unslop, /unslop-risk) on your current task
Request fresh perspective on a root-cause analysis or research direction
Maintain a persistent advisor across multiple related decisions in a session

Who it's for

Developers seeking code review or design feedback
Teams wanting outside perspective without delegating the work
Anyone needing a second opinion before committing to a direction
Users of the Paseo agent framework

paseo-advisor FAQ

How does the advisor differ from delegating work to another agent?

The advisor reads your situation and gives judgment, but does not execute changes. You remain in control and decide what to do with the advice.

Can the advisor run other skills like /unslop or /diagnose?

Yes. Include the skill reference in your arguments (e.g., /paseo-advisor /unslop) and the advisor will invoke it against your current task.

What if I don't name a profile—how does the skill pick an advisor?

The skill matches the profile whose notes best fit your question type (design, audit, research). It prefers profiles from different provider families for genuine contrast.

Can I keep the same advisor for multiple decisions?

Yes. Don't archive after the first reply; send follow-ups when you need another take. Archive when the topic shifts or you're done.

What should I include in the briefing to the advisor?

The sharp question, what you've considered and ruled out, relevant file paths (don't paste), and an explicit ask for recommendation with reasoning. End with the no-edits suffix.

Full instructions (SKILL.md)

Source of truth, from getpaseo/paseo.

name: paseo-advisor description: Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself. user-invocable: true argument-hint: "[--profile <name>] <question or topic>"

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.

User's request: $ARGUMENTS

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.

The briefing

The advisor has zero context. Make it self-contained:

The question, sharply.
What you've considered and what you've ruled out.
Relevant files by path (don't paste — let the agent read).
Explicit ask: "give me a recommendation, with reasoning."

End with the no-edits suffix:

This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code.

Forwarded skills

If $ARGUMENTS contains another skill reference — /unslop, /unslop-risk, $unslop, etc. — the user is asking the advisor to run that skill against the current task. Examples:

/paseo-advisor /unslop → advisor runs /unslop on the current diff.
/paseo-advisor /unslop-risk → advisor does an unslop-risk review.
/paseo-advisor $diagnose this build failure → advisor invokes /diagnose.

Parse the forwarded skill name out of $ARGUMENTS (/<name> or $<name>). In the briefing, tell the advisor explicitly:

Invoke the `<name>` skill against this task. Load it via the Skill tool before doing anything else.

Pass through any remaining arguments after the skill name as the skill's own input. The advisor — not you — runs the skill; you're still just the orchestrator handing it the work.

Launch and synthesize

Create the advisor agent via Paseo with a [Advisor] <topic> title and the briefing as the initial prompt. Wait for it to finish. Read its response. Synthesize for the user — the advisor's verdict + your recommendation.

Persistent advisor

If the user wants ongoing input ("keep this advisor for the next few decisions"), don't archive after the first reply. Send follow-ups when you need another take. Archive when the user says they're done, or when the topic shifts and a fresh context would serve better.