Skip to content
Back to skills

Advisor

ASecurity

User-invoked only; use advisor solely when the user explicitly requests advisor.

  • 25 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 18, 2026
ai-agentsdebugging

Security analysis

A100/100

Scanned October 18, 2026

npx -y skills add nikolanovoselec/codeflare --skill advisor --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Advisor?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Advisor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nikolanovoselec-advisor/badge)](https://www.skillsdirectory.com/skills/nikolanovoselec-advisor)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: advisor
description: User-invoked only; use advisor solely when the user explicitly requests advisor.
disable-model-invocation: true
---

# Advisor (Pi): User-Invoked Stronger-Model Review

The `advisor` tool (provided by the `@juicesharp/rpiv-advisor` extension) hands the **entire current conversation branch** to a stronger reviewer model and returns guidance.

## Hard gate — user request only

Only the user may invoke advisor. Do **not** call the `advisor` tool, run `/advisor`, or suggest `/advisor` unless the user's current message explicitly asks for advisor, for example:

- `/advisor`
- "ask the advisor"
- "use the advisor"
- "call advisor"
- "check this with the advisor"

The assistant must not invoke advisor proactively for:

- planning;
- being stuck;
- routine debugging or CI fixes;
- code review;
- risky or irreversible actions;
- before writing, committing, pushing, deploying, or declaring done;
- generic "second opinion" requests that do not name advisor.

If advisor might help but the user did not explicitly ask for it, continue without advisor or ask a normal clarification question. Do not mention advisor as a required step, and do not tell the user to run `/advisor` proactively.

## Configuration

Advisor authenticates through **Pi's model registry** and uses the model selected by the user through the user-only `/advisor` command. The selection persists across sessions at `~/.config/rpiv-advisor/advisor.json`. Only the user should open `/advisor`; the assistant must not run, simulate, or recommend that command unless asked.

## When explicitly requested

When the user's current message explicitly requests advisor, call `advisor` with no parameters. Relay the returned guidance and make clear what, if anything, it changes.

## Troubleshooting

If the `advisor` tool is unavailable or returns an error, report that directly. Do not retry repeatedly and do not substitute another external LLM unless the user explicitly asks for that.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.