Skip to content
Agentmart
Submit a tool

advisory

Consult for stalls, repeated errors, complex algorithms, unresolved cross-layer interactions, or consequential decisions, diagnoses, plans, and reviews.

Skill by BetoFrega

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/betofrega-advisory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Consult for stalls, repeated errors, complex algorithms, unresolved cross-layer interactions, or consequential decisions, diagnoses, plans, and reviews.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/advisory

What's inside

Skill name
advisory
Description
Consult for stalls, repeated errors, complex algorithms, unresolved cross-layer interactions, or consequential decisions, diagnoses, plans, and reviews.
License
MIT
Instructions
22 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Advisory

Strongly recommend one independent advisor when another perspective can reduce
uncertainty or reveal risk, especially for the description's triggers. Consultation is discretionary; layer
count alone is insufficient. No per-call user approval is needed.

Apply [model-selection](../model-selection/SKILL.md). Prefer Fable 5.1 for
consequential decisions, diagnoses, plans, and reviews; prefer Opus 5.5 for stalls,
repeated errors, complex algorithms, or cross-layer interactions without such a
decision. These preferences override lowest-cost selection when the model is
available and compatible with tools, context, and data retention; otherwise use the
next most capable model. User choices govern; disclose fallback limitations.
Select effort independently and set both explicitly where supported. Check current
Codex or Claude CLI availability and compatibility; neither CLI is required.

Supply the unresolved question, evidence, constraints, and decision criteria without
seeding a conclusion when independence matters. The advisor investigates/recommends;
the primary agent decides/executes. Evaluate advice against evidence and surface
material disagreement or decision-changing risk. Consultation grants no scope
expansion, mutations, external actions, or further delegation.

From BetoFrega/skills, MIT.

More from BetoFrega/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 12, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from BetoFrega

Cite this page

advisory skill. Agent Mart. https://agentmart.dev/skills/betofrega-advisory (last updated 2026-10-24)