Skip to content
Back to skills

Consult

ASecurity

Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.

  • 34 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added February 7, 2026
development

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 1, 2026

npx -y skills add saadshahd/moo.md --skill consult --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Consult?

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

Security grade badge for Consult
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/saadshahd-consult/badge)](https://www.skillsdirectory.com/skills/saadshahd-consult)

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: consult
description: Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.
---

## Pick

Take the experts the user names. Where they name none, or the question needs an angle theirs miss, read `profiles/` and add one or two whose work bears on it — each bringing a different idea to try, not a side in an argument.

## Ideas

Three to five ideas across the panel. The reply opens on idea 1 — no preamble, no method, no note on sources or counts:

```
1. <Expert> — **<the change>**
   *<why, in their voice>*
```

The change alone is bold: it is what the user acts on. The name stays plain, the why italic.

- The change is concrete: what to cut, add, or swap in the thing in question.
- The why is one clause: what that expert would see in this thing, judged on the matter in hand. Their way of thinking, applied — never a record of what they did, a count from their catalogue, or a title of their work.
- No line past 72 characters; a line that won't fit is saying two things.
- A number appears only where the idea is the number.
- Where the thing already exists, each idea is an A/B against it. One line after the ideas says how a pick wins, as `Win: <one clause>`. An idea judged another way carries its own `win:` line under its why, never in the shared one.

## Result

The ideas, then the question alone on its last line: `Build all <N>?` Nothing else, not even a recommendation: choosing is the user's.

The question has one retrievable answer → retrieve it; stating a fact needs no expert. The user wants a verdict on something that exists → use **judge** skill. The user wants a proposal they already committed to attacked → use **interrogate** skill.

Files in this skill

  • SKILL.md6.2 KB
  • profiles/abramov.md2.5 KB
  • profiles/alexander.md2.8 KB
  • profiles/appleton.md2.5 KB
  • profiles/beck.md2.7 KB
  • profiles/brander.md2.5 KB
  • profiles/cagan.md2.2 KB
  • profiles/case.md2.6 KB
  • profiles/evans.md2.5 KB
  • profiles/feathers.md2.8 KB
  • profiles/fielding.md2.5 KB
  • profiles/fowler.md2.8 KB
  • profiles/freeman.md2.5 KB
  • profiles/frost.md2.3 KB
  • profiles/graham.md2.5 KB
  • profiles/gregg.md2.4 KB
  • profiles/hettinger.md2.2 KB
  • profiles/hickey.md2.1 KB
  • profiles/hightower.md2.4 KB
  • profiles/humble.md2.4 KB

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.