# Devils Advocate

> Produces a one-shot devil's-advocate critique of a plan, design, or decision: steel-manned strengths first, then severity-tagged findings each with a concrete alternative, then a verdict.

- **Type:** Skill
- **Install:** `agentstack add skill-gsarig-skills-devils-advocate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [gsarig](https://agentstack.voostack.com/s/gsarig)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [gsarig](https://github.com/gsarig)
- **Source:** https://github.com/gsarig/skills/tree/main/skills/devils-advocate

## Install

```sh
agentstack add skill-gsarig-skills-devils-advocate
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Steps

### 1. Calibrate intensity to stakes

Before critiquing, judge how hard the decision is to reverse and how costly a wrong call would be. Scale the depth of everything below accordingly: light-touch on cheap, reversible choices; exhaustive pre-mortem on architecture, security, data-loss, or anything hard to undo. State the calibration level in one line at the top so the user knows how heavy this pass is.

### 2. Steel-man before you attack

**This step is not optional.** Re-express the plan as its strongest version and list its genuine strengths before raising a single objection. If you cannot articulate why the plan is reasonable, you do not understand it well enough to critique it; read more first. This guards against straw-manning and keeps the critique honest.

### 3. Audit the assumptions

Enumerate the assumptions the plan rests on, especially unstated ones. Classify each by likelihood-of-being-wrong and impact-if-wrong. Aim the critique at the high-impact, uncertain assumptions. Do not spend findings on low-impact details or things that are near-certain.

### 4. Stress-test with the toolkit

Apply, scaled to the calibration from step 1:
- **Pre-mortem:** assume the plan shipped and failed. Narrate why.
- **Inversion:** what would reliably *guarantee* failure here? Is the plan accidentally close to it?
- **Second-order effects:** what does this cause downstream, one and two steps out?

### 5. Report in this format

- **Strengths:** from the steel-man.
- **Findings:** each tagged **Critical / Major / Minor**, carrying: assumption challenged, failure scenario, impact, and a recommendation.
- **Verdict:** one line, one of: *Proceed*, *Proceed with revisions* (name them), *Do not proceed as scoped*.

**Core rule: no bare objection.** "This could fail" is not a finding. Either pair the objection with a concrete fix ("this fails under condition X because of Y; do Z instead"), or, when no clean alternative exists, name what would settle it: a test, the missing data, or the person who would know. Every finding carries either a proposed mitigation or the thing that would resolve the uncertainty. Never drop a legitimate concern just because you lack a ready fix.

## Important: what to avoid

- **Manufactured dissent.** If the plan is genuinely sound at its stakes level, say so and keep the findings list short or empty. Do not invent objections to look rigorous.
- **Contrarianism for its own sake, nihilism, straw-manning, reverse-confirmation-bias** (reflexively distrusting whatever is proposed), or critiquing the person rather than the plan.
- **Treating the verdict as authority.** This is input for the user to weigh, not a ruling to obey.

## Handoff

If a finding needs back-and-forth to resolve, dependent decisions, or unstated constraints only the user holds, stop and point to `grill-me` for an interactive pass. This skill is the one-shot batch critique; `grill-me` is the interview.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [gsarig](https://github.com/gsarig)
- **Source:** [gsarig/skills](https://github.com/gsarig/skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-gsarig-skills-devils-advocate
- Seller: https://agentstack.voostack.com/s/gsarig
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.