Skip to content
Back to skills

Adversarial Squad

ASecurity

Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec investigation squad", "brownfield check", "second opinion on this design", "review squad", "run a multi-lens review". Does NOT handle: the implement-review loop (use spec-kitty-implement-review), spec/plan/tasks generation, or direct code editing ...

  • 1,669 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agents

Security analysis

A100/100

Scanned September 29, 2026

npx -y skills add spec-kitty/spec-kitty --skill adversarial-squad --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adversarial Squad?

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

Security grade badge for Adversarial Squad
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/spec-kitty-adversarial-squad/badge)](https://www.skillsdirectory.com/skills/spec-kitty-adversarial-squad)

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: adversarial-squad
description: >-
  Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut
  so independent doctrine lenses converge on findings one reviewer would miss.
  Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass",
  "pre-spec investigation squad", "brownfield check", "second opinion on this design",
  "review squad", "run a multi-lens review".
  Does NOT handle: the implement-review loop (use spec-kitty-implement-review),
  spec/plan/tasks generation, or direct code editing by the orchestrator. It is an
  optional, charter/memory-activated enrichment — it never gates a mission.
---

# Adversarial Squad Deployment (harness)

The operational alias for the doctrine procedure `adversarial-squad-deployment`
(`packs/built-in/procedures/adversarial-squad-deployment.procedure.yaml`), which is
the single owner of when, who, and how to run a squad. This skill changes **no**
mission type or guard; it is a technique the orchestrator opts into.

## Load the procedure

Before dispatching, load the procedure's full playbook:

```
spec-kitty charter context --include procedure:adversarial-squad-deployment
```

Apply its point-cut list, casting rule, dispatch discipline, model-tier routing,
synthesis step, and findings-disposition contract as written there — this skill
does not restate them.

## Invocation

Invoke by name (`adversarial-squad`) with the point-cut + question, e.g.
*"adversarial-squad: post-tasks anti-laziness on WP01–WP08."* This skill is the alias
surface; the doctrine procedure is the canonical record of the technique.

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.