ZBS Index What actually exists in applied AI, with the source next to it

skill

adversarial-review

Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finishing a build, or before shipping, or whenever ATLAS or Boss wants a hostile second opinion on a diff, a running app, or a whole codebase. Spawns clean-context reviewers with opposing lenses (correctness, security, empty-world) and reproduces every finding by running the target before believing it. Distinct from /code-review, which statically reads a diff and never runs the app.

Description as published by the maintainer. Source

  • active

active — Most recent push to the repository was 2026-06-25.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 316 Stars on the repository that contains this skill, not on the skill itself. A collection of fifty skills shares one number, so it says nothing about this particular skill. cumulative, all time GitHub
Last commit 2026-06-25 Most recent push to the containing repository. It may reflect work on a different skill in the same collection. point in time GitHub
repository status active The repository holding this skill exists and is not archived. as of fetch GitHub

Will this work with your setup?

Install location suggests this is meant for claude-code. Installed under .claude/skills/, the Claude Code convention. Not a test result: we have not run it.

We have not run this skill against a task with and without it enabled, so we cannot tell you whether it improves anything, what it costs in tokens, or whether it duplicates behaviour your harness already has. When we have run that test, the result will appear on this page with the task, the versions and the budget it used.

The skill definition lives at .claude/skills/adversarial-review/SKILL.md in https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas.

Where to get it

Also from syahiidkamil

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. syahiidkamil/Software-Engineer-AI-Agent-Atlas on GitHub — GitHub, observed , trust tier 3.