Skip to content
Agentmart
Submit a tool

pr-review-adversarial

Two-phase adversarial validation for PR review findings.

Skill by dgowrie

IndexedLicense unknown
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/dgowrie-pr-review-adversarial

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

Two-phase adversarial validation for PR review findings. Phase 1 attacks the CODE (your own skeptical pass over freshly re-fetched state, plus one independent fresh-context `pr-code-reviewer` subagent) and unions the candidates. Phase 2 attacks the FINDINGS (a second, new `pr-code-reviewer` whose only job is to refute every candidate and every proposed fix, defaulting to NOT PROVEN). Catches findings that are wrong, fixes that are unsafe, and dismissals that were premature. Works on peer PRs and your own. Trigger phrases: "adversarial review", "run an adversarial /pr-review", "refute these findings", "attack this diff", "validate these findings before I stage them", "am I sure about these findings", or explicit `/pr-review-adversarial`.

Use cases: agent-building

Reviews

Write a review

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/pr-review-adversarial

What's inside

Skill name
pr-review-adversarial
Description
Two-phase adversarial validation for PR review findings. Phase 1 attacks the CODE (your own skeptical pass over freshly re-fetched state, plus one independent fresh-context `pr-code-reviewer` subagent) and unions the candidates. Phase 2 attacks the FINDINGS (a second, new `pr-code-reviewer` whose only job is to refute every candidate and every proposed fix, defaulting to NOT PROVEN). Catches findings that are wrong, fixes that are unsafe, and dismissals that were premature. Works on peer PRs and your own. Trigger phrases: "adversarial review", "run an adversarial /pr-review", "refute these findings", "attack this diff", "validate these findings before I stage them", "am I sure about these findings", or explicit `/pr-review-adversarial`.
License
unknown
Instructions
269 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from dgowrie/claude-workflows

Signals

Stars
0
Forks
0
Open issues
67
Last commit (this folder)
Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/dgowrie/claude-workflows
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from dgowrie

Cite this page

pr-review-adversarial skill. Agent Mart. https://agentmart.dev/skills/dgowrie-pr-review-adversarial (last updated 2026-10-24)