adversarial-review SKILL.md skillA

adversarial-review from ucsandman/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ucsandman/claude-skills/adversarial-review@git:20260904.14d2e37

Pins git:20260904.14d2e37 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ucsandman/claude-skills
Path
adversarial-review/SKILL.md
Versions recorded
2
Latest version
git:20260904.14d2e37, committed Sep 4, 2026
First version recorded
Aug 12, 2026
Size
7,202 bytes
Repository stars
5
License
MIT

Multi-agent adversarial code review - parallel finders, verified by a skeptic. Use for "adversarial review" or "did the agents break anything".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Adversarial Review

Review a change-set with a two-stage multi-agent pipeline: **find** (parallel
read-only reviewers, each owning one failure dimension) then **verify** (an
independent skeptic per finding, prompted to refute it). Only findings that
survive verification are reported. This kills the two classic failure modes of
LLM review: plausible-but-wrong findings, and one reviewer trying to hold every
concern at once.

This skill authorizes use of the Workflow tool for the orchestration.

## 1. Establish scope (cheap, inline)

- Default: the working tree — `git diff HEAD --stat` plus `git status --short`
  for untracked files. If the tree is clean, use commits ahead of the default
  branch (`git log origin/main..HEAD`); if none, the last commit.
- If args name a base ref, PR number (`gh pr diff <n> --stat`), or paths, scope
  to that instead.
- Build a SCOPE block: repo path, the changed-file list grouped by
  feature/area if discernible (read the recent commit messages), and one line
  of context per group ("X was just implemented by engineer A who did not know
  about Y"). If several independent changes landed in sequence, SAY SO in the
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ucsandman/claude-skills/adversarial-review@sha256:d2a779dde177ad70

The line at the top of this page pins the label git:20260904.14d2e37, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_olkde6krkx7h43rq.svg)](https://markdownregistry.com/a/art_olkde6krkx7h43rq)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 12, 2026 and Sep 4, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
git:20260904.14d2e37 latest2026-09-04 14d2e37 7,202 BA view · diff
git:20260812.9665e9c2026-08-12 9665e9c 7,028 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7202 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ucsandman/claude-skills · 5 stars · license MIT · pushed 2026-09-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_olkde6krkx7h43rq
GET https://markdownregistry.com/api/v1/resolve?ref=ucsandman/claude-skills/adversarial-review
GET https://markdownregistry.com/api/v1/blob/d2a779dde177ad708613709d64a2db917155f0b198c78b162e6441074df3300a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ucsandman/claude-skills

aesthetic-animaxxing SKILL.md skill
ucsandman/claude-skills · aesthetic-animaxxing/SKILL.md · Apply the Animaxxing aesthetic: monochrome editorial design set in Rethink Sans and JetBrains Mono, poster-scale type…
git:20260915.793ae04 · audit A · 5 stars
ai-search-optimization SKILL.md skill
ucsandman/claude-skills · ai-search-optimization/SKILL.md · Improve retrieval, citations, and accurate representation in AI search answers.
git:20260905.41afbd2 · audit A · 5 stars
announce SKILL.md skill
ucsandman/claude-skills · announce/SKILL.md · Use when a product or feature is ready to go public — after shipping, when the user says "announce it", "go live"…
git:20260915.793ae04 · audit A · 5 stars
audio-track SKILL.md skill
ucsandman/claude-skills · audio-track/SKILL.md · Use when the user wants music, voiceover, narration, or a soundtrack added to a video asset, OR wants standalone…
git:20260915.793ae04 · audit A · 5 stars
blindspot SKILL.md skill
ucsandman/claude-skills · blindspot/SKILL.md · Inspect unfamiliar or high-stakes code before edits, including auth, billing, and migrations.
git:20260905.41afbd2 · audit A · 5 stars
brave-wes SKILL.md skill
ucsandman/claude-skills · brave-wes/SKILL.md · Use when you need to clicks on the provided element or other brave-wes operations from the shell. Run 'brave-wes…
git:20260915.793ae04 · audit B · 5 stars
chrome-wes SKILL.md skill
ucsandman/claude-skills · chrome-wes/SKILL.md · Use when you need to clicks on the provided element or other chrome-wes operations from the shell. Run 'chrome-wes…
git:20260915.793ae04 · audit A · 5 stars
clihub SKILL.md skill
ucsandman/claude-skills · clihub/SKILL.md · Use when you need to find a capability across all matrices for a task (e or other clihub operations from the shell. Run…
git:20260915.793ae04 · audit A · 5 stars
dashclaw-governance SKILL.md skill
ucsandman/claude-skills · dashclaw-governance/SKILL.md · Apply DashClaw governance: guard decisions, approvals, action recording, and agent session lifecycle.
git:20260905.41afbd2 · audit A · 5 stars
de-vibe SKILL.md skill
ucsandman/claude-skills · de-vibe/SKILL.md · Remove AI-generated design tells and give an interface a distinct identity; /de-vibe.
git:20260905.41afbd2 · audit A · 5 stars
deskclaw SKILL.md skill
ucsandman/claude-skills · deskclaw/SKILL.md · Inspect the Windows desktop, screenshots, native apps, and dialogs.
git:20260905.41afbd2 · audit A · 5 stars
dispatch-blocks SKILL.md skill
ucsandman/claude-skills · dispatch-blocks/SKILL.md · Use the established brief blocks when dispatching subagents or workflows.
git:20260905.41afbd2 · audit A · 5 stars

Every file in ucsandman/claude-skills

Other files named adversarial-review

adversarial-review SKILL.md skill
iflytek/skillhub · builtin-skills/skills/adversarial-review/SKILL.md · 开发完成后的三方对抗式代码评审闭环:蓝军(敌意审查,须给证据链)→ 第三方(独立审计,不信双方文档、只读代码,专找"修改引入的新缺陷"并稽核蓝军漏审的维度)→…
v2.5.1 · audit A · 5,260 stars
adversarial-review SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/adversarial-review/SKILL.md · Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review…
git:20260530.4ea03d2 · audit A · 4,305 stars
adversarial-review SKILL.md skill
a5c-ai/babysitter · library/methodologies/metaswarm/skills/adversarial-review/SKILL.md · Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via…
git:20260601.da7723a · audit A · 1,862 stars
adversarial-review SKILL.md skill
timharris707/skills · skills/run/adversarial-review/SKILL.md · Run an adversarial review of a change before it ships: isolated finders trying to break it, a skeptic pass that kills…
git:20261008.0b04f1c · audit A · 44 stars
adversarial-review SKILL.md skill
timharris707/skills · plugins/clickai-codex/skills/run/adversarial-review/SKILL.md · Before committing substantial work, at worker completion, before external review, or on an explicit…
git:20261008.0b04f1c · audit A · 44 stars
adversarial-review SKILL.md skill
event4u-app/agent-config · src/skills/adversarial-review/SKILL.md · Adversarial critique — devil's advocate, stress-test, honest teardown ('poke holes', 'be brutal', 'was hältst du…
git:20260906.720eb73 · audit A · 12 stars
adversarial-review SKILL.md skill
robertoecf/adversarial-review · skills/adversarial-review/SKILL.md · Use for requested adversarial review of plans, diffs, configs, prompts or skills, and whenever a project requires that…
v0.9.9 · audit A · 12 stars
adversarial-review SKILL.md skill
s977043/river-review · skills/agent-skills/adversarial-review/SKILL.md · 敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 (Pre-mortem / War Game / Logic Torturing)と、宣言・主張と実態の乖離を突く claim-vs-actual…
v0.1.0 · audit A · 7 stars

Browse by kind, by grade A, or by owner.