adversarial-review SKILL.md skillA

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

Install it, pinned
mdr add iflytek/skillhub/adversarial-review@v2.5.1

Pins v2.5.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
iflytek/skillhub
Path
builtin-skills/skills/adversarial-review/SKILL.md
Versions recorded
1
Latest version
v2.5.1, committed Oct 15, 2026
Size
14,230 bytes
Repository stars
5,260
License
Apache-2.0

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)→ 中立裁定(逐条采纳/驳回、审查双方共同前提)。当用户说"蓝军评审""第三方复核""对抗性审查""红蓝互搏""三方评审""交叉验证""发布前审查""帮我挑刺""adversarial review""red team review""pre-release review""critique this""find bugs in my code"或要求提升代码质量、准备发布前把关时使用。也适用于用户想把当前会话变成"多个 Agent 互搏"来提升代码水平的场景。.

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

# 三方对抗式代码评审(Blue Team / Third Party / Adjudication)

## 这个 skill 要解决什么

单人或单 AI 写代码,最大的风险不是"不会写",而是:

1. **用未验证的乐观假设说服自己推迟修复**("这个兜底应该够了吧");
2. **测试提供假安全感**(测试全绿,但功能其实早坏了);
3. **为了修 A 而引入 B**(新写的修复代码本身没被独立审视)。

这三个问题**靠"再仔细看一遍"解决不了**——写代码的人和审代码的人是同一个,就一定会为自己辩护。只能靠**结构化的对抗关系**:

| 角色 | 立场 | 硬性约束 |
|---|---|---|
| **蓝军** | 敌意审查——假设代码会出事,去**证明** | 每条结论必须附证据链(`文件:行号` / 实测命令 / 上游源码);🔴/🟠 必须是**实测**结论,仅凭推理最高 🟡;禁止空话 |
| **第三方** | 独立审计——**不信任任何一方文档**,直接读代码 | 逐条复核"声称修了的是否真修了"、**专找修改引入的新缺陷**、并稽核蓝军**漏掉了哪些维度** |
| **中立裁定** | 对双方结论**逐条采纳 / 驳回 / 改级** | 必须由**与蓝军不同的 agent** 担任;当事人不能当法官 |

**关键不是"多找两个 AI 看看",而是顺序与互不信任**:第三方不信开发团队,裁定方不信蓝军和第三方。任一环节缺失,闭环就破。

### 配套文件(按需读取)

- **`references/review-dimensions.md`** —— **完整质量维度清单(19 项)**。第 0 步按改动类型选维度时必须读,否则审查会漏掉大片区域。
- **`references/prompt-templates.md`** —— **三个角色的完整提示词模板 + 占位符约定 + 「设计要点」表(改模板前必读)**。第 1/2/3 步派发子代理时直接取用,不要临时自编。
- **`references/quickstart.md`** —— 面向用户的上手说明(档位选择、什么时候不该用它)。
- **`examples/sample-review.md`** —— 一次真实评审的产出样例。

> ⚠️ **能力边界(必须向用户如实说明)**
> 子代理与主代理通常是**同一模型**,这不是真正独立的第三方。其价值来自**角色约束 + 强制证据**,而非"另一个 AI 的观点"。
> - ✅ 能有效抓出:代码级错误、逻辑漏洞、测试造假、自相矛盾、遗漏分支、声明与实现不符;
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add iflytek/skillhub/adversarial-review@sha256:9ae38522bc6b9cde

The line at the top of this page pins the label v2.5.1, 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_wbk5ejcb4ynuzck2.svg)](https://markdownregistry.com/a/art_wbk5ejcb4ynuzck2)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 15, 2026.

versioncommittedcommitsizeaudit
v2.5.1 latest2026-10-15 52b8401 14,230 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 (14230 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

iflytek/skillhub · 5,260 stars · license Apache-2.0 · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wbk5ejcb4ynuzck2
GET https://markdownregistry.com/api/v1/resolve?ref=iflytek/skillhub/adversarial-review
GET https://markdownregistry.com/api/v1/blob/9ae38522bc6b9cde2b6242988d59678a91ed69a60dc9b11251e04011f033bd71

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 iflytek/skillhub

AGENTS.md AGENTS.md file
iflytek/skillhub · AGENTS.md
git:20261015.51c9478 · audit A · 5,260 stars
ai-claim-checker SKILL.md skill
iflytek/skillhub · builtin-skills/skills/ai-claim-checker/SKILL.md · Evaluate factual claims in AI-generated text and teach a lightweight verification habit. Use when a learner wants to…
v1.0.0 · audit A · 5,260 stars
cue-omni-reader SKILL.md skill
iflytek/skillhub · builtin-skills/skills/cue-omni-reader/SKILL.md · Parse and understand an HTTP(S) URL or an authorized local document, audio, or video source through Cue Omni Reader…
v1.0.0 · audit A · 5,260 stars
daily-standup-journal SKILL.md skill
iflytek/skillhub · builtin-skills/skills/daily-standup-journal/SKILL.md · Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for…
v1.0.0 · audit A · 5,260 stars
decision-matrix SKILL.md skill
iflytek/skillhub · builtin-skills/skills/decision-matrix/SKILL.md · Compare options with weighted scoring, pros and cons, pre-mortems, opportunity costs, and ICE prioritization. Use when…
v1.0.0 · audit A · 5,260 stars
diagram-maker SKILL.md skill
iflytek/skillhub · builtin-skills/skills/diagram-maker/SKILL.md · Create standalone SVG/HTML or editable Excalidraw diagrams for concepts, architecture, processes, flows, and…
v1.0.0 · audit A · 5,260 stars
documentation-writer SKILL.md skill
iflytek/skillhub · builtin-skills/skills/documentation-writer/SKILL.md · Create or revise software documentation using the Diátaxis distinction between tutorials, how-to guides, reference, and…
v1.0.0 · audit A · 5,260 stars
exam-ready SKILL.md skill
iflytek/skillhub · builtin-skills/skills/exam-ready/SKILL.md · Prepare a concise exam review from study materials and a syllabus supplied by the user. Use for topic summaries, recall…
v1.0.0 · audit A · 5,260 stars
frontend-design SKILL.md skill
iflytek/skillhub · builtin-skills/skills/frontend-design/SKILL.md · Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with…
v1.0.0 · audit A · 5,260 stars
ledger-tasks-yylo SKILL.md skill
iflytek/skillhub · builtin-skills/skills/ledger-tasks-yylo/SKILL.md · Comprehensive guide for using YYLO Ledger task management without bypassing controller routing, lifecycle state, or…
v1.0.0 · audit A · 5,260 stars
linkedin-post-formatter SKILL.md skill
iflytek/skillhub · builtin-skills/skills/linkedin-post-formatter/SKILL.md · Draft or reformat copy-paste-ready LinkedIn posts from user-provided ideas and source material. Use for professional…
v1.0.0 · audit A · 5,260 stars
meeting-note-summarizer SKILL.md skill
iflytek/skillhub · builtin-skills/skills/meeting-note-summarizer/SKILL.md · Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants…
v1.0.0 · audit A · 5,260 stars

Every file in iflytek/skillhub

Other files named adversarial-review

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
adversarial-review SKILL.md skill
ucsandman/claude-skills · adversarial-review/SKILL.md · Multi-agent adversarial code review - parallel finders, verified by a skeptic. Use for "adversarial review" or "did the…
git:20260904.14d2e37 · audit A · 5 stars

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