adversarial-review SKILL.md skillA
adversarial-review from revolutionla/adversarial-review is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add revolutionla/adversarial-review/adversarial-review@v2.5.1Pins v2.5.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- revolutionla/adversarial-review
- Path
skills/adversarial-review/SKILL.md- Versions recorded
- 8
- Latest version
- v2.5.1, committed Sep 27, 2026
- First version recorded
- Sep 11, 2026
- Size
- 14,254 bytes
- Repository stars
- 4
- License
- MIT
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）。 - **`references/skill-spec.md`** —— 写/改 skill 时的 SKILL.md 规范速查。 - **`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
mdr add revolutionla/adversarial-review/adversarial-review@sha256:8a16bc3090cd95f0The 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.
[](https://markdownregistry.com/a/art_4cyncu5jipmsf6jl)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Sep 11, 2026 and Sep 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.5.1 latest | 2026-09-27 | 94f7f78 | 14,254 B | A | view · diff |
| v2.5.0 | 2026-09-27 | 013c176 | 14,254 B | A | view · diff |
| v2.4.0 | 2026-09-27 | 7c45ac3 | 14,140 B | A | view · diff |
| v2.3.0 | 2026-09-26 | bf0f72f | 14,140 B | A | view · diff |
| v2.2.0 | 2026-09-26 | 625d5da | 13,510 B | A | view · diff |
| v2.1.1 | 2026-09-26 | 27ac17e | 12,725 B | A | view · diff |
| v2.1.0 | 2026-09-26 | 8b63f62 | 12,725 B | A | view · diff |
| v2.0 | 2026-09-11 | bfb58ee | 12,311 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14254 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
revolutionla/adversarial-review · 4 stars · license MIT · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4cyncu5jipmsf6jl GET https://markdownregistry.com/api/v1/resolve?ref=revolutionla/adversarial-review/adversarial-review GET https://markdownregistry.com/api/v1/blob/8a16bc3090cd95f079fac6d42bbe08d7bd6ba7a9273ddd6c7543736ddf81e32d
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.