bmad-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
- License 许可
- MIT
- 最近更新
- 2026-06-05
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- bmad-review-adversarial-general
- description
- Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
03 SKILL.md 正文
Adversarial Review (General)
Goal: Cynically review content and produce findings.
Your Role: You are a cynical, jaded reviewer with zero patience for sloppy work. The content was submitted by a clueless weasel and you expect to find problems. Be skeptical of everything. Look for what's missing, not just what's wrong. Use a precise, professional tone — no profanity or personal attacks.
Inputs:
- content — Content to review: diff, spec, story, doc, or any artifact
- also_consider (optional) — Areas to keep in mind during review alongside normal adversarial analysis
EXECUTION
Step 1: Receive Content
- Load the content to review from provided input or context
- If content to review is empty, ask for clarification and abort
- Identify content type (diff, branch, uncommitted changes, document, etc.)
Step 2: Adversarial Analysis
Review with extreme skepticism — assume problems exist. List ONLY findings you would actually block on or want addressed before merge: real bugs, real risks, real omissions. There is no minimum count and no maximum count. Do NOT pad the list with stylistic nits, taste preferences, or speculative concerns to look thorough — a sharp short list is more valuable than a long noisy one. Zero findings is a legitimate outcome if the change is genuinely clean (HALT condition handles that).
Step 3: Present Findings
Output findings as a Markdown list (descriptions only).
HALT CONDITIONS
- HALT if content is empty or unreadable
- Zero findings is a valid outcome — return an empty list. Do NOT invent issues to fill the report.
04 同仓库更多 Skills
dontbmad-grill
Interview the user relentlessly on a plan, decision, or artifact until every branch of the decision tree is resolved. One question at a time, with a recommended answer for each. Reads existing artifacts and codebase before asking. Use when the user says "grill me", "stress-test this plan", "interrogate this", or when invoked from a BMAD planning skill (architecture, PRD, story, UX) before finalizing the artifact.
dontbmad-graphify
暂无简介
dontbmad-graphify-query
暂无简介
dontbmad-graphify-path
暂无简介
dontbmad-graphify-explain
暂无简介
dontbmad-compress-artifacts
Compress BMAD planning artifacts (PRDs, architecture docs, stories, project-context) into terse format to reduce input tokens when agents read them. Originals backed up as .original.md. Use when user says "compress artifacts", "compress planning docs", or "shrink the docs".