bmad-code-review
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- bmad-code-review
- description
- Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
02 资源文件 5
- 其他customize.toml1.6 KB
- 参考文档steps/step-01-gather-context.md6.3 KB
- 参考文档steps/step-02-review.md2.2 KB
- 参考文档steps/step-03-triage.md2.6 KB
- 参考文档steps/step-04-present.md6.2 KB
03 SKILL.md 正文
Code Review Workflow
Goal: Review code changes adversarially using parallel review layers and structured triage.
Your Role: You are an elite code reviewer. You gather context, launch parallel adversarial reviews, triage findings with precision, and present actionable results. No noise, no filler.
Conventions
- Bare paths (e.g.
checklist.md) resolve from the skill root. {skill-root}resolves to this skill's installed directory (wherecustomize.tomllives).{project-root}-prefixed paths resolve from the project working directory.{skill-name}resolves to the skill directory's basename.
On Activation
Step 1: Resolve the Workflow Block
Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow
If the script fails, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
{skill-root}/customize.toml— defaults{project-root}/_bmad/custom/{skill-name}.toml— team overrides{project-root}/_bmad/custom/{skill-name}.user.toml— personal overrides
Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.
Step 2: Execute Prepend Steps
Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.
Step 3: Load Persistent Facts
Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} — load the referenced contents as facts. All other entries are facts verbatim.
Step 4: Load Config
Load config from {project-root}/_bmad/bmm/config.yaml and resolve:
project_name,planning_artifacts,implementation_artifacts,user_namecommunication_language,document_output_language,user_skill_leveldateas system-generated current datetimesprint_status={implementation_artifacts}/sprint-status.yamlproject_context=**/project-context.md(load if exists)- CLAUDE.md / memory files (load if exist)
- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config
{communication_language}
Step 5: Greet the User
Greet {user_name}, speaking in {communication_language}.
Step 6: Execute Append Steps
Execute each entry in {workflow.activation_steps_append} in order.
Activation is complete. Begin the workflow below.
WORKFLOW ARCHITECTURE
This uses step-file architecture for disciplined execution:
- Micro-file Design: Each step is self-contained and followed exactly
- Just-In-Time Loading: Only load the current step file
- Sequential Enforcement: Complete steps in order, no skipping
- State Tracking: Persist progress via in-memory variables
- Append-Only Building: Build artifacts incrementally
Step Processing Rules
- READ COMPLETELY: Read the entire step file before acting
- FOLLOW SEQUENCE: Execute sections in order
- WAIT FOR INPUT: Halt at checkpoints and wait for human
- LOAD NEXT: When directed, read fully and follow the next step file
Critical Rules (NO EXCEPTIONS)
- NEVER load multiple step files simultaneously
- ALWAYS read entire step file before execution
- NEVER skip steps or optimize the sequence
- ALWAYS follow the exact instructions in the step file
- ALWAYS halt at checkpoints and wait for human input
FIRST STEP
Read fully and follow: ./steps/step-01-gather-context.md
04 同仓库更多 Skills
speclite-dev-story
暂无简介
speclite-code-review-01-reviewer
Fixture-owned installed skill entry for the minimal artifact loop.
speclite-skill-lint
只读检查 Skill 定义;用于 lint skill、check skill、检查技能或评估 Skill 规范。区分基础格式、Codex 适配和 SpecLite 约定,报告证据及未检查项;Agent 定义包转交 speclite-agent-lint。
speclite-skill-creator
创建或迭代 SpecLite workflow Skill;用于 create skill、新建技能、生成技能包或封装工作流。设计入口、辅助资源和验证用例;Agent 定义包转交 speclite-agent-creator。
speclite-html-ppt-generator
生成 SpecLite-owned 单文件 HTML PPT。用于用户要求创建 docs presentation、HTML PPT、网页 slides、Swiss Style deck、杂志风 deck,或其他可直接浏览器打开的介绍/分享型 deck。核心能力:使用本 Skill 内置模板、主题、layout 和 validator 生成横向翻页 HTML,并避免依赖外部个人 skill 路径。
speclite-docs-intro-ppt-creator
生成 SpecLite docs 下的介绍型 HTML PPT。用于用户要求把某个项目体系、系统设计、治理机制、理念或工作流总结成 docs presentation、HTML PPT、网页 slides、介绍 deck。核心能力:限定输出目录、基于事实材料规划叙事、调用 speclite-html-ppt-generator 生成单 HTML deck,并用确定性检查和浏览器抽样收口。