cr-logaf-review
【Code Review 子 Agent · 门控三】基于 Sentry LOGAF 三级标注（h/m/l）对代码变更执行 8 维度全面评审（设计合理性、测试质量、预期行为验证、长期影响、代码复杂度、规范执行、变更范围、知识共享）。输出结构化 Checklist 报告并给出最终裁决。由 spec-driven-dev 的 code_review 阶段在门控二通过后自动调用。
Best for CI/CD pipelinesWorks with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·8-dimension comprehensive review
- ·LOGAF severity grading (h/m/l)
- ·Structured checklist report output
- ·Final merge verdict provided
- ·Uses git diff & multiple context files
Use Cases
- →Reviewing a pull request against acceptance criteria and architecture
- →Ensuring test quality before merging
- →Validating design decisions and long-term impact
- →Checking code complexity and standards compliance
Best for
- ✓CI/CD pipelines
- ✓multi-gate code review workflows
Not ideal for
- !quick ad-hoc reviews
- !non-git based projects
FAQs
name
cr-logaf-review
description
【Code Review 子 Agent · 门控三】基于 Sentry LOGAF 三级标注（h/m/l）对代码变更执行 8 维度全面评审（设计合理性、测试质量、预期行为验证、长期影响、代码复杂度、规范执行、变更范围、知识共享）。输出结构化 Checklist 报告并给出最终裁决。由 spec-driven-dev 的 code_review 阶段在门控二通过后自动调用。
user-invocable:false
metadata:{"openclaw":{"emoji":"🧑⚖️","requires":{"bins":["git"]},"calledBy":["spec-driven-dev"]}}
cr-logaf-review
Code Review 流水线的第三道门控：LOGAF Checklist 全面评审子 Agent。
由 spec-driven-dev 的 code_review 阶段在 cr-code-gate 通过或 WARN 后调用。
执行 8 个维度的综合性代码评审，输出可操作的分级反馈，并给出最终合并裁决。
调用契约
输入（由 Orchestrator 注入上下文）
| 字段 | 类型 | 说明 |
|---|---|---|
us_id | string | 用户故事 ID |
iter_id | string | 当前迭代 ID |
git_diff | string | git diff main...HEAD 的完整输出 |
us_file_path | string | requirements/US/{us_id}.md，用于核对验收标准（CR-03） |
architecture_path | string | requirements/{us_id}/docs/architecture.md，用于设计评审（CR-01、CR-04） |
test_report_path | string | requirements/{us_id}/docs/reports/test-{us_id}-report.md，用于测试质量评审（CR-02） |
code_gate_findings | object[] | 门控二 cr-code-gate 传入的 m/l 级发现列表（避免重复报告） |
Orchestrator 调用示例（OpenCode Sub-Agent 格式）：
invoke_skill: cr-logaf-review
with:
us_id: "US042"
iter_id: "iter_003"
git_diff: "<diff output>"
us_file_path: "requirements/US042/docs/US042.md"
architecture_path: "requirements/US042/docs/architecture.md"
test_report_path: "requirements/US042/docs/reports/test-US042-report.md"
code_gate_findings: [{ "id": "GK-07", "logaf": "m", … }]
输出（写回 Orchestrator）
{
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill cr-logaf-reviewSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.