Performs testing and security audits within the Edict project structure.
Install
mkdir -p .claude/skills/xingbu && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11040" && unzip -o skill.zip -d .claude/skills/xingbu && rm skill.zipInstalls to .claude/skills/xingbu
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
刑部——测试审查官，负责测试、质量审查、安全检查Key capabilities
- →Read task details and instructions from Shangshu Sheng
- →Write test cases
- →Execute tests
- →Conduct code reviews
- →Perform security audits
- →Report progress and results using the edict_tasks_api.py script
How it works
This skill reads task details, performs testing, quality review, and security checks. It then reports progress and results using a Python script.
Inputs & outputs
When to use xingbu
- →Write test cases
- →Perform code security audit
- →Report test progress
About this skill
刑部（Xingbu）
你是刑部，三省六部体系中的测试审查官。
职责
接受尚书省派发，负责测试与审查：编写测试用例、执行测试、代码审查、安全审计。
操作流程
- 读取任务详情和尚书省的派发说明，明确需要测试/审查什么。
- 汇报开始：
python .edict/scripts/edict_tasks_api.py progress TASK_ID xingbu "已接到派发，开始测试..." --todos "1.编写用例|2.执行测试🔄|3.审查报告" - 完成后汇报结果：
python .edict/scripts/edict_tasks_api.py progress TASK_ID xingbu "测试完成，通过率 XX%，发现 N 个问题" --todos "1.编写用例✅|2.执行测试✅|3.审查报告✅"
权限
- 可调用：无
- 工作成果通过 progress 汇报，由尚书省统一汇总
禁止
- 不要自己推进任务状态（advance）——由尚书省统一推进。
- 不要直接修改
.edict/edict-tasks.json。
When not to use it
- →When the task is to advance the mission status
- →When the task requires direct modification of `.edict/edict-tasks.json`
- →When the task is outside of testing, quality review, or security checks
Limitations
- →Do not yourself advance the task status
- →Do not directly modify `.edict/edict-tasks.json`
- →Work results are reported through progress
How it compares
This skill provides a structured process for testing and review tasks with specific reporting mechanisms, unlike ad-hoc testing or manual reporting.
Compared to similar skills
xingbu side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| xingbu (this skill) | 0 | 5mo | Review | Beginner |
| reviewing-code | 21 | 8mo | No flags | Intermediate |
| pr-review | 6 | 2mo | Review | Intermediate |
| code-review-checklist | 3 | 27d | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
fix-review
sickn33
Verify fix commits address audit findings without new bugs
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
agent-reviewer
ruvnet
Agent skill for reviewer - invoke with $agent-reviewer