Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/godv61-code-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/code-review
What's inside
- Skill name
code-review- Description
- 审核需求符合性、代码质量与可选的 SonarQube 结果,推动失败项修复。
- License
- MIT
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 代码审核元技能 对照需求、任务产物、变更和测试回执审核。项目若启用 SonarQube,测试通过并进入本阶段后主动调用 `dev_task sonar_check`,对提交前的新代码执行本地规则审核;使用者无需另行点击。读取审核文件和未覆盖范围;有阻断问题时先按返回的 recovery 回到代码开发,再修复、验证变化的输入并重新验收受影响实施项,之后回到代码审核再次运行 sonar_check。不要在审核阶段修改完再反复调用只允许开发阶段的 review_item。使用 `dev_task review` 记录最终结果。 先使用问题消息中的具体格式、源码位置与报告。仍有具体疑问时定点查询规则说明,不扫描 DSH 安装目录、app.asar 或整个用户运行目录。测试回执证明程序运行结果,不证明所有需求已覆盖;逐项核对核心业务流程、条件分支、副作用及失败恢复是否有对应测试,区分自动验证、源码核对和待联调事项。 对可复用的失败案例提出项目 Rule 候选,包含触发场景、错误与正确示例、对应 Sonar 规则;经审阅后挂到相应代码开发 Skill。不要把单次误报或整个 Quality Profile 原样写成规则。 本地规则审核的疑似误报先核对代码语义、规则说明与位置。确属误报时,使用 `sonar_disposition` 逐条提交具体原因和证据,等待人工批准;原始命中与原始门禁仍留在审核文件。此处置仅对当前未变化的本地审核有效,不能用于 CI 或上传式服务端 Quality Gate。已确认误报不应作为 `learn_rule` 的候选。
From godv61/dsh-task-engine, MIT.
More from godv61/dsh-task-engine
- 0.629score
eng-delivery
godv61
使用 dev_task 读取任务状态、执行流程门禁与完成条件;具体技能、规则、产物和提交文本以用户配置为准。
SkillAFreshness: A★ 15Claude Code +9 - 0.626score
code-development
godv61
按验收条件和有序任务清单实现代码,并遵守绑定的项目规则。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
architecture-design
godv61
为新模块或大范围重构确定边界、接口、兼容点和关键取舍。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
requirements-analysis
godv61
澄清需求目标、边界和可验收结果,形成后续设计与开发的输入。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
task-orchestration
godv61
按需求实现的依赖顺序拆解任务,记录每步输入、输出和验收。
SkillAFreshness: A★ 15Claude Code +9 - 0.591score
test-validation
godv61
执行与本次变更相称的验证,并记录可追溯的实际命令回执。
SkillAFreshness: A★ 15Claude Code +9
Signals
- Stars
- 15
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Oct 8, 2026 (21 days ago)
- Last release
- Oct 24, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/godv61/dsh-task-engine
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from godv61
- 0.629score
eng-delivery
godv61
使用 dev_task 读取任务状态、执行流程门禁与完成条件;具体技能、规则、产物和提交文本以用户配置为准。
SkillAFreshness: A★ 15Claude Code +9 - 0.626score
code-development
godv61
按验收条件和有序任务清单实现代码,并遵守绑定的项目规则。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
architecture-design
godv61
为新模块或大范围重构确定边界、接口、兼容点和关键取舍。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
requirements-analysis
godv61
澄清需求目标、边界和可验收结果,形成后续设计与开发的输入。
SkillAFreshness: A★ 15Claude Code +9 - 0.621score
task-orchestration
godv61
按需求实现的依赖顺序拆解任务,记录每步输入、输出和验收。
SkillAFreshness: A★ 15Claude Code +9 - 0.591score
test-validation
godv61
执行与本次变更相称的验证,并记录可追溯的实际命令回执。
SkillAFreshness: A★ 15Claude Code +9
Cite this page
code-review skill. Agent Mart. https://agentmart.dev/skills/godv61-code-review (last updated 2026-10-24)