📦 编程
v1.0.0使用 Cursor AI 在指定项目目录内执行编码任务,包括功能实现、Bug 修复、重构和代码审查。
0· 18·0 当前·0 累计
下载技能包
最后更新
2026/4/19
安全扫描
OpenClaw
安全
medium confidence该技能与其声明的用途(在本地项目上运行 Cursor CLI)内部一致,但在安装和运行前,你需了解若干小遗漏与操作风险。
评估建议
This skill does what it says: it runs the Cursor CLI against code in a project directory. Before using it, confirm how your installed cursor-agent behaves (does it auto-commit or open an interactive session?). Only run it on repositories you are comfortable sharing with Cursor's service and avoid running it directly on production branches. Consider: (1) testing in a disposable or forked repo and on a feature/dev branch, (2) ensuring no secrets are present in the repo, (3) adding an explicit veri...详细分析 ▾
✓ 用途与能力
Name/description match the implemented behavior: the script invokes a Cursor CLI agent against a specified project directory and creates a task file describing the requested code changes. The included requirements.txt references cursor-agent, which is coherent for a Cursor-based coding skill.
ℹ 指令范围
SKILL.md and the script both run Cursor against a repository (expected), but there is a gap: SKILL.md recommends verifying edits before committing, yet the script directly runs cursor-agent and does not enforce a verification step or otherwise gate commits. Depending on cursor-agent's behavior this could result in automated commits/PRs without an explicit local review. The skill also defaults to a workspace path in the docs, which may encourage running against user projects.
✓ 安装机制
This is an instruction-only skill with no install spec; the only artifact is requirements.txt (cursor-agent) and a bash script. No remote downloads or archive extraction are present in the package itself. The runtime depends on an external cursor-agent binary being present on PATH.
ℹ 凭证需求
No required environment variables are declared, which is reasonable, but the script will export and use CURSOR_API_KEY if present (optional). The skill does not request unrelated secrets or system config. Important operational note: running cursor-agent will send repository contents to Cursor's service (network activity to cursor.com or Cursor's backend) — that is inherent to the stated purpose but worth explicit attention.
✓ 持久化与权限
The skill is not always-enabled and does not request persistent system-wide privileges. It does not modify other skills or global agent configuration. It writes temporary task files to /tmp and operates on the specified project path.
安全有层次,运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/19
初始版本
● 可疑
安装命令
点击复制官方npx clawhub@latest install coding-with-cursor-ai
镜像加速npx clawhub@latest install coding-with-cursor-ai --registry https://cn.longxiaskill.com
技能文档
描述
使用 Cursor AI 代理执行编码任务,实现高级代码生成、重构与 Bug 修复。本技能专用于在/home/ubuntu/workspace 项目内处理复杂逻辑变更、功能实现与代码审查。 用法
在以下场景调用:- 实现新功能
- 修复 Bug
- 重构代码
- 编写单元测试
- 执行代码审查
输入
project: 项目根目录路径(例:/home/ubuntu/workspace/zinner/repo/zinner-webapi)task: 自然语言描述的编码任务files: 可选,需聚焦的文件列表
执行
技能启动 Cursor AI 代理会话,授予其对项目仓库的完整访问权限,利用 Cursor 的高级推理与代码编辑能力完成任务并提交更改。约束
- 提交前务必验证 Cursor 的修改
- 未经审查不得在生产分支运行 Cursor
- 优先在
dev或功能分支进行自动编码
示例
``yaml
project: /home/ubuntu/workspace/zinner/repo/zinner-webcms
task: 添加带有占位内容的“条款与条件”页面
``