← 返回 Skills 市场
anneheartrecord

weekly-report-generator

作者 anneheartrecord · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
181
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install weekly-report-generator-by-git
功能描述
根据 git 提交记录自动生成本周周报,按功能模块归类输出编号列表格式
使用说明 (SKILL.md)

生成周报

根据配置的项目目录的 git 提交记录,自动生成本周周报。支持多项目聚合。

脚本

运行 scripts/get_git_log.sh 获取本周 git 提交记录。

bash scripts/get_git_log.sh

Instructions

你是一个周报生成助手。根据上面脚本输出的 git log 信息,按以下规则生成周报:

格式要求

按功能模块归类,编号列表 + 缩进子项。格式如下:

  1. 模块名:功能描述
  2. 模块名:
    • 子功能描述1
    • 子功能描述2

归类规则

  1. 如果输出包含多个项目(===PROJECT: xxx===),将所有项目的 commit 统一归类,不按项目分隔
  2. 根据 commit message 和涉及的文件路径,推断出功能模块名(如"部署流程"、"镜像管理"、"监控告警"等)
  3. 同一模块下的多个 commit 合并为子项
  4. 如果某个模块只有一个 commit,直接写在模块名后面,不用子项
  5. commit message 需要做适当的中文归纳简化,不要直接照搬原文
  6. 不要加任何多余的描述、表格、总结、标题、日期范围等,只输出编号列表本身
  7. 编号从 1 开始连续编号

示例输出

  1. 用户模块:登录流程增加二次验证
  2. 权限管理:
    • 角色权限支持批量配置
    • 新增操作审计日志
  3. 数据导出:导出任务改为异步执行
  4. 接口优化:
    • 列表查询增加分页缓存
    • 参数校验逻辑统一收敛
安全使用建议
This skill appears to do what it says: aggregate local git commits and help generate a numbered weekly report. Before installing or running it: 1) Ensure git is installed and available on the machine and that you run the script with a compatible shell (script uses /bin/zsh and array syntax — run with zsh or change the shebang); 2) Create a config.conf in the skill directory that defines PROJECT_DIRS (the script references config.example.conf but that file isn't included); 3) Point PROJECT_DIRS only to repositories you intend to analyze (do not point to repos containing secrets or system configuration you don't want scanned); 4) Be aware the script prints commit messages and --stat output (which can include filenames and small diffs) — review for sensitive data; 5) If you want to be strict about requirements, add documentation that git and zsh are required and include a config.example.conf. These steps will reduce surprises and ensure the skill runs as intended.
功能分析
Type: OpenClaw Skill Name: weekly-report-generator-by-git Version: 1.0.0 The skill is a legitimate utility designed to automate the generation of weekly reports from Git commit logs. It consists of a shell script (scripts/get_git_log.sh) that retrieves local commit history and a markdown file (skill.md) providing formatting instructions for the AI agent. The code follows standard practices for local data processing and lacks any indicators of malicious intent, data exfiltration, or harmful prompt injection.
能力评估
Purpose & Capability
The skill's name/description match the code: the script collects git logs across configured project directories and outputs markers consumed by SKILL.md instructions. However, the skill actually requires git and a POSIX shell with array support (script shebang is /bin/zsh) and a config.conf in the skill directory; these are not declared in the metadata.
Instruction Scope
SKILL.md directs the agent to run scripts/get_git_log.sh and then summarize the printed git log. The script only reads a local config.conf and local git repositories and prints git log/stat sections; it does not call external endpoints or read other system credentials. Minor issues: SKILL.md tells the user to run the script with 'bash' while the script uses a zsh shebang and array syntax — this mismatch could cause runtime errors. SKILL.md also doesn't explain how to create config.conf or its format (config.example.conf is referenced by the script but is not included).
Install Mechanism
No install spec or external downloads. The only code is the included shell script; nothing is written/downloaded by an installer.
Credentials
No credentials or sensitive environment variables are required. The script expects a config.conf defining PROJECT_DIRS and accepts an optional AUTHOR env var; this is proportionate for the task. Users should ensure PROJECT_DIRS do not point to sensitive system paths or repos containing secrets because commit messages and diffs could expose information.
Persistence & Privilege
The skill does not request permanent presence (always: false) and does not modify system or other skills' configs. Autonomous invocation is allowed by default but is not combined with other concerning privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install weekly-report-generator-by-git
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /weekly-report-generator-by-git 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
根据 Git 提交记录自动生成按模块归类的中文周报Skill
元数据
Slug weekly-report-generator-by-git
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

weekly-report-generator 是什么?

根据 git 提交记录自动生成本周周报,按功能模块归类输出编号列表格式. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 181 次。

如何安装 weekly-report-generator?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install weekly-report-generator-by-git」即可一键安装,无需额外配置。

weekly-report-generator 是免费的吗?

是的,weekly-report-generator 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

weekly-report-generator 支持哪些平台?

weekly-report-generator 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 weekly-report-generator?

由 anneheartrecord(@anneheartrecord)开发并维护,当前版本 v1.0.0。

💬 留言讨论