← 返回 Skills 市场
englandtong

Daily Workflow (开工啦/收工啦)

作者 EnglandTong · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
35
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install daily-workflow
功能描述
Daily work start and end workflow manager. Triggered by phrases like 'kai gong la' (starting work) or 'shou gong la' (ending work). Manages project documenta...
使用说明 (SKILL.md)

\r \r

Daily Workflow Skill\r

\r Manage daily work sessions with automated project documentation tracking and AI-to-AI handover support.\r \r

When to Use This Skill\r

\r Trigger this skill when the user mentions:\r

  • "开工啦" - Starting the work day\r
  • "收工啦" - Ending the work day\r \r These phrases indicate intentional work session boundaries where project state should be captured and restored.\r \r

Core Workflow\r

\r

Phase 1: Start Work ("开工啦")\r

\r Execute the following sequence when the user indicates work is starting:\r \r

  1. Ensure Docs Directory exists\r
    • Check if Docs/ directory exists in workspace root\r
    • Create Docs/ if it does not exist\r \r
  2. Check and Create Required Files\r
    • Verify these five files exist in Docs/:\r
      • PROJECT_TARGET.md - Project objectives and goals\r
      • PROJECT_STATUS.md - Current project status\r
      • COMPLETED_JOBS.md - Completed work items\r
      • PENDING_JOBS.md - Pending/incomplete work items\r
      • NEXT_STEPS.md - Planned next steps\r
    • Create any missing files with appropriate template headers\r \r
  3. Read All Documentation\r
    • Read all five files from Docs/\r
    • Extract key information:\r
      • Current project objectives\r
      • Latest project status\r
      • Recently completed work\r
      • Pending tasks and blockers\r
      • Planned next steps\r \r
  4. Present Work Session Briefing\r
    • Summarize current project state\r
    • Highlight completed work since last session\r
    • Identify pending tasks\r
    • Suggest priority work for current session\r
    • Ask user for confirmation or adjustments to the plan\r \r

Phase 2: End Work ("收工啦")\r

\r Execute the following sequence when the user indicates work is ending:\r \r

  1. Update Completed Jobs\r
    • Append today's completed work items to Docs/COMPLETED_JOBS.md\r
    • Use format: `## [YYYY-MM-DD]\
  • [completed item 1]\
  • [completed item 2]`\r
    • Include sufficient detail for another AI to understand what was done\r \r
  1. Update Pending Jobs\r
    • Update Docs/PENDING_JOBS.md with:\r
      • Tasks started but not completed\r
      • Blockers encountered\r
      • Tasks deferred to next session\r
    • Remove completed items from pending list\r \r
  2. Update Project Status\r
    • Update Docs/PROJECT_STATUS.md with:\r
      • Current completion percentage\r
      • Key milestones reached\r
      • Current focus area\r
      • Any changes in project direction\r \r
  3. Update Project Target (if needed)\r
    • Modify Docs/PROJECT_TARGET.md only if:\r
      • Project objectives have changed\r
      • New requirements discovered\r
      • Scope adjustments needed\r
    • Otherwise, leave unchanged\r \r
  4. Update Next Steps\r
    • Write clear, actionable next steps to Docs/NEXT_STEPS.md\r
    • Include:\r
      • Specific tasks to tackle next session\r
      • Priority order\r
      • Any prerequisites or dependencies\r
      • Context needed to resume work immediately\r \r
  5. Present Session Summary\r
    • Summarize what was completed\r
    • List updated documentation files\r
    • Confirm next steps are clearly documented\r
    • Ensure handover-ready state for next AI\r \r

File Templates\r

\r When creating missing files, use these templates:\r \r

PROJECT_TARGET.md\r

# Project Target\r
\r
## Project Overview\r
[Describe the project's main objective]\r
\r
## Key Goals\r
- [Goal 1]\r
- [Goal 2]\r
\r
## Success Criteria\r
- [Criterion 1]\r
- [Criterion 2]\r
\r
## Last Updated\r
[YYYY-MM-DD]\r
```\r
\r
### PROJECT_STATUS.md\r
```markdown\r
# Project Status\r
\r
## Current Status\r
[Brief description of current state]\r
\r
## Completion\r
[XX]% complete\r
\r
## Current Focus\r
[What is being worked on now]\r
\r
## Recent Milestones\r
- [YYYY-MM-DD] [Milestone description]\r
\r
## Last Updated\r
[YYYY-MM-DD]\r
```\r
\r
### COMPLETED_JOBS.md\r
```markdown\r
# Completed Jobs\r
\r
## [YYYY-MM-DD]\r
- [Completed task 1]\r
- [Completed task 2]\r
\r
## [YYYY-MM-DD]\r
- [Completed task 1]\r
```\r
\r
### PENDING_JOBS.md\r
```markdown\r
# Pending Jobs\r
\r
## High Priority\r
- [ ] [Task 1]\r
- [ ] [Task 2]\r
\r
## Medium Priority\r
- [ ] [Task 3]\r
\r
## Low Priority\r
- [ ] [Task 4]\r
\r
## Blockers\r
- [Blocker description if any]\r
```\r
\r
### NEXT_STEPS.md\r
```markdown\r
# Next Steps\r
\r
## Immediate Actions (Next Session)\r
1. [Action 1 - with context]\r
2. [Action 2 - with context]\r
\r
## Upcoming Tasks\r
- [Task 1]\r
- [Task 2]\r
\r
## Notes for Next AI\r
[Important context, decisions made, things to remember]\r
```\r
\r
## AI-to-AI Handover Principles\r
\r
Write all documentation assuming the next reader will be a different AI instance that needs to:\r
- Understand what was being built and why\r
- Resume work without asking basic questions\r
- Continue the same coding style and conventions\r
- Respect decisions already made\r
\r
**Key practices:**\r
- Write in detail, not shorthand\r
- Explain the "why" not just the "what"\r
- Include code snippets or file references when relevant\r
- Note any workarounds, hacks, or technical debt\r
- Record user preferences and decisions\r
\r
## Workflow Diagram\r
\r
```\r
User says "开工啦"\r
    ↓\r
Check Docs/ exists → Create if missing\r
    ↓\r
Check 5 files exist → Create missing with templates\r
    ↓\r
Read all 5 files\r
    ↓\r
Present work session briefing\r
    ↓\r
User works with AI assistance\r
    ↓\r
User says "收工啦"\r
    ↓\r
Update COMPLETED_JOBS.md\r
    ↓\r
Update PENDING_JOBS.md\r
    ↓\r
Update PROJECT_STATUS.md\r
    ↓\r
Update PROJECT_TARGET.md (if needed)\r
    ↓\r
Update NEXT_STEPS.md\r
    ↓\r
Present session summary\r
    ↓\r
Project state saved for next AI\r
```\r
\r
## Important Notes\r
\r
- Always use absolute paths when referencing `Docs/` directory\r
- Append to `COMPLETED_JOBS.md` (never overwrite previous entries)\r
- Overwrite `NEXT_STEPS.md` each session (it's for the immediate next session)\r
- Preserve historical information in `PROJECT_STATUS.md` and `COMPLETED_JOBS.md`\r
- When in doubt, write more context, not less\r
安全使用建议
This appears reasonable to install if you want an AI-maintained Docs/ handover workflow. Before using it, be comfortable with the agent editing those files, and avoid placing secrets or sensitive personal information in the generated project notes.
功能分析
Type: OpenClaw Skill Name: daily-workflow Version: 1.0.0 The daily-workflow skill is a productivity tool designed to manage project state and facilitate context handover between AI sessions. It automates the creation and maintenance of five documentation files (e.g., PROJECT_STATUS.md, NEXT_STEPS.md) within a local 'Docs/' directory. The skill's logic is transparent, restricted to project-related documentation, and contains no indicators of data exfiltration, malicious command execution, or unauthorized system access.
能力评估
Purpose & Capability
The purpose is clear and coherent: manage daily start/end work documentation. The noteworthy behavior is local project-document creation, reading, and updating.
Instruction Scope
The workflow is triggered by explicit phrases and is scoped to five files under a workspace Docs/ directory. It asks for plan confirmation at start, while end-of-day documentation updates are expected after the user trigger.
Install Mechanism
No install spec, binaries, environment variables, credentials, or code files are present; this is an instruction-only skill.
Credentials
Workspace file reads and writes are proportionate to the stated documentation workflow and appear limited to project handover files.
Persistence & Privilege
The skill intentionally persists project state, user decisions, and next-step context for later AI sessions. No credential or account privilege use is shown.
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 daily-workflow
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-workflow 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
初始版本 1.0.0 功能介绍: - ✅ 支持「开工啦」触发词,自动读取项目状态 - ✅ 支持「收工啦」触发词,自动保存工作进度 - ✅ 自动管理 Docs/ 目录下的5个核心文档: - PROJECT_TARGET.md (项目目标) - PROJECT_STATUS.md (项目进度) - COMPLETED_JOBS.md (已完成工作) - PENDING_JOBS.md (未完成工作) - NEXT_STEPS.md (下一步计划) - ✅ 自动创建缺失的目录和文档(使用标准模板) - ✅ AI-to-AI 无缝交接,保留完整项目上下文 - ✅ 适用于多 AI 协作的项目管理场景 适用场景: - 每日工作开始/结束时的项目状态管理 - 多人/多 AI 协作时的上下文传递 - 需要详细工作日志的项目管理
元数据
Slug daily-workflow
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

Daily Workflow (开工啦/收工啦) 是什么?

Daily work start and end workflow manager. Triggered by phrases like 'kai gong la' (starting work) or 'shou gong la' (ending work). Manages project documenta... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 35 次。

如何安装 Daily Workflow (开工啦/收工啦)?

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

Daily Workflow (开工啦/收工啦) 是免费的吗?

是的,Daily Workflow (开工啦/收工啦) 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Daily Workflow (开工啦/收工啦) 支持哪些平台?

Daily Workflow (开工啦/收工啦) 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 Daily Workflow (开工啦/收工啦)?

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

💬 留言讨论