← Back to Skills Marketplace
Dev Project Tracker
by
huangliujiao-tal
· GitHub ↗
· v1.0.0
· MIT-0
347
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install dev-project-tracker
Description
按需求/版本维度管理项目全生命周期。创建需求目录、记录日常进展、追踪问题、管理变更、自动蒸馏归档。 触发词：创建需求目录、新建项目、项目进展、记录进展、项目归档、蒸馏项目、查看项目、项目状态、 "新需求"、"建个项目目录"、"记一下进展"、"这个需求上线了"。 适用于任何按版本/需求迭代的软件项目。
README (SKILL.md)
Project Tracker
按需求/版本一站式管理项目文档，覆盖从创建到归档的完整生命周期。
目录结构规范
每个需求/版本一个目录，放在 projects/\x3Cproject-name>/\x3Crequirement-name>/ 下：
projects/\x3Cproject>/\x3Crequirement>/
├── README.md # 总览：需求名称、负责人、上线时间、状态
├── WORK_LOG.md # 日常进展（按日期倒序）
├── DIVISION.md # 分工表
├── ISSUES.md # 问题追踪
├── CHANGES.md # 变更记录
├── docs/ # 需求文档、PRD链接
├── tech/ # 技术方案
└── design/ # 设计稿链接
操作指南
创建需求目录
收到"创建需求目录"或"新需求"时：
- 读取
references/templates/下的模板文件 - 在
projects/\x3Cproject>/\x3Crequirement>/下创建完整目录结构 - 填入已知信息（需求名、负责人、预计上线时间等）
- README.md 中
状态字段设为🟢 开发中
记录日常进展
收到"记录进展"或项目相关更新时：
- 在
WORK_LOG.md顶部添加新条目（日期倒序） - 格式：
## YYYY-MM-DD+ 具体内容 - 同步更新个人日志
memory/YYYY-MM-DD.md - 关键决策同时写入长期记忆（memory_store）
追踪问题
在 ISSUES.md 中管理：
| # | 问题描述 | 状态 | 负责人 | 创建日期 | 解决日期 |
|---|---------|------|--------|---------|---------|
| 1 | xxx | 🔴待解决 | xxx | 2026-03-20 | - |
状态：🔴待解决 → 🟡处理中 → 🟢已解决
变更记录
需求变更时在 CHANGES.md 记录：
## YYYY-MM-DD 变更标题
- **变更内容：** xxx
- **变更原因：** xxx
- **影响范围：** xxx
- **确认人：** xxx
生命周期管理
README.md 中必须包含 状态 和 实际上线 字段：
| 阶段 | 状态 | 触发条件 | 操作 |
|---|---|---|---|
| 活跃期 | 🟢 开发中 | 创建时 | 完整记录所有文件 |
| 蒸馏期 | 🟡 已上线(蒸馏中) | 上线后2周 | WORK_LOG/ISSUES 压缩为摘要，tech/design 保留 |
| 归档期 | 🔴 已归档 | 上线后3个月 | 压缩为 ARCHIVE.md，删除原目录 |
蒸馏/归档前必须通知负责人确认。
查看项目状态
收到"查看项目"或"项目状态"时：
- 扫描
projects/下所有需求目录 - 读取每个 README.md 的状态和上线时间
- 汇总输出项目看板
注意事项
- 项目进展写 WORK_LOG.md，不混入个人日志
- 关键决策、人员信息同步到长期记忆
- 设计稿链接存
design/DESIGN.md，需求文档链接存docs/ - 技术方案存
tech/，按前端/后端分文件
Usage Guidance
This skill appears internally consistent, but before enabling it you should: (1) confirm where 'projects/' and 'memory/' will live (pass an explicit projects root when running the scanner) to avoid scanning or writing outside the intended workspace; (2) review your agent's memory retention/privacy settings because the skill instructs storing key decisions in memory_store; (3) test the included script in a safe directory — the script uses date -j -f (macOS-style) which may fail on some Linux systems; (4) back up important data before enabling automated archiving/cleanup; and (5) if you want stricter limits, run the skill in a constrained environment or restrict the agent's filesystem permissions so it can only access the intended project directories.
Capability Analysis
Type: OpenClaw Skill
Name: dev-project-tracker
Version: 1.0.0
The skill bundle is a project management tool designed to track requirements, logs, and issues through a structured directory system. It includes a shell script (scripts/scan-projects.sh) that performs local file parsing (grep/find) to summarize project statuses and calculate archiving timelines. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; all components align with the stated purpose of project lifecycle management.
Capability Assessment
Purpose & Capability
Name/description align with what is present: templates, README/WORK_LOG/ISSUES/CHANGES files and a small scanner script. Nothing requires cloud credentials or unrelated system access.
Instruction Scope
SKILL.md directs the agent to create/read/write files under projects/ and to update 'memory/YYYY-MM-DD.md' and the 'memory_store' (agent long-term memory). This is within the tracker purpose but worth noting: instructions both say 'do not mix personal logs' and also say '同步更新个人日志 memory/...', which is ambiguous. Also the scan script reads any README.md under the supplied projects root — ensure the configured projects root is correct so it doesn't scan unintended directories.
Install Mechanism
No install spec (instruction-only) and only one small shell script included. No downloads or extracted archives; low install risk.
Credentials
No environment variables, no credentials, and no external endpoints. The only sensitive action is writing key decisions to the agent's memory_store — expected for a tracker but has privacy implications the user should consider.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modify other skills. Autonomous invocation is allowed by default (normal).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install dev-project-tracker - After installation, invoke the skill by name or use
/dev-project-tracker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
初版：按需求/版本维度管理项目全生命周期，包含目录模板、进展记录、问题追踪、变更管理、自动蒸馏归档
Metadata
Frequently Asked Questions
What is Dev Project Tracker?
按需求/版本维度管理项目全生命周期。创建需求目录、记录日常进展、追踪问题、管理变更、自动蒸馏归档。 触发词：创建需求目录、新建项目、项目进展、记录进展、项目归档、蒸馏项目、查看项目、项目状态、 "新需求"、"建个项目目录"、"记一下进展"、"这个需求上线了"。 适用于任何按版本/需求迭代的软件项目。 It is an AI Agent Skill for Claude Code / OpenClaw, with 347 downloads so far.
How do I install Dev Project Tracker?
Run "/install dev-project-tracker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Dev Project Tracker free?
Yes, Dev Project Tracker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Dev Project Tracker support?
Dev Project Tracker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Dev Project Tracker?
It is built and maintained by huangliujiao-tal (@huangliujiao-tal); the current version is v1.0.0.
More Skills