dsh-task-breakdown
Skill4 starsChanged 3 months agoMITView on GitHub
接手复杂任务时使用：拆解为可验证的子任务、明确验收标准、防止范围蔓延。
In this repository18 other files it gives its agents.
- dsh-changelogSkill
- dsh-chinese-docsSkill
- dsh-code-reviewSkill
- dsh-debug-sessionSkill
- dsh-dependency-auditSkill
- dsh-doc-syncSkill
- dsh-git-commitSkill
- dsh-office-artifactsSkill
- dsh-plugin-clientSkill
- dsh-plugin-devSkill
- dsh-plugin-i18nSkill
- dsh-plugin-publishSkill
- dsh-preset-authoringSkill
- dsh-pr-reviewSkill
- dsh-refactor-safeSkill
- dsh-skill-adapterSkill
- dsh-test-firstSkill
- dsh-webapp-testingSkill
The file
Files
任务拆解
流程
- 验收标准先行：把"做完"定义为可验证的检查项（命令输出、文件存在、行为符合）
- 拆子任务：每项 30 分钟内可完成、可独立验证
- 依赖排序：先做被依赖的；无法排序说明拆得不够
- 写进 todo 工具：每项一个条目，完成即勾
- 防范围蔓延：过程中冒出的新需求记入 backlog，不混入当前任务
执行纪律
- 先跑通"最小闭环"（端到端最简路径），再补边角
- 每完成一个子任务就验证，不等最后
- 受阻时记录阻塞点与已尝试的方案，而不是换方向
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.