Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/deepagents-todolist
Using TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex multi-step workflows.
Passed 21 of 21 test cases with the skill, and 8 of 21 without it.
and 15 more in the full report
14 fixed8 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am parsing task states emitted by an automated AI task manager in TypeScript. I want to build a runtime validator that filters out invalid status strings. What are the only valid status values allowed for task planning items in this environment?
| Checked | Without skill | With skill |
|---|---|---|
| Restricts valid task status values strictly to pending, in_progress, and completed. | Missed | Passed |
The instructions your model reads when the skill loads.
TodoListMiddleware 通过 write_todos 工具为代理提供任务规划和进度跟踪功能。它自动包含在每个深度代理中，帮助代理将复杂的多步骤任务分解为可管理的部分。
| 使用 TodoList 的场景 | 跳过 TodoList 的场景 |
|---|---|
| 需要协调的复杂多步骤任务 | 简单的单动作任务 |
| 进度可见性很重要的长时间运行操作 | 快速操作（< 3 步） |
| 可能需要计划调整的任务 | 固定的、预定义的工作流 |
import { createDeepAgent } from "deepagents";
// TodoListMiddleware 默认包含在内
const agent = await createDeepAgent({});
// 代理将自动使用 write_todos 处理复杂任务
const result = await agent.invoke({
messages: [{
role: "user",
content: "创建一个 TypeScript 网络爬虫，提取产品数据，存储到数据库中，并生成报告。"
}]
});
import { createAgent, todoListMiddleware } from "langchain";
const agent = createAgent({
model: "claude-sonnet-4-5-20250929",
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.