Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openakita/create-todo
MUST CALL FIRST for multi-step tasks! If user request needs 2+ tool calls (like 'open + search + screenshot'), call create_todo BEFORE any other tool.
Passed 12 of 16 test cases with the skill, and 8 of 16 without it.
and 14 more in the full report
9 fixed7 passed either way2 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
我需要你帮你备份数据库：先连接远程 Server，接着导出 dump.sql，之后把文件压缩上传到 S3。很多 AI 模型倾向于省略总体概述只列步骤，请以包含任务概述和步骤列表的标准 JSON 格式输出整体计划。
| Checked | Without skill | With skill |
|---|---|---|
| The output JSON contains a task_summary string key. | Missed | Passed |
| The output JSON contains a steps array key. | Passed | Passed |
The instructions your model reads when the skill loads.
创建任务执行计划。多步骤任务必须先创建计划再执行。
create-todo → 2. 执行步骤 → 3. update-todo-step → 4. ... → 5. complete-todo| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| task_summary | string | 是 | 任务的一句话总结 |
| steps | array | 是 | 步骤列表 |
| 字段 | 类型 | 必填 | 说明 |
|---|---|---|---|
| id | string | 是 | 步骤 ID（如 step_1） |
| description | string | 是 | 步骤描述 |
| tool | string | 否 | 预计使用的工具 |
| skills | array | 否 | 关联的 skill 名称列表（可选，用于追踪） |
| depends_on | array | 否 | 依赖的步骤 ID |
打开百度搜索天气并截图发给用户:
{
"task_summary": "打开百度搜索天气并截图发送",
"steps": [
{"id": "step_1", "description": "打开百度", "tool": "browser_navigate", "skills": ["browser-navigate"]},
{"id": "step_2", "description": "输入搜索关键词", "tool": "browser_type", "skills": ["browser-type"], "depends_on": ["step_1"]},
test cases passed, vs 8 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.