一键导入
write-todos-skill
Create and manage structured task lists for planning and tracking complex multi-step operations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Create and manage structured task lists for planning and tracking complex multi-step operations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | write-todos-skill |
| description | Create and manage structured task lists for planning and tracking complex multi-step operations. |
| allowed-tools | write_todos |
| metadata | {"author":"machina","version":"2.0","category":"automation"} |
You have access to the write_todos tool. Use it to plan, track, and update a structured task list when working on complex objectives.
Use write_todos when the task requires 3 or more steps. Do NOT use it for trivial requests that you can complete in 1-2 tool calls.
Follow this loop for every complex task:
Before doing any work, call write_todos to create your plan. Break the objective into specific, actionable steps. Mark the first task in_progress immediately.
{
"todos": [
{"content": "Identify the relevant source files", "status": "in_progress"},
{"content": "Implement the core logic", "status": "pending"},
{"content": "Add error handling", "status": "pending"},
{"content": "Verify the changes work", "status": "pending"}
]
}
After completing a step, call write_todos again with the updated list. Mark the finished task completed and the next task in_progress. Do this after every step -- do not batch updates.
{
"todos": [
{"content": "Identify the relevant source files", "status": "completed"},
{"content": "Implement the core logic", "status": "in_progress"},
{"content": "Add error handling", "status": "pending"},
{"content": "Verify the changes work", "status": "pending"}
]
}
If you discover new work or a step becomes irrelevant, update the list. Add new tasks, remove unnecessary ones, or reword tasks to be more accurate.
{
"todos": [
{"content": "Identify the relevant source files", "status": "completed"},
{"content": "Implement the core logic", "status": "completed"},
{"content": "Fix unexpected edge case in parser", "status": "in_progress"},
{"content": "Add error handling", "status": "pending"},
{"content": "Verify the changes work", "status": "pending"}
]
}
Keep working until every task is completed. Always have at least one task in_progress unless all are done.
write_todos call per turn -- never call it multiple times in parallel.in_progress before starting a task, completed after finishing it.completed if there are unresolved errors or the work is partial.| Field | Type | Description |
|---|---|---|
| todos | array | Full list of todo items |
| todos[].content | string | Specific, actionable task description |
| todos[].status | string | pending, in_progress, or completed |
Drive the user's real Chrome over raw CDP by writing Python against browser-harness helpers - screenshot, coordinate clicks, JS evaluation, form fill, tabs. For tasks needing full freedom or the user's own logins.
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
Deploy sites and apps to Vercel, inspect deployments, stream logs, and manage projects/env/domains via the Vercel CLI. Deploy a directory and get back the live deployment URL; everything else the CLI supports is available through the custom command passthrough.
Use this skill to generate well-branded interfaces and assets for MachinaOS (zeenie.ai), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
Run AI-generated Python in a hard sandbox (Pydantic Monty) with enforced time + memory limits and opt-in capabilities. Use for untrusted code; supports a Python subset.
Interactive browser automation - navigate, click, type, fill forms, take screenshots, get accessibility snapshots. Supports system Chrome/Edge via auto-detection.