一键导入
todoist-organize-tasks
Intelligently organize Todoist projects, tasks, labels and sections — search before creating, learn user patterns, smart decomposition
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
Intelligently organize Todoist projects, tasks, labels and sections — search before creating, learn user patterns, smart decomposition
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
Analyze spreadsheet data intelligently - understand structure, choose right analysis tool (SQL/pivot/chart), apply formatting, present insights.
Create charts and visualizations in Google Sheets — detect data structure, select chart type, format for clarity, present insights
Generate an editable Microsoft Word (.docx) document — reports, letters, memos, structured docs. Use when the user wants a Word file. Built with docx-js (Node) for high fidelity.
Generate a polished, printable PDF — reports, letters, invoices, resumes, one-pagers. Use when the user wants a PDF document. Typst is the primary engine; LaTeX (tectonic) is the fallback for niche packages or specific academic/journal templates.
Generate a PowerPoint (.pptx) slide deck — pitch decks, reviews, summaries. Use when the user wants slides. Built with pptxgenjs (Node) for native, editable slides and charts.
Generate an Excel (.xlsx) workbook or a CSV file — tables, financial models, data exports, formatted reports with charts. Use when the user wants a spreadsheet or CSV. Built with openpyxl + pandas (Python).
| name | todoist-organize-tasks |
| description | Intelligently organize Todoist projects, tasks, labels and sections — search before creating, learn user patterns, smart decomposition |
| target | todoist_agent |
User wants to create a project, organize tasks, set up a task structure, or batch-manage their Todoist workspace.
Before creating anything, gather context:
TODOIST_GET_ALL_PROJECTS → existing projects, hierarchy, colors
TODOIST_GET_ALL_PERSONAL_LABELS → existing labels
Think:
TODOIST_GET_ALL_PROJECTS, then filter by name)Always search first:
TODOIST_GET_ALL_PROJECTS() → filter by project name to check for duplicates
TODOIST_GET_ALL_PERSONAL_LABELS() → filter by label name to check if label exists
If a matching project exists:
When creating a new project:
TODOIST_CREATE_PROJECT(
name="Project Name",
color="blue", # Match user's color patterns
view_style="list", # or "board" for kanban
parent_id="..." # For sub-projects
)
Then add sections for logical groupings:
TODOIST_CREATE_SECTION(project_id, name="Planning")
TODOIST_CREATE_SECTION(project_id, name="In Progress")
TODOIST_CREATE_SECTION(project_id, name="Done")
Break down the user's request into tasks intelligently:
Priority mapping:
Date intelligence:
due_string for natural language: "tomorrow", "next Monday at 3pm", "every Friday"due_date for specific dates: "2025-03-15"duration + duration_unit for time estimatesTODOIST_CREATE_TASK(
content="Task title",
project_id="...",
section_id="...",
priority=3,
due_string="next Monday",
labels=["existing-label"],
description="Additional context"
)
Sub-tasks: Use parent_id to create hierarchy:
TODOIST_CREATE_TASK(content="Parent task", project_id=...) → get task_id
TODOIST_CREATE_TASK(content="Sub-task 1", parent_id=task_id)
TODOIST_CREATE_TASK(content="Sub-task 2", parent_id=task_id)
Create labels only if they don't exist:
TODOIST_GET_ALL_PERSONAL_LABELS() → no label named "urgent"
TODOIST_CREATE_LABEL(name="urgent", color=30) # berry_red
Label strategy:
After creating, present the structure:
Project: "Q1 Marketing Plan" (blue)
Planning (3 tasks)
- Research competitors (due: Mon, p2)
- Define target audience (due: Tue, p2)
- Set budget (due: Wed, p1)
Execution (2 tasks)
- Launch campaign (due: next Fri, p1)
- Monitor metrics (recurring: every Mon, p3)
Labels used: marketing, q1