Dida Task

Community

lovekeji-ai

dida-task

滴答清单（Dida365）任务管理工具。通过官方 OpenAPI + 私有 API，让 agent 能读取（任务、清单、已完成任务、番茄/专注统计）和写入（创建、更新、完成、删除任务和清单）滴答清单的数据。当用户提到"滴答"、"dida"、"清单"、"todo"、"任务"、"提醒"、"番茄钟"、"专注"且明显是要操作清单 App 时使用。不支持 TickTick 国际版，只支持国内 dida365。

Overview

Publisher	lovekeji-ai
Repository	`keji-skills`
Skill name	`dida-task`
Stars	50
Forks	5
Bundled files	7
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
7 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by lovekeji-ai on GitHub. Read the source before you install it.

Installation

Install the Dida Task AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/lovekeji-ai/keji-skills/tree/main/skills/dida-task
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/lovekeji-ai/keji-skills.git /tmp/keji-skills
mkdir -p .claude/skills
cp -r /tmp/keji-skills/skills/dida-task .claude/skills/dida-task

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dida Task in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dida Task on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dida Task is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dida-Task：滴答清单 Agent 工具

让 agent 完全打通滴答清单（Dida365）：读、写、统计一应俱全。

何时使用

触发场景：

用户要写任务到滴答："加个任务"、"提醒我..."、"加到 dida / 滴答"
用户要读滴答数据："今天完成了哪些任务"、"我有哪些清单"、"专注了多久"
用户要统计/复盘："这周完成了什么"、"花了几个番茄在 X 上"

不要触发：

用户的"任务"明显指当前对话工作项，不是 App 里的任务
用户在专门的 GTD 笔记系统里操作（除非明确说"同步到滴答"）

首次使用

凭证未配置时，先引导用户走 setup：

bash
python3 scripts/dida.py setup

详细引导见 setup.md。

能力速查

所有命令统一入口：python3 scripts/dida.py <子命令>

读

命令	作用
`read list-projects`	列所有清单
`read list-columns <project>`	列 kanban 清单的分组（columns）
`read list-tasks <project>`	列某清单下未完成任务
`read get-task <task-id>`	拿单个任务详情
`read search <关键词>`	全量任务模糊搜索（按标题/内容）
`read today`	跨清单：今日到期的未完成任务，按清单分组
`read upcoming [--days N]`	跨清单：未来 N 天（默认 7）到期
`read by-tag <tag> [--prefix]`	按标签筛选；`--prefix` 含子标签（如 `12wy` 匹配 `12wy/a`）
`read list-tags`	列出账号所有标签（含父子关系、颜色）
`read completed-today`	今天已完成任务
`read completed-range <from> <to>`	按日期范围拉已完成任务

番茄/专注

命令	作用
`pomo today`	今天专注总时长 + 段数
`pomo by-task <task-id-或关键词>`	某任务花了几个番茄 / 多少分钟
`pomo stats <from> <to>`	按日期范围的专注统计（heatmap + 项目分布）

写

命令	作用
`write create-task --title <标题> [选项]`	创建任务
`write update-task <task-id> [选项]`	更新任务
`write complete-task <task-id>`	标记完成
`write delete-task <task-id>`	删除任务（默认 dry-run）
`write add-subtask <task-id> --title <标题>`	给任务追加一个子任务（checklist 项）
`write complete-subtask <task-id> <子任务-id-或关键词>`	标记某子任务完成
`write create-project --name <名字> [选项]`	创建清单
`write update-project <project-id> [选项]`	更新清单
`write delete-project <project-id>`	删除清单（默认 dry-run）

create-task / update-task 选项：

参数	说明
`--content <文本>`	备注内容
`--project <id\|名字>`	create-task：目标清单（默认收件箱）；update-task：移动到该清单
`--priority {0,1,3,5}`	0 无 / 1 低 / 3 中 / 5 高
`--due <YYYY-MM-DD[THH:MM]>`	截止时间
`--all-day`	全天任务（忽略时分）
`--repeat "RRULE:..."`	重复规则，如 `RRULE:FREQ=WEEKLY;BYDAY=MO`
`--column <id\|名字>`	kanban 分组（需配合 `--project`）
`--tags "a,b,c"`	标签数组，逗号分隔
`--items "step1\|step2\|step3"`	子任务（仅 create-task；竖线分隔，自动设 `kind=CHECKLIST`）

元

命令	作用
`setup`	首次配置（OAuth + cookie）
`refresh-token`	OAuth token 过期时重走授权
`refresh-cookie`	Cookie 失效时引导更新
`health`	检查 token / cookie 状态

所有命令支持 --json 输出结构化数据，方便 agent 解析。

Agent 使用准则

写操作默认确认：delete-task / delete-project 默认 dry-run，加 --confirm 才真删
批量写入要分步：一次创建多个任务时，先列计划→等用户确认→再调 API
批量必须限速：官方 API 限流 100 req/min per token（滚动 60s 窗口，超限返回 HTTP 500 exceed_query_limit，不是 429）。批量写入每条 sleep 1s，超过 50 条每 20 条歇 30s。注意 update-task/delete-task/complete-task 内部会调 _find_project_id_of_task，最坏遍历所有清单（N+1 次调用），是隐藏的限流杀手 —— 大批量操作前先 read list-projects 拿到 project id 直接传，能少一半请求
凭证失败要给指引：API 401/500 access_forbidden 时，不要重试，告诉用户跑哪个 refresh 命令
限流触发等满 60 秒：触发 exceed_query_limit 后等满 60s，不是 30s（滚动窗口）
输出尊重用户语境：用户问中文就用中文回，时间用北京时间

详细文档

setup.md — 首次配置完整流程（如何申请 client_id、拿 cookie）
api-reference.md — 官方 + 私有 API 端点速查
examples/usage.md — 常见用法示例

重要声明

已完成任务读取、番茄统计走的是滴答的私有 API（非官方公开），用 cookie 鉴权：

优点：功能完整（官方 OpenAPI 没有这些能力）
风险：滴答随时可能改、cookie 会过期（几周到几个月）
失败时 skill 会给出明确的 refresh 指引，不会卡死

所有写操作（建任务/改任务/删任务）走官方 OpenAPI，稳定可靠。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dida Task AI skill do?

Why use Dida Task on TypingMind?

Because you install it once and use it with any model. Dida Task is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dida Task in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lovekeji-ai/keji-skills/tree/main/skills/dida-task. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dida Task?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dida Task?

As many as you like. As long as a model supports skills, you can use Dida Task with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dida Task AI skill free?

Yes. It is published on GitHub by lovekeji-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Clawhub

openclaw

OrganizationPopular

Search ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.

Diagnosing Superpowers

obra

CommunityPopular

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so…

Brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Executing Plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Dida-Task：滴答清单 Agent 工具

何时使用

首次使用

能力速查

读

番茄/专注

写

元

Agent 使用准则

详细文档

重要声明

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now