据 AlphaMoat 统计,截至 2026-09,4todo 累计下载 3,561 次、获 3 个星标,在全部 5,078 个 AI 技能中排名第 3,075 位,在「AI 智能体」分类(969 个)中排名第 623 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 112 | 3,561 | 3 | - |
| SkillHub ↗ | 189 | 3,519 | 3 | — |
各平台的计数口径不同,统计时间不一致。
需要 curl 和从受保护环境注入的 FOURTODO_API_TOKEN,不将凭据贴入聊天或日志。先列工作区和任务,再执行获准创建、完成、移动或循环任务变更,并重新查询核对。账户变更尤其循环删除或排期修改须确认。循环任务重排只改象限,不改相对顺序。凭据无效或工作区只读时停止重试,并遵守限流。尽可能使用可撤销最小权限令牌;共享主机上命令参数可能泄露凭据。
资料发布于 2026-10-27
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 3,561 | — | 3 |
| 2026-08 | 3,420 | +4.4% | 3 |
| 2026-07 | 3,275 | +10.1% | 3 |
| 2026-06 | 2,974 | +5.2% | 3 |
| 2026-05 | 2,828 | — | 3 |
| 2026-03 | 2,384 | — | 3 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: 4todo description: Manage 4todo (4to.do) from chat. Capture tasks, prioritize with the Eisenhower Matrix, reorder, complete, and manage recurring tasks across workspaces. --- # 4todo [4to.do](https://4to.do) Eisenhower Matrix To‑Do List ## Goal
- Use `curl` to call the 4todo API (`https://4to.do/api/v0`) to manage:
- workspaces
- todos
- recurring todos
- Store the token in a way that is injectable but not leak-prone (prefer OpenClaw per-run env injection; do not paste secrets into prompts, logs, or repo files).
## Required Environment Variable
- `FOURTODO_API_TOKEN`: your 4todo API token (Bearer token)
- If missing, ask the user to set it via OpenClaw config (do not ask them to paste the token into chat).
## Runtime Requirement
- `curl` must be available on `PATH` (and inside the sandbox container, if the agent is sandboxed).
## User-facing output rules (important)
- Be non-technical by default. Focus on outcomes, not implementation.
- Avoid mentioning: curl, endpoints, headers, API mechanics, JSON payloads, config patches.
- Mention technical details only when debugging or if the user explicitly asks “how does it work?”.
- Do not print internal IDs by default:
- Do **not** show `ws_...`, `todo_...`, `rec_todo_...` unless the user asks.
- Refer to workspaces and tasks by **name**.
- If disambiguation is needed (duplicate names), ask a clarifying question and present a short numbered list of names; only offer IDs if the user requests them.
- Quadrants:
- In chat, prefer plain language: “urgent & important”, “important (not urgent)”, “urgent (not important)”, “neither”.
- Use `IU | IN | NU | NN` internally for API calls. Only show codes if the user uses codes first or explicitly asks.
### Examples (preferred)
Workspaces:
```
Your workspaces:
1) Haoya (default)
2) 4todo
3) Echopark
```
Todos (summary):
```
Urgent & important:
1) UK company dissolution
2) Hetzner monthly payment (recurring, monthly)
Important (not urgent):
1) Weekly review (recurring, Fridays)
```
## Store / Inject the Token in OpenClaw (recommended)
OpenClaw can inject environment variables only for the duration of an agent run (then restores the original env), which helps keep secrets out of prompts.
Recommended (production): set `FOURTODO_API_TOKEN` in your Gateway process environment using your hosting provider’s secret store, and do not store tokens in chat logs.
### Host runs (not sandboxed): use `skills.entries`
Edit `~/.openclaw/openclaw.json`:
```json5
{
skills: {
entries: {
"4todo": {
enabled: true,
env: {
FOURTODO_API_TOKEN: "YOUR_4TODO_API_TOKEN"
}
}
}
}
}
```
Notes:
- `skills.entries.<skill>.env` is injected only if the variable is not already set.
### Sandboxed sessions: use `agents.defaults.sandbox.docker.env`
When a session is sandboxed, skill env injection does **not** propagate into the Docker container. Provide the token via Docker env:
```json5
{
agents: {
defaults: {
sandbox: {
docker: {
env: {
FOURTODO_API_TOKEN: "YOUR_4TODO_API_TOKEN"
}
}
}
}
}
}
```
## Request Conventions
- Every request must include `Authorization: Bearer <token>`.
- Requests with a JSON body must include `Content-Type: application/json`.
- `GET /todos` requires a `workspace` query parameter.
- Quadrants: `IU | IN | NU | NN` (internal).
## Workflow (recommended order)
Copy this checklist and keep it updated while executing:
```
Task checklist:
- [ ] List workspaces (pick `ws_...`)
- [ ] List todos for that workspace
- [ ] Perform the requested mutation (create / complete / reorder / recurring)
- [ ] Re-fetch to verify the change
```
1. `GET /workspaces`: pick a target `ws_...` (usually the default workspace).
2. `GET /todos?workspace=ws_...`: fetch todos (grouped by quadrant).
3. Create: `POST /todos`.
4. Complete: `POST /todos/:id/complete` (idempotent).
5. Reorder / move quadrant: `POST /todos/reorder`.
6. Recurring todos: use the `/recurring-todos` endpoints.
## HTTP Examples (curl)
This skill intentionally uses `curl` for maximum portability across OSes and environments.
Notes:
- HTTPS only (`https://4to.do/api/v0`).
- Always pass the token via `FOURTODO_API_TOKEN` (never paste tokens into chat).
```bash
curl -sS -H "Authorization: Bearer $FOURTODO_API_TOKEN" -H "Accept: application/json" "https://4to.do/api/v0/workspaces"
curl -sS -H "Authorization: Bearer $FOURTODO_API_TOKEN" -H "Accept: application/json" "https://4to.do/api/v0/todos?workspace=ws_...&show=all"
curl -sS -X POST -H "Authorization: Bearer $FOURTODO_API_TOKEN" -H "Accept: application/json" -H "Content-Type: application/json" --data-raw '{"name":"...","quadrant":"IU","workspace_id":"ws_..."}' "https://4to.do/api/v0/todos"
curl -sS -X POST -H "Authorization: Bearer $FOURTODO_API_TOKEN" -H "Accept: application/json" "https://4to.do/api/v0/todos/todo_.../complete"
curl -sS -X POST -H "Authorization: Bearer $FOURTODO_API_TOKEN" -H "Accept: application/json" -H "Content-Type: application/json" --data-raw '{"moved_todo_id":"todo_...","previous_todo_id":"todo_...","next_todo_id":null,"quadrant":"IN"}' "https://4to.do/api/v0/todos/reorder"
```
Note: if `moved_todo_id` starts with `rec_todo_`, the API updates only the recurring todo quadrant and ignores `previous_todo_id/next_todo_id`.
## Common Error Handling (agent guidance)
- `401 token_expired / invalid_token`: stop retrying; ask the user to create a new token in 4todo settings and update OpenClaw config.
- `402 WORKSPACE_RESTRICTED`: the workspace is read-only; do not retry mutations; switch workspace or prompt user to upgrade/unlock.
- `429 rate_limited`: honor `Retry-After` / `X-RateLimit-*` and back off before retry.
- `400 Invalid quadrant type`: ensure quadrant is one of `IU|IN|NU|NN`.
## Reference
- Full API doc bundled with this skill: `{baseDir}/references/api_v0.md`
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把 agent 的记忆与跨技能状态存成带类型和约束的知识图谱的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。