minitodo SKILL.md skillA

minitodo from dreamlonglll/mini-todo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dreamlonglll/mini-todo/minitodo@v2.1.0

Pins v2.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dreamlonglll/mini-todo
Path
cloud/skill/minitodo/SKILL.md
Versions recorded
5
Latest version
v2.1.0, committed Oct 2, 2026
First version recorded
May 14, 2026
Size
22,150 bytes
Repository stars
78
License
none declared

通过云端 HTTP API 读写用户的 mini-todo 待办;适合 today / add / done / list / search / show / update / delete 场景,可被 openclaw cron 调度(agent 自行拉数据 + 判断是否推送)做临期提醒。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# mini-todo Skill

让 Claude Code 通过云端 HTTP API 操作用户的 mini-todo 待办数据。底层数据通过
WebDAV 与 PC 端共享同一份 `sync-data.json.gz`:AI 的写入约 1.5 秒后(连续写入最多
攒 10 秒)推送到 WebDAV,PC 端下次同步即可见。

## 何时调用

用户说出下面意图时,先 `Bash` 调用本 skill 的 CLI:

- "今天有什么待办?" → `python ~/.claude/skills/minitodo/minitodo.py today --json`
- "未来 24h 有什么临期?" / 被 cron 唤起做提醒 → `list --pending --json` 后**你自己**按时间判断该推哪些
- "帮我加一个'买菜'到待办" → `add`
- "把 C3 / ID xxx 标记完成" → `done C3`(短码)或 `done <i64-id>`
- "看看所有未完成的高优先级" → `list --pending --priority high`
- "搜一下含'报告'的待办" → `search`
- "C3 / ID xxx 是什么?" → `show C3`
- "把 C3 / ID xxx 的截止时间改到 2026-05-20" → `update C3 endTime=2026-05-20`
- "删除 C3 / ID xxx" → `delete C3`

> **`C{seq}` 短码**是 cloud 给每个 todo 分配的递增编号(响应 JSON 里 `seq` 字段),
> 比 16 位完整 i64 id 更适合用户口语反馈;删除后短码不会被复用。所有 `done` / `show` /
> `update` / `delete` 的 id 位置都同时接受 `C{seq}` / `c{seq}`(大小写不敏感)和完整 i64 id。

非待办相关问题不要调用本 skill;它只覆盖 mini-todo 这一个领域。

## 安装

默认安装到 Claude Code 的 skill 目录;通过 `--target` 切到 openclaw 或两者都装。

```bash
bash install.sh                   # ~/.claude/skills/minitodo/(默认)
bash install.sh --target openclaw # ~/.openclaw/workspace/skills/minitodo/
bash install.sh --target both     # 两者都装
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dreamlonglll/mini-todo/minitodo@sha256:7d2b843e0d368c28

The line at the top of this page pins the label v2.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2d6ezzc2wyn4d4rr.svg)](https://markdownregistry.com/a/art_2d6ezzc2wyn4d4rr)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 14, 2026 and Oct 2, 2026, about one every 35 days.

versioncommittedcommitsizeaudit
v2.1.0 latest2026-10-02 f36b762 22,150 BA view · diff
v2.1.02026-10-02 26c7d5c 21,744 BA view · diff
v2.0.02026-08-09 45e2911 14,528 BA view · diff
v2.0.02026-05-14 3f5d412 14,328 BA view · diff
v2.0.02026-05-14 fa5df1c 13,755 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22150 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dreamlonglll/mini-todo · 78 stars · license none declared · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2d6ezzc2wyn4d4rr
GET https://markdownregistry.com/api/v1/resolve?ref=dreamlonglll/mini-todo/minitodo
GET https://markdownregistry.com/api/v1/blob/7d2b843e0d368c28f0657f9fd49ec1038792419019268151958e17a7e92449f4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dreamlonglll/mini-todo

trellis-before-dev SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-before-dev/SKILL.md · Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec…
git:20260507.1e204fb · audit A · 78 stars
trellis-brainstorm SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-brainstorm/SKILL.md · Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value…
git:20260507.1e204fb · audit A · 78 stars
trellis-break-loop SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-break-loop/SKILL.md · Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention…
git:20260507.1e204fb · audit A · 78 stars
trellis-check SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-check/SKILL.md · Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and…
git:20260507.1e204fb · audit A · 78 stars
trellis-continue SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-continue/SKILL.md · Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls…
git:20260507.1e204fb · audit A · 78 stars
trellis-finish-work SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-finish-work/SKILL.md · Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record…
git:20260507.1e204fb · audit A · 78 stars
trellis-meta SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-meta/SKILL.md · Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus…
git:20260507.1e204fb · audit A · 78 stars
trellis-update-spec SKILL.md skill
dreamlonglll/mini-todo · .agents/skills/trellis-update-spec/SKILL.md · Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something…
git:20260507.1e204fb · audit A · 78 stars
trellis-before-dev SKILL.md skill
dreamlonglll/mini-todo · .claude/skills/trellis-before-dev/SKILL.md · Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec…
git:20260507.1e204fb · audit A · 78 stars
trellis-brainstorm SKILL.md skill
dreamlonglll/mini-todo · .claude/skills/trellis-brainstorm/SKILL.md · Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value…
git:20260507.1e204fb · audit A · 78 stars
trellis-break-loop SKILL.md skill
dreamlonglll/mini-todo · .claude/skills/trellis-break-loop/SKILL.md · Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention…
git:20260507.1e204fb · audit A · 78 stars
trellis-check SKILL.md skill
dreamlonglll/mini-todo · .claude/skills/trellis-check/SKILL.md · Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and…
git:20260507.1e204fb · audit A · 78 stars

Every file in dreamlonglll/mini-todo

Browse by kind, by grade A, or by owner.