← 返回 Skills 市场
kazuya-ecnu

Daily Notes

作者 Kazuya · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ⚠ suspicious
112
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install daily-notes
功能描述
日常随笔记录,收录一切想记下来的东西——奇思妙想、灵感片段、日常感想、碎碎念、发现、备忘录,支持图片附件与多图关联。Daily notes with image attachments and multi-image association support.
使用说明 (SKILL.md)

daily-notes v1.1 / 日常随笔记录

数据文件 / Data Files(存放于 ~/.openclaw/workspace/notes-data/

  • ~/.openclaw/workspace/notes-data/notes.json — 随笔记录列表(含图片路径)
  • ~/.openclaw/workspace/notes-data/images/ — 图片附件目录,按 YYYY-MM-DD_描述.jpg 命名

数据格式 / Data Format

{
  "notes": [
    {
      "id": "uuid",
      "content": "记录内容 / Note content",
      "tags": ["想法", "技术", "生活", "碎碎念"],
      "status": "pending | in_progress | done | archived",
      "images": ["images/2026-04-06_场景描述.jpg", ...],
      "created_at": "YYYY-MM-DDTHH:mm:ss",
      "updated_at": "YYYY-MM-DDTHH:mm:ss"
    }
  ]
}

主动记录规则 / Proactive Capture Rule

用户的任何发言,无论是否带有明确目的,都应视为值得记录的随笔。 Any user message, regardless of whether it has a clear purpose, should be treated as worth recording.

  • 没有明确任务意图的发言 → 自动记入 daily-notes
  • 包含情绪、感想、碎碎念、随手想法的发言 → 自动记入 daily-notes
  • 有明确任务指令的发言(如"帮我写代码"、"查询天气")→ 正常执行任务,不要强制记录
  • 是否记录以是否承载了用户的想法、感受或意图为判断标准,而非以是否有工具执行为判断标准

操作 / Operations

  1. 记录随笔 / Record Note:解析内容 → 提取标签 → 生成 ID → 追加到 notes.json → 反馈已记录
  2. 查看列表 / List Notes:读取 notes.json → 按时间倒序展示 → 支持按标签或状态筛选
  3. 搜索记录 / Search:按关键词搜索 content 和 tags
  4. 更新状态 / Update Status:找到对应记录 → 更新 status 和 updated_at
  5. 关联图片 / Attach Images:用户发送图片时 → 追加到对应记录的 images 数组
  6. 删除记录 / Delete:软删除(archived)或彻底删除(含图片一并删除)

状态说明 / Status

  • pending — 待处理 / Pending(默认)
  • in_progress — 进行中 / In progress
  • done — 已完成 / Done
  • archived — 已归档/放弃 / Archived

标签分类 / Tags

  • 想法 / idea — 奇思妙想、创意点子
  • 技术 / tech — 技术实现、代码思路
  • 生活 / life — 日常感想、碎碎念
  • 碎碎念 / ramble — 随手记录的心情、吐槽
  • 备忘 / memo — 临时记录、待办提醒
  • 发现 / discovery — 学到的新东西、有趣的观察
  • 心情 / mood — 情绪、感受
  • 健康 / health — 身体、锻炼、饮食
  • 财务 / finance — 省钱,投资、理财
  • 可根据内容自由添加新标签 / Free to add custom tags

图片处理规则 / Image Rules

  • 用户发送图片时,保存到 images/ 目录
  • 文件名格式 / Filename format:YYYY-MM-DD_场景描述.jpg
  • images 字段存储相对于 notes-data/ 的相对路径列表,如 ["images/2026-04-06_xxx.jpg"]
  • 一条记录可关联多张图片(images 数组)/ Multiple images per note
  • 删除记录时,关联的图片一并删除 / Images deleted with note
  • 展示记录时,图片路径以相对路径形式呈现

注意事项 / Notes

  • content 尽量完整记录原始内容,保留原汁原味
  • content: write original thoughts faithfully, keep the raw voice
  • tags 自动提取或用户补充 / Auto-extracted or user-provided
  • 按时间倒序展示,最新的在最前面 / Newest first
  • 触发词已覆盖中英文 / Triggers available in both Chinese and English
安全使用建议
This skill implements a straightforward local note store, but its runtime policy to 'record any user message' is privacy-risky. Before installing, consider: (1) Do you want the agent to automatically log all casual messages? That can capture passwords, private info, or other sensitive text. (2) Ask the author or edit SKILL.md to require explicit user confirmation/command before recording (e.g., only save when user says '记一下' or 'record this'), or at minimum limit triggers. (3) Ensure stored data is acceptable to keep in plaintext under ~/.openclaw/workspace/notes-data/ (or add encryption/backups and a clear retention/deletion policy). (4) If you will allow autonomous invocation, be aware it can run without manual approval and produce continuous logs; consider disabling autonomous invocation for this skill. (5) Verify image handling (where images are stored, size limits, and deletion behavior) and manually inspect notes.json after first runs. If you cannot modify the SKILL.md or trust the skill's behavior, do not install or only enable it in a confined/test environment.
功能分析
Type: OpenClaw Skill Name: daily-notes Version: 1.2.0 The skill is a standard note-taking utility designed to store text and images locally in the user's workspace (~/.openclaw/workspace/notes-data/). While the SKILL.md contains a 'Proactive Capture Rule' instructing the AI to record most user messages as notes, this behavior is consistent with the stated purpose of a 'daily life log' and lacks any indicators of data exfiltration, unauthorized network access, or malicious execution. The agent.py script contains only basic file path helpers and JSON I/O logic with no high-risk functions.
能力评估
Purpose & Capability
Name/description, data formats, and the provided agent.py are consistent with a local note-taking skill that stores notes and image attachments under ~/.openclaw/workspace/notes-data/. There are no unexpected external dependencies or credentials. However, the SKILL.md's proactive capture rule (recording 'any user message') goes beyond typical note-taking expectations and expands the stated purpose into always-on logging.
Instruction Scope
SKILL.md explicitly instructs the agent to treat any user message (unless it contains an explicit task intent) as worth recording and to automatically append such messages to notes.json. This grants the skill broad discretion to collect arbitrary user content, which can include sensitive data (passwords, private messages, PII) without explicit consent or confirmation. The instructions lack retention, encryption, or access-control guidance and leave ambiguity about when and how recording is triggered.
Install Mechanism
No install spec / downloads are present. The only code file (agent.py) is small and only reads/writes a JSON file under ~/.openclaw/workspace/notes-data/ and constructs image paths. No external network endpoints or third-party packages are installed. This is low-risk from an install-code sourcing perspective.
Credentials
The skill requests no environment variables, credentials, or external tokens—appropriate for a local notes tool. However, because the skill will store free-form user messages and image paths in plain JSON under the workspace, it can collect sensitive content without additional safeguards (encryption, ACLs).
Persistence & Privilege
always:false and no explicit persistence flags are requested, but the SKILL.md's proactive-capture rule combined with normal autonomous invocation (disable-model-invocation:false) means the agent could be invoked automatically and record user messages frequently. That combination effectively allows continuous local logging even though the skill did not request an 'always' privilege at registry level.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install daily-notes
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-notes 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.0
新增主动记录规则:任何无明确目的的发言都自动记入随笔,无需用户明确要求。Proactive capture: any message without a clear task purpose is automatically recorded as a note.
v1.1.0
新增图片附件支持,支持一条记录关联多张图片,支持中英文触发词。Added image attachment support with multi-image association, bilingual triggers.
v1.0.0
重构为日常随笔记录,收录奇思妙想、碎碎念、备忘等一切想记下来的东西,支持多标签分类和状态追踪
元数据
Slug daily-notes
版本 1.2.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Daily Notes 是什么?

日常随笔记录,收录一切想记下来的东西——奇思妙想、灵感片段、日常感想、碎碎念、发现、备忘录,支持图片附件与多图关联。Daily notes with image attachments and multi-image association support. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 112 次。

如何安装 Daily Notes?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install daily-notes」即可一键安装,无需额外配置。

Daily Notes 是免费的吗?

是的,Daily Notes 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Daily Notes 支持哪些平台?

Daily Notes 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Daily Notes?

由 Kazuya(@kazuya-ecnu)开发并维护,当前版本 v1.2.0。

💬 留言讨论