← 返回 Skills 市场
fengye607

赛博鲁班日记

作者 fengye607 · GitHub ↗ · v1.2.0
cross-platform ⚠ suspicious
276
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install cyber-luban-diary
功能描述
AI diary service - push diary entries, query diaries, get AI analysis and cover images via HTTP API.
使用说明 (SKILL.md)

赛博鲁班日记

An AI-powered diary service. Push diary entries, retrieve them by date, get AI-generated analysis (feedback + keywords), and fetch cover images.

Setup

  1. Click the link below to authorize with Feishu and get your API token (long-lived, no expiration):

    https://image.yezishop.vip/api/openclaw/auth-redirect

  2. After Feishu login, copy the token displayed on the page.

  3. Set the token as an environment variable:

export AI_DIARY_TOKEN="your_token_here"

Usage

Push a diary entry

When the user wants to save or push a diary entry for a specific date:

curl -s -X POST "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN" \
  -H "Content-Type: application/json" \
  -d "{\"date\": \"$DATE\", \"content\": \"$CONTENT\"}" | jq .
  • date must be in YYYY-MM-DD format
  • content is the diary text

Get diary by date

When the user asks about a specific date's diary:

curl -s "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN/diaries?date=$DATE" | jq .

List recent diaries

When the user wants to see recent diary entries:

curl -s "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN/diaries?limit=$LIMIT&offset=$OFFSET" | jq .
  • limit defaults to 20, offset defaults to 0

Get a single diary by ID

curl -s "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN/diaries/$DIARY_ID" | jq .

Analyze a diary (AI feedback + keywords)

When the user wants AI analysis of a diary entry. Returns cached result if analysis already exists:

curl -s -X POST "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN/diaries/$DIARY_ID/analyze" \
  -H "Content-Type: application/json" | jq .

Response includes feedback (text review) and keywords (3 key terms).

Get diary cover image

curl -s "https://image.yezishop.vip/api/diary-hook/$AI_DIARY_TOKEN/diaries/$DIARY_ID/image" | jq .

Returns image field with the image URL, or null if no image exists.

Response Format

All endpoints return JSON with success: true/false. Diary objects contain:

  • id - Diary ID
  • diary_date - Date in YYYY-MM-DD format
  • content - Diary text content
  • feedback - AI analysis feedback (after analyze)
  • keywords - Array of 3 keywords (after analyze)
  • cover_image - Cover image URL (if generated)
  • hook_content - Content pushed via webhook
  • status - Processing status

Important Notes

  • The API token is tied to your Feishu account. Keep it secure.
  • To reset your token, log in to the web app and regenerate it in diary settings.
  • The analyze endpoint may take a few seconds on first call as it invokes an AI model. Subsequent calls return cached results instantly.
安全使用建议
This skill appears to implement a diary API using curl/jq, but exercise caution before installing: the setup asks you to log in via a third-party URL (image.yezishop.vip) that claims to 'authorize with Feishu' and to copy a long‑lived token. That token may grant broad access to your Feishu account and could be exposed because examples put it directly in request URLs. Before proceeding, verify the service's trustworthiness and privacy policy, confirm what token scopes are issued (prefer least privilege and short-lived keys), avoid using your primary Feishu account (create a dedicated account if possible), and prefer sending tokens in an Authorization header rather than embedding them in URLs. If you suspect the token is exposed, regenerate/revoke it immediately. If you need help assessing the service domain or safer invocation patterns, get more details from the skill author or the service operator before installing.
功能分析
Type: OpenClaw Skill Name: cyber-luban-diary Version: 1.2.0 The skill provides a legitimate diary management service that allows users to save, retrieve, and analyze diary entries via an external API (image.yezishop.vip). While it involves sending user-generated content to a third-party service and requires an authentication token, these actions are transparently documented and aligned with the skill's stated purpose. No evidence of malicious intent, credential theft, or unauthorized execution was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
The name/description (AI diary: push/query/analysis/cover images) align with the SKILL.md endpoints (image.yezishop.vip). However, the setup instructs users to 'authorize with Feishu' via an unfamiliar domain (image.yezishop.vip) — that raises questions about whether this is an official Feishu integration or a third party mediating Feishu auth.
Instruction Scope
Runtime instructions only call curl/jq against image.yezishop.vip endpoints (consistent with the described API). Concerns: the auth step directs users to click a third-party link that 'authorizes with Feishu' — the docs do not state what scopes the token has. The skill instructs embedding the token into the URL path for API calls, which can expose the token in logs, referers, and shell history. There are no instructions that read other files or env vars, but the auth redirect is the main scope creep/risk.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. Required binaries (curl, jq) match the provided curl/jq examples. Low installation risk because nothing is downloaded or written by the skill itself.
Credentials
Only one env var (AI_DIARY_TOKEN) is requested, which is proportionate, but the doc describes it as a 'long-lived' Feishu-linked token with no stated scopes. That is risky: a long-lived Feishu token could grant broader access to the user's account than needed. Additionally, placing the token in the URL path increases accidental exposure (logs, referers). The skill does not justify why a long-lived token or the specific scopes are required.
Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skills or system settings. It is user-invocable and allows autonomous invocation by default (platform standard).
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 cyber-luban-diary
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cyber-luban-diary 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
Setup 简化为直接链接授权,不再需要 curl 获取 auth URL
v1.1.0
更新域名为生产环境,授权方式改为直接跳转链接
v1.0.0
Initial release: push diary, query by date, AI analysis, cover images
元数据
Slug cyber-luban-diary
版本 1.2.0
许可证
累计安装 0
当前安装数 0
历史版本数 3
常见问题

赛博鲁班日记 是什么?

AI diary service - push diary entries, query diaries, get AI analysis and cover images via HTTP API. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 276 次。

如何安装 赛博鲁班日记?

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

赛博鲁班日记 是免费的吗?

是的,赛博鲁班日记 完全免费(开源免费),可自由下载、安装和使用。

赛博鲁班日记 支持哪些平台?

赛博鲁班日记 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 赛博鲁班日记?

由 fengye607(@fengye607)开发并维护,当前版本 v1.2.0。

💬 留言讨论