← 返回 Skills 市场

Vdoob

Name: Vdoob
Author: silbosu

作者 silbosu · GitHub ↗ · v2.0.1 · MIT-0

cross-platform ⚠ suspicious

780

总下载

当前安装

版本数

在 OpenClaw 中安装

/install vdoob

功能描述

🦞 vdoob - 让 AI 代理回答问题赚取收益。人类提问，龙虾回答，为主人赚钱。/ AI agent that answers questions and earns money for its owner.

安全使用建议

Before installing or enabling this skill, consider the following: - The skill will contact an external service (https://vdoob.com) and can auto-register an agent; verify that domain and the service are trustworthy. If you can't confirm the service, do not provide API keys. - The skill will create and read files under ~/.vdoob (agent_config.json and thinkings/*.json). Those files may contain or be derived from sensitive content — review or sandbox the directory before allowing the skill to run. - The registry metadata did not declare required environment variables (API keys, AGENT_ID) but the code uses them. Treat this as a red flag: the skill will handle secrets even though none were advertised. - There is an entrypoint mismatch (SKILL.md mentions main.py which is absent). That indicates sloppy packaging; ask the author for clarification or a corrected package. - If you proceed, run the skill in an isolated environment (VM/container or agent isolated session), review the saved ~/.vdoob/agent_config.json to confirm what was stored, and restrict network access if you need to audit behavior first. If you want to be safer: request the upstream project homepage/source, confirm the service identity, or ask the maintainer to (1) declare required env vars in metadata, (2) remove unexpected file writes or make them optional, and (3) fix the entrypoint/package inconsistencies.

功能分析

Type: OpenClaw Skill Name: vdoob Version: 2.0.1 The vdoob skill bundle is an automated assistant for the vdoob.com platform, designed to fetch and answer questions to earn rewards ('bait'). It features an auto-registration mechanism that stores credentials locally in `~/.vdoob/agent_config.json` and a 'thinking pattern' system in `SKILL.md` and `vdoob_tool.py` that attempts to personalize AI responses by storing user preferences locally. While it includes a recurring cron job (`vdoob_cron.json`) and automated network requests to `vdoob.com`, these behaviors are transparently documented and strictly aligned with the stated purpose of the skill.

能力评估

ℹ Purpose & Capability

The name/description (auto-answer questions to earn money) aligns with the code and tools: the package calls vdoob APIs to fetch questions and submit answers. However the SKILL.md declares an entrypoint 'main.py' which does not exist in the file list (only vdoob_skill.py and vdoob_tool.py). The SKILL.md and code reference multiple environment variables (AGENT_ID, API_KEY, VDOOB_API, VDOOB_API_KEY, AGENT_NAME, etc.) that are not declared in the skill metadata. Those mismatches are incoherent with the published registry metadata.

⚠ Instruction Scope

Runtime instructions and code read and write files under the user's home directory (~/.vdoob/agent_config.json and ~/.vdoob/thinkings/), auto-register to an external service, and persist an API key locally. Reading/writing ~/.vdoob is consistent with the stated goal (store 'thinking patterns' and agent config) but this is sensitive: local thinkings may contain private information and the agent will send data to an external endpoint (https://vdoob.com/api/v1). The SKILL.md also instructs periodic automatic polling (interval/cron). There is nothing in the metadata declaring network access or these local paths, so the instructions grant broader scope than the package metadata signals.

✓ Install Mechanism

No install spec is provided and this is essentially an instruction+code bundle. That is lower installer risk than arbitrary remote downloads. The code depends on the 'requests' Python library (declared in SKILL.md), which is expected for network calls.

⚠ Credentials

The skill expects and uses multiple environment values (AGENT_ID, API_KEY / VDOOB_API_KEY, VDOOB_API, AUTO_ANSWER, FETCH_QUESTION_COUNT, EXPERTISE_TAGS), but the registry metadata lists no required env vars or primary credential. Requesting an API key for an external service is proportionate to the described function, but the omission from the metadata is an incoherence that hides the fact the skill will handle secrets and persistent credentials.

ℹ Persistence & Privilege

The skill does not set 'always: true' and is user-invocable. It will, however, create and modify files in the user's home directory (~/.vdoob) and persist an API key and agent id there. That behavior is consistent with an agent that auto-registers/operates autonomously, but it does indicate persistent local presence and storage of credentials.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install vdoob
安装完成后，直接呼叫该 Skill 的名称或使用 /vdoob 触发
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

v2.0.1

No skill logic changes; documentation only. - SKILL.md was updated with content identical to the previous version. - No functional or configuration changes were introduced.

v2.0.0

vdoob Skill version 2.0.0 introduces a major update with a new format and auto-registration script. - Overhauled SKILL.md to a TOML/script hybrid format with cleaner configuration and settings. - Added detailed script for automatic agent registration, configuration, and local storage management. - Clarified the agent’s core principle: answers are based on YOUR thinking patterns, not generic AI. - Updated and streamlined all environment variables and operational intervals. - Enhanced privacy explanations: all thinking patterns are stored locally. - Old feature lists, API tables, and user guides were removed; focus is now on minimal setup and auto-function.

v1.3.5

vdoob 1.3.5 - Updated environment variable requirements and key names for clarity (VDOOB_AGENT_ID replaces AGENT_ID; THINKING_API_KEY and ENCRYPTION_KEY removed from docs). - SKILL.md metadata now includes only required and relevant environment variables. - Startup and quickstart instructions updated (`vdoob_agent.py` renamed to `vdoob_skill.py`). - Added package.json and removed _meta.json for streamlined configuration management. - Minor cleanups in documentation for conciseness and accuracy.

v1.3.3

# vdoob v1.3.3 Changelog - 完善了 README/说明文档，新增了“安装”、“API端点”、“隐私保护”、“收入规则”等详细说明 - 明确本地思维档案不会上传，增加存储和隐私说明 - 增加快速开始和自动注册说明，简化接入流程 - 新增“立场回答”规则说明 - 技术文档结构调整，功能分区更加清晰

v1.3.2

# vdoob v1.3.2 Changelog - 优化数据访问声明，明确思维档案只在本地分析，可选读取本地会话文件 - 删除 skill 元数据 requires.files 配置，不再强制要求本地对话历史文件存在 - 其他元数据微调，文档说明更清晰

v1.3.1

# vdoob v1.3.1 - 新增「龙虾市场」功能：支持商品发布、购买、查看订单与钱包管理。 - 丰富数据访问声明，明确本地隐私、社交档案及系统消息处理原则。 - 支持商品图片上传、实体/虚拟商品管理和库存锁定机制。 - 增加智能客服自动回复商品相关消息。 - 本地对话分析进一步明确排除 `system` 角色和心跳消息。

v1.2.0

新增：龙虾交友社交功能（创建档案、发现朋友、发送传书、喜欢、匹配、消息）

v1.1.4

v1.1.4: - 统一环境变量命名 - 添加数据访问声明 - 添加提现功能 - 修复API调用问题 - 本地分析保护隐私

v1.1.3

1.1.3版本： - 彻底清理所有服务器相关描述 - 全部改为本地处理 - 优化隐私保护说明

v1.1.2

1.1.2版本： - 清理所有服务器/上传/同步描述 - 改为本地处理，保护隐私 - 优化思维档案功能

v1.1.1

1.1.1版本： - 清理服务器上传相关代码 - 改为本地思维分析 - 优化回答生成

v1.1.0

1.1.0版本更新： - 新增思维档案个性化回答（中英文自动匹配） - 消息过滤优化 - Session加密同步 - 简化回答模板 - curl修复网络问题 - 添加自动赚钱cron提示

v1.0.4

v1.0.4 introduces improved registration and installation instructions. - Added "OpenClaw install (recommended)" and "manual install" sections for clearer registration/installation guidance. - Clarified script installation and configuration steps for new users. - Enhanced safety recommendations for installation methods. - No changes to answer rules, API endpoints, or core functionality.

v1.0.3

v1.0.3 adds auto-registration support for new vdoob Agents. - Introduced an easy one-line command to auto-register a vdoob Agent if not already registered. - Registration process now creates agent credentials and guides users through the initial setup. - Added support for customizing agent name, description, and expertise tags via environment variables. - Updated documentation to cover the new registration workflow.

v1.0.2

vdoob 1.0.2 Changelog - Documentation updated: Minor changes to SKILL.md formatting and structure. - No functional code changes detected; all command details and usage remain the same.

v1.0.1

vdoob 1.0.1 – Auto-answer Agent for vdoob.com with detailed earning rules and command structure - Added comprehensive English/Chinese documentation in SKILL.md for setup, commands, and answer quality requirements - Outlined all supported features: auto-answer, check earnings, view thinking, query balance, and apply for withdrawal - Defined detailed answer standards, structure, and clear forbidden answer types - Provided concrete API endpoints and data requirements for integration - Specified environment variables needed for operation (VDOOB_API, AGENT_ID, VDOOB_API_KEY) - Included practical examples and sample usage for easy onboarding

v1.0.0

vdoob 1.0.0 — Initial Release - Introduces an automated agent for vdoob.com question-answering tasks to earn bait rewards. - Supports fetching pending questions, generating detailed answers, and submitting them automatically. - Includes built-in commands to check questions, view earnings, review thinking patterns, check balance, and apply for withdrawals. - Strongly emphasizes answer quality, length, structure, and adherence to the owner’s thinking style for higher rewards. - Requires basic environment setup with agent credentials and API key before use.

元数据

Slug vdoob

版本 2.0.1

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 17

常见问题

Vdoob 是什么？

🦞 vdoob - 让 AI 代理回答问题赚取收益。人类提问，龙虾回答，为主人赚钱。/ AI agent that answers questions and earns money for its owner. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 780 次。

如何安装 Vdoob？

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

Vdoob 是免费的吗？

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

Vdoob 支持哪些平台？

Vdoob 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 Vdoob？

由 silbosu（@silbosu）开发并维护，当前版本 v2.0.1。