What makes Bilibili Messager | B站私信助手 notable?

1.9K downloads. Trust evidence available

How should Bilibili Messager | B站私信助手 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Bilibili Messager | B站私信助手

Send Bilibili DMs, reply to messages, read chat history via browser automation. | 通过浏览器自动化发送 B 站私信、回复消息、读私信、看聊天记录。 Skill: Bilibili Messager | B站私信助手 Owner: moroiser Summary: Send Bilibili DMs, reply to messages, read chat history via browser automation. | 通过浏览器自动化发送 B 站私信、回复消息、读私信、看聊天记录。 Tags: latest:1.4.8 Version history: v1.4.8 | 2026-05-04T18:13:16.239Z | user 1. Fixed: _meta.json version consistency with registry. 修复：_meta.json 版本号与 registry 一致。 v1.4.7 | 2026-05-04T18:05:43.979Z | user 1. Fixed: _meta.json version consistency

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

1.4.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 1.4.8release · observed May 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1708w2t7w31qf7b0gsy7kamnx83gqa6:bilibili-messager

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-moroiser-bilibili-messager/snapshot"

Documentation

CLAWHUB

77,663 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: Bilibili Messager | B站私信助手
description: |
  Send Bilibili DMs, reply to messages, read chat history via browser automation. | 通过浏览器自动化发送 B 站私信、回复消息、读私信、看聊天记录。
metadata:
  "openclaw":
    requires:
      bins: ["browser"]
      browser_profiles: ["openclaw"]  # 必须使用 openclaw profile，且已登录 Bilibili
    runtime:
      credentialExpectations:
        - "Bilibili 已登录的浏览器会话（openclaw profile）"
      filesystemWrites:
        - "~/.openclaw/workspace/skills/bilibili-messager/"
        - "~/.openclaw/workspace/projects/bilibili-messager/"
    warning:
      - "发送操作需要用户两步验证确认"
      - "读取聊天记录会将私信内容暴露到 agent 上下文，仅读取你愿意分享的内容"
      - "使用独立 openclaw profile，不与其他账号混用"
---

# Bilibili Messager | B站私信助手

## ⚠️ 安全声明

本技能通过已登录的 Bilibili 浏览器会话读写私信。

**限制：**
- 只使用独立的 `openclaw` profile（不混用其他账号）
- 发送前必须两步验证确认目标账号和消息内容
- 读取模式仅用于你愿意暴露给 agent 的会话内容
- 不要用于读取高度敏感或非自愿的私人对话

## 前置要求 | Prerequisites

| 条件 | 说明 |
|------|------|
| **Browser profile** | 必须使用 `openclaw` profile（已通过 `browser` 工具启动并登录 Bilibili） |
| **登录状态** | Bilibili 账号已在 `openclaw` profile 中保持登录态 |
| **账号确认** | 发送操作前，技能会要求用户明确确认目标账号和消息内容 |

### 为什么需要 openclaw profile？

本技能通过在 Bilibili 私信页面执行 DOM JavaScript（`querySelector`、`innerText`、`click` 等）实现消息读取和发送。这些操作需要浏览器环境持有有效的 Bilibili 登录会话。

- `openclaw` profile 由 OpenClaw 启动和管理，独立于 Morois 的日常浏览器 profile
- 技能仅在 Bilibili 私信页（`message.bilibili.com`）域内执行 DOM 操作，无法访问其他网站
- 任何对外发送操作均需用户明确确认，不会自动发送

---

## 模式 | Mode

> 读取本 SKILL.md 后，先确认当前任务属于哪种模式，再跳转对应章节执行。

| 模式 | 说明 |
|------|------|
| **send** | 发送新私信（必须两步验证） |
| **reply** | 回复现有会话中的消息（必须两步验证） |
| **read** | 读取聊天记录（只读，不写入任何内容） |

---

## 通用原则 | General Principles

1. **Browser profile**：使用 `openclaw` profile（已登录 Bilibili）
2. **两步验证**：发送类操作（send / reply）必须两步验证，不可跳过
3. **只读优先**：读取聊天记录使用 read 模式，不执行任何写入操作
4. **发送前确认**：执行任何对外发送前，必须先向用户确认目标账号和消息内容
---

## 发送私信 | Mode: Send

### 步骤 1：打开私信页并确认登录

```
browser action=open targetUrl=https://message.bilibili.com/#/whisper
```

检查页面是否跳转到登录页。若跳转到登录页，停下来让用户完成登录。

### 步骤 2：找到目标会话

在左侧会话列表中找到目标联系人。可以通过文字搜索或滚动列表。

- 使用 `browser action=act evaluate` 配合 DOM 查询找到目标会话
- 找到后点击进入会话

### 步骤 3：两步验证（强制，必须执行）

#### 第一步（AI 内部执行，不输出给用户）

- 确认已正确进入目标会话（检查 URL 包含 `mid` 参数或页面标题显示对方名字）
- 确认消息内容已准备完毕
- 检查消息长度（不超过 500 字）

#### 第二步（输出给用户，等待明确确认）

向用户汇报以下全部内容，**确认前不得写入或发送**：

| 汇报项 | 内容 |
|--------|------|
| 目标账号 | 会话对方的名字 |
| 消息内容 | 将要发送的完整内容 |
| 字数 | 是否在 500 字以内 |

**确认标志**：用户明确回复「好」「确认」「发」「发吧」「发送」等。

### 步骤 4：写入消息

使用 `innerText` 方式写入（经验证有效）：

```javascript
() => {
  var editor = document.querySelector('.content-input, [contenteditable="true"]');
  if (!editor) return 'editor not found';
  editor.focus();
  editor.innerText = '消息内容';
  editor.dispatchEvent(new Event('input', {bubbles: true}));
  return 'typed';
}
```

### 步骤 5：点击发送按钮

```javascript
() => {
  var btns = document.querySelectorAll('button, [class*="btn"]');
  for (var btn of btns) {
    if ((btn.textContent || '').includes('发送')) {
      btn.click();
      return 'sent';
    }
  }
  return 'send button not found';
}
```

**注意**：

_meta.json

{
  "ownerId": "kn75k53tcdhqwka2fra5x817p9821zpb",
  "slug": "bilibili-messager",
  "version": "1.4.8",
  "publishedAt": 1777918396239
}

skill-card.md

## Description:

Sends Bilibili DMs, replies to messages, and reads chat history through a logged-in browser session.

This skill is ready for commercial/non-commercial use.

## Publisher:

[moroiser](https://clawhub.ai/user/moroiser)

### License/Terms of Use:

MIT-0

## Use Case:

External users who manage Bilibili conversations use this skill to read selected private-message history and draft, send, or reply to DMs after explicit confirmation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The agent may read selected Bilibili private-message content into its context.

Mitigation: Only read conversations the user is willing to share, avoid highly sensitive or non-consensual private messages, and use a dedicated openclaw browser profile.

Risk: The skill can send DMs from the logged-in Bilibili account.

Mitigation: Confirm the logged-in account, recipient, message body, and message length before sending or replying; require explicit user confirmation.

Risk: A shared browser profile could expose the wrong account or unrelated browsing context.

Mitigation: Use a dedicated openclaw browser profile and clear the Bilibili login state when the skill is no longer needed.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/moroiser/skills/bilibili-messager)
- [Publisher profile](https://clawhub.ai/user/moroiser)
- [Bilibili private messages](https://message.bilibili.com/#/whisper)

## Skill Output:

**Output Type(s):** [Guidance, Shell commands, Code]

**Output Format:** [Markdown guidance with browser tool commands and JavaScript snippets]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses a logged-in openclaw browser profile; outgoing messages require explicit recipient and message confirmation.]

## Skill Version(s):

1.4.8 (source: server release evidence and artifact _meta.json)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 7h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular