← Back to Skills Marketplace
265
Downloads
1
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install wxclawbot-send
Description
主动给微信用户发消息（文本、图片、视频、文件）。微信机器人默认只能被动回复， 这个技能让 agent 能主动推送消息到用户微信。 Use when: 主动发微信, 定时提醒, 告警通知, 推送报告, 发图片/文件到微信, proactive WeChat message, push notification to...
Usage Guidance
This skill appears to do exactly what it claims: install a CLI that uses your WeChat bot token and account files to send text and media. Before installing, verify the npm package and GitHub repo are trusted and that the WXCLAW_TOKEN you provide has only the needed privileges. Be aware: sending files requires the CLI to read local files or download URLs — an agent with this skill could be instructed to send sensitive local files (secrets, keys, documents) to a WeChat user, so only grant the skill to agents you trust and avoid leaving highly sensitive data in paths the agent can access. Also note the code respects OPENCLAW_STATE_DIR/CLAWDBOT_STATE_DIR (not listed in metadata) for locating account data — if you use custom state dirs, ensure they contain only expected account files. Rotate tokens if you suspect misuse and validate account discovery (wxclawbot accounts --json) after install.
Capability Analysis
Type: OpenClaw Skill
Name: wxclawbot-send
Version: 0.5.2
The skill bundle provides a legitimate CLI tool and library (@claw-lab/wxclawbot-cli) designed to allow OpenClaw agents to proactively send WeChat messages. It handles account discovery from the standard `~/.openclaw` directory, implements AES-128-ECB encryption for media uploads as required by the WeChat iLink protocol, and communicates with official endpoints (ilinkai.weixin.qq.com and novac2c.cdn.weixin.qq.com). While the tool has the capability to read local files and environment variables (WXCLAW_TOKEN), these actions are transparently documented and essential for its stated purpose of WeChat integration, with no evidence of malicious intent, obfuscation, or unauthorized data exfiltration.
Capability Assessment
Purpose & Capability
Name/description, required binary (wxclawbot), install (npm package @claw-lab/wxclawbot-cli) and primaryEnv (WXCLAW_TOKEN) align with a CLI that sends WeChat messages. Required config path (~/.openclaw/openclaw-weixin/accounts/) and code that reads account/context-token files are consistent with stated functionality.
Instruction Scope
SKILL.md instructs the agent to run wxclawbot CLI commands and to use --json for programmatic calls. The included code reads account files and context-token files from the declared account directory and will read arbitrary local files or download URLs when sending attachments (readFileOrUrl). Reading those files is necessary for file-send functionality but also means the agent/CLI can send any local file the agent is instructed to send.
Install Mechanism
Install uses an npm package (@claw-lab/wxclawbot-cli) that provides the wxclawbot binary — a standard, traceable install mechanism for a Node CLI. No suspicious download hosts or extract-from-arbitrary-URL steps are present.
Credentials
Declared primary env WXCLAW_TOKEN and optional WXCLAW_BASE_URL are appropriate. The code also honors OPENCLAW_STATE_DIR and CLAWDBOT_STATE_DIR as state-dir overrides (used to locate account files) but those env vars are not declared in metadata — this is minor but worth noting. Access to the accounts directory and context-token files is required for operation; these files contain tokens and are therefore sensitive.
Persistence & Privilege
Skill is user-invocable, not always-on, and does not request system-wide persistent privileges or modify other skills' configs. It runs as a CLI invoked by the agent (normal behavior).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wxclawbot-send - After installation, invoke the skill by name or use
/wxclawbot-send - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.5.2
- Skill documentation is now primarily in Chinese, optimized for mainland Chinese users.
- Usage scenarios, quick start, and error handling sections revised with simplified instructions and clearer tables.
- Descriptions and trigger lists updated to better match proactive WeChat messaging use-cases in both Chinese and English.
- Environment variables and prerequisites section now feature improved Chinese explanations and example commands.
- Package version bumped to 0.5.2.
v0.5.1
- Adds structured transport error reporting when using --json, including errorKind (e.g., timeout, dns, network) and a retryable flag.
- Documents new error fields for automation and improved error handling in SKILL.md.
- No changes to CLI usage or arguments; fully backward compatible for existing integrations.
v0.5.0
- Added support for context tokens to enable proactive push notifications on WeChat.
- CLI now reads and uses `{accountId}.context-tokens.json` for user-specific context tokens.
- Documentation updated to explain context token mechanism and how push behavior works.
- No manual setup required; context tokens are managed automatically by openclaw-weixin.
- Other references and usage unchanged.
v0.4.2
- Improved documentation on account discovery and account ID changes after openclaw-weixin upgrades.
- Added clarification to the output format of wxclawbot accounts --json.
- Updated error handling section to specify stricter WeChat server-side rate limits (recommend waiting 60–120s on rate limiting).
- Enhanced environment variable and integration guidance for correct programmatic use.
v0.4.1
- Bump version to 0.4.1.
- Update documentation in SKILL.md, README.md, and README.en.md.
- No functional or interface changes; documentation clarifications and improvements only.
v0.4.0
- Switched CLI and npm package dependency from @herai/wxclawbot-cli to @claw-lab/wxclawbot-cli.
- Updated installation instructions and references to the new npm package name.
- Added English README (README.en.md) for improved documentation.
- Minor documentation and metadata updates for clarity.
v0.3.0
Agent-first README, ClawHub-compatible SKILL.md metadata, CI publish workflow
v0.2.1
Initial ClawHub release. Send text, images, video, and files to WeChat users from AI agents.
Metadata
Frequently Asked Questions
What is WeixinClawBot Send?
主动给微信用户发消息（文本、图片、视频、文件）。微信机器人默认只能被动回复， 这个技能让 agent 能主动推送消息到用户微信。 Use when: 主动发微信, 定时提醒, 告警通知, 推送报告, 发图片/文件到微信, proactive WeChat message, push notification to... It is an AI Agent Skill for Claude Code / OpenClaw, with 265 downloads so far.
How do I install WeixinClawBot Send?
Run "/install wxclawbot-send" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is WeixinClawBot Send free?
Yes, WeixinClawBot Send is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does WeixinClawBot Send support?
WeixinClawBot Send is cross-platform and runs anywhere OpenClaw / Claude Code is available (macos, linux).
Who created WeixinClawBot Send?
It is built and maintained by Eric Wang (@lroolle); the current version is v0.5.2.
More Skills