Remote OpenClaw
Menu
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Skills/riba2534/feishu-cli/feishu-cli-msg
feishu-cli-msg logo

feishu-cli-msg

riba2534/feishu-cli
789 installs1K stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/riba2534/feishu-cli --skill feishu-cli-msg

Summary

>-

SKILL.md

飞书消息发送技能

通过 feishu-cli 发送飞书消息、回复、转发、合并转发、加急和下载消息资源。

feishu-cli:如尚未安装,请前往 riba2534/feishu-cli 获取安装方式。

与 feishu-cli-chat 技能的职责边界

重要:CLI 路径 ≠ SKILL 归属。 feishu-cli msg 下的子命令同时被两个 SKILL 分管,按动作类型划分,不按 CLI 路径划分。 | 动作类型 | 子命令 | 归属 SKILL | | --- | --- | --- | | 发送类(本 SKILL 覆盖) | send / reply / forward / merge-forward / urgent / flag / resource-download | feishu-cli-msg | | 读取类(请用 chat SKILL) | history / list / get / mget / thread-messages / search-chats / read-users / pins | feishu-cli-chat | | 互动类(请用 chat SKILL) | reaction / pin / unpin / delete | feishu-cli-chat | 端到端拉一段时间窗的群消息(含话题展开、名字反解、卡片解析)直接跑: ``bash python3 skills/feishu-cli-chat/scripts/fetch_chat_history.py oc_xxx --since 24h ``

核心概念

消息架构

飞书消息 API 的 content 字段是一个 JSON 字符串(不是 JSON 对象)。CLI 提供三种输入方式:

输入方式参数适用场景
快捷文本--text "内容"纯文本消息,最简单
发送文件--file <路径> 或 -f本地文件自动上传并发送(限 30MB)
发送图片--image <路径>本地图片自动上传并发送(限 10MB)
内联 JSON--content '{"key":"val"}' 或 -c简单 JSON,一行搞定
JSON 文件--content-file file.json复杂消息(卡片、富文本等)

互斥:以上 5 种输入方式只能指定一个,同时指定会报错。

接收者类型

--receive-id-type说明示例
email邮箱地址user@example.com
open_idOpen IDou_xxx
user_idUser IDxxx
union_idUnion IDon_xxx
chat_id群聊 IDoc_xxx

消息类型选择

决策树(Claude 未指定类型时自动选择)

默认优先使用 interactive(卡片消息),样式美观、内容丰富、支持颜色/多列/按钮等。

用户需求
├─ 【默认】通知/报告/告警/任何有信息量的消息 → interactive(卡片)
├─ 发送已上传的图片/文件/音视频 → image/file/audio/media
├─ 分享群聊或用户名片 → share_chat/share_user
└─ 仅以下场景才用 text/post:
   ├─ 用户明确要求发纯文本 → text
   └─ 用户明确要求发富文本 → post

为什么优先卡片:text 不支持任何格式渲染,post 样式有限,卡片支持彩色 header、多列 fields、按钮、分割线、备注等,视觉效果远优于其他类型。

消息类型一览

类型说明content 格式大小限制
text纯文本{"text":"内容"}150 KB
post富文本{"zh_cn":{"title":"","content":[[...]]}}150 KB
image图片{"image_key":"img_xxx"}—
file文件{"file_key":"file_v2_xxx"}—
audio语音{"file_key":"file_v2_xxx"}—
media视频{"file_key":"...","image_key":"..."}—
sticker表情包{"file_key":"file_v2_xxx"}仅转发
interactive卡片Card JSON / template_id / card_id30 KB
share_chat群名片{"chat_id":"oc_xxx"}—
share_user个人名片{"user_id":"ou_xxx"}—

system 系统分割线(仅 p2p)CLI --msg-type 白名单暂未收录(见 cmd/send_message.go:261-266),需要时用 feishu-cli api POST /open-apis/im/v1/messages 直接透传。

身份说明

本技能以发送类命令为主,默认使用 App Token(Bot 身份),无需登录。

  • 必需 User Token:msg flag 收藏/书签子命令(im:feed.flag:read/write),见末尾"消息书签"章节。
  • 优先 User Token + Tenant 兜底:msg resource-download 已登录时自动用 User Token 下载(要求你能看到该消息),未登录则尝试 App Token(要求 Bot 能看到该消息)。

其他子命令(reaction/pin/delete/history/list/get/mget/thread-messages/search-chats)的 Token 策略见 feishu-cli-chat 技能。

发送命令

基础格式

feishu-cli msg send \
  --receive-id-type <type> \
  --receive-id <id> \
  [--msg-type <msg_type>] \
  [--text "<text>" | --file <path> | --image <path> | --content '<json>' | --content-file <file.json>]

file 类型(直发文件)

# 直接发送本地文件(自动上传,限 30MB)
feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --file /path/to/report.pdf

自动推断文件 MIME 类型(opus/mp4/pdf/doc/xls/ppt),未知类型使用 stream。超过 30MB 的文件请先用 file upload 上传到云空间,再用 --msg-type file --content '{"file_key":"..."}' 发送。

image 类型(直发图片)

# 直接发送本地图片(自动上传,限 10MB)
feishu-cli msg send \
  --receive-id-type chat_id \
  --receive-id oc_xxx \
  --image /path/to/screenshot.png

支持 JPEG、PNG、BMP、GIF、TIFF、WebP 格式。

text 类型

# 最简形式(默认 msg-type 为 text)
feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --text "你好,这是一条测试消息"

text 类型支持的内联 @ 语法:

  • @ 用户:<at user_id="ou_xxx">Tom</at> —— ou_xxx 必须是真实 open_id
  • @ 所有人:<at user_id="all"></at>
  • @ 机器人:与 @ 用户语法相同,把 ou_xxx 换成机器人 open_id 即可

只能用 open_id:<at email="..."> 在 text 消息里不会触发 @ entity(飞书 IM 客户端会把邮箱字符串自动渲染成超链接,看起来像 @ 但没有通知、不是真的提及)。需要 @ 邮箱用户,先查 open_id:

# 第一步:查 open_id
feishu-cli user search --email alice@example.com -o json
# 第二步:用真实 open_id @ 人
feishu-cli msg send --receive-id-type chat_id --receive-id oc_xxx \
  --text '<at user_id="ou_xxx">Alice</at> 你好'

容错(仅 --text 模式):msg send / msg reply 在 --text 模式下会自动修正 AI 易写错的 @ 标签格式,下列写法都会被规范化为标准 <at user_id="...">:

  • <at id=ou_xxx>(缺引号 / 用 id 而非 user_id)
  • <at open_id="ou_xxx"/>(自闭合 / 用 open_id)
  • <at user_id=ou_xxx/>(自闭合无引号)

--content / --content-file 模式不做隐式 normalize(用户自己写的 JSON 自己负责,避免破坏结构)。

注意:text 类型不支持富文本样式(加粗、斜体、下划线、删除线、超链接等均不会渲染)。如需格式排版,请使用 post 类型。

post 类型(富文本)

推荐使用 md 标签承载 Markdown,一个 md 标签独占一个段落:

cat > /tmp/msg.json << 'EOF'
{
  "zh_cn": {
    "title": "项目进展通知",
    "content": [
      [{"tag": "md", "text": "**本周进展**\n- 完成功能 A 开发\n- 修复 3 个 Bug\n- [查看详情](https://example.com)"}],
      [{"tag": "md", "text": "**下周计划**\n1. 功能 B 开发\n2. 性能优化"}]
    ]
  }
}
EOF

feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --msg-type post \
  --content-file /tmp/msg.json

post 支持的 tag 类型:

tag说明主要属性
text文本text, style(bold/italic/underline/lineThrough)
a超链接text, href
at@用户user_id, user_name
img图片image_key, width, height
media视频file_key, image_key
emotion表情emoji_type
hr分割线—
code_block代码块language, text
mdMarkdowntext(独占段落,推荐使用)

图片自动上传(--upload-images)

msg send 支持 --upload-images,扫描 post / interactive 消息中的 Markdown 图片语法 !alt,把 path 指向的本地图片自动上传到飞书 IM 图床、替换为 image_key,再发送。

维度行为
触发条件仅当 --msg-type post 或 --msg-type interactive 时生效(其他类型即使传也忽略,见 cmd/send_message.go:212)
适用语法内容里的 !alt 标记;URL(http/https)和已有 image_key 不会被改写
路径解析相对路径:以 --content-file 所在目录为 basePath;用 --content 内联 JSON 时以当前工作目录为 basePath(见 cmd/send_message.go:213-220)
失败回落上传失败直接报错退出,不会继续发送残缺消息(避免 image_key 缺失被服务端拒绝)
进度提示上传 > 0 张时 stderr 打印 已自动上传 N 张本地图片
# post 内嵌本地图:自动上传相对路径 ./diagrams/foo.png
feishu-cli msg send --receive-id-type email --receive-id user@example.com \
  --msg-type post --content-file /path/to/post.json --upload-images

# interactive 卡片内嵌本地图同理
feishu-cli msg send --receive-id-type chat_id --receive-id oc_xxx \
  --msg-type interactive --content-file /tmp/card.json --upload-images

不需要预先调 feishu-cli media upload:本标志已包装了"上传 + 替换 + 发送"的全流程。需要把图片当作独立 image 消息发送,请直接用 --image <path> 快捷方式。

interactive 类型(卡片消息)

卡片消息有三种发送方式:

方式一:完整 Card JSON(仅发送;复杂卡片先用 feishu-cli-card 生成)

cat > /tmp/card.json << 'EOF'
{
  "schema": "2.0",
  "header": {
    "template": "blue",
    "title": {"tag": "plain_text", "content": "任务完成通知"}
  },
  "body": {
    "direction": "vertical",
    "elements": [
      {"tag": "markdown", "content": "**项目**: feishu-cli\n**状态**: 已完成\n**负责人**: <at id=all></at>"}
    ]
  }
}
EOF

feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --msg-type interactive \
  --content-file /tmp/card.json

方式二:template_id

cat > /tmp/card.json << 'EOF'
{
  "type": "template",
  "data": {
    "template_id": "AAqk1xxxxxx",
    "template_variable": {"name": "张三", "status": "已完成"}
  }
}
EOF

feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --msg-type interactive \
  --content-file /tmp/card.json

方式三:card_id

feishu-cli msg send \
  --receive-id-type email \
  --receive-id user@example.com \
  --msg-type interactive \
  --content '{"type":"card","data":{"card_id":"7371713483664506900"}}'
Interactive 卡片职责边界

本技能只负责发送 interactive 消息,不负责设计卡片 JSON。

  • 结构化或美观卡片必须先使用 feishu-cli-card 生成 v2 JSON(schema=2.0)。
  • 本技能发送:feishu-cli msg send --msg-type interactive --content-file <card.json>。
  • 不要在本技能内新写 v1 elements/action/note 卡片模板;旧 v1 示例仅用于历史兼容排查。

执行流程

发送消息流程

  1. 确定接收者:默认 user@example.com(email),或从上下文获取
  2. 选择消息类型:
  • 用户明确指定类型 → 使用指定类型
  • 结构化或美观通知 → 先用 feishu-cli-card 构造 JSON,再用 interactive 发送
  • 用户明确要求纯文本/富文本,或内容很短 → 使用 text / post
  1. 准备内容:纯文本直接传 --text;卡片 JSON 使用 --content-file;文件/图片使用 --file / --image
  2. 发送并检查结果:执行命令,确认返回 message_id

权限要求

权限说明
im:message消息读写(发送/回复/转发)
im:message:send_as_bot以机器人身份发送消息

注意事项

限制说明
text 大小限制单条最大 150 KB
卡片/富文本大小限制单条最大 30 KB
system 消息CLI --msg-type 暂不支持,仅 p2p 会话有效;需用 feishu-cli api 透传
sticker 消息仅支持转发收到的表情包,不支持自行上传
卡片按钮回调按钮的交互回调需应用服务端支持,CLI 发送的按钮仅 url 跳转有效
API 频率限制请求过快返回 429,等待几秒后重试
删除消息仅能删除机器人发送的消息

错误处理

错误原因解决
content format of a post type is incorrectpost 类型 JSON 格式错误确保格式为 {"zh_cn":{"title":"","content":[[...]]}}
invalid receive_id接收者 ID 无效检查 --receive-id-type 和 --receive-id 是否匹配
bot has no permission机器人无权限确认应用有 im:message:send_as_bot 权限
rate limit exceededAPI 限流等待几秒后重试
user not found用户不存在检查邮箱或 ID 是否正确
card content too large卡片 JSON 超过 30 KB精简卡片内容或拆分为多条消息
Bot/User can NOT be out of the chatBot 不在目标群内添加 --user-access-token 切换为 User 身份重试

批量获取消息

读消息详情和批量获取消息请使用 feishu-cli-chat 技能。msg get/list/history/mget 默认请求 user_card_content 并额外提取 card_texts,该行为和排错说明维护在 chat skill 中,避免发送与读取职责混在一起。

下载消息资源

下载消息中的图片或文件附件。

# 下载消息中的图片
feishu-cli msg resource-download <message_id> <file_key> --type image -o /tmp/photo.png

# 下载消息中的文件
feishu-cli msg resource-download <message_id> <file_key> --type file -o /tmp/attachment.pdf

# Bot 不可见但当前用户可见的历史消息资源,可显式用 User Token
feishu-cli msg resource-download <message_id> <file_key> --type file --user-access-token u-xxx -o /tmp/attachment.pdf

# 下载大文件时指定超时时间
feishu-cli msg resource-download <message_id> <file_key> --type file --user-access-token u-xxx -o /tmp/large.bin --timeout 30m
参数说明默认值
<message_id>消息 ID必填
<file_key>资源的 file_key必填
--type资源类型 image/file必填
-o, --output输出文件路径—
--user-access-token使用用户身份下载用户可见、但 Bot 不可见的历史消息资源—
--timeout下载超时时间(Go duration 格式,如 10m、30m、1h)5m

file_key 来源:通过 msg get <message_id> 获取消息详情,从 content 中提取 image_key 或 file_key。 使用用户身份直连下载时,如遇到飞书大文件限制,会自动使用 HTTP Range 分片下载并合并。

话题(Thread)消息

发送到已有话题

msg send 支持 --thread-id(等价于 --receive-id-type thread_id --receive-id <thread_id>):

# 在已有话题内追加一条消息
feishu-cli msg send --thread-id omt_xxx --text "话题内继续聊"

# 卡片消息也支持
feishu-cli msg send --thread-id omt_xxx \
  --msg-type interactive \
  --content "$(cat card.json)"

--thread-id 与 --receive-id-type/--receive-id 互斥,只能指定一组。

回复时开启话题

msg reply 支持 --reply-in-thread(reply_in_thread=true):

# 在非话题群聊中,以话题形式回复某条消息(会开启一个新话题)
feishu-cli msg reply om_xxx --text "这里开个话题" --reply-in-thread

# 若群聊已是话题模式,--reply-in-thread 会自动回复到消息所在话题

话题回复列表

获取话题回复属于读取消息,请使用 feishu-cli-chat 技能。发送话题内消息仍使用本技能的 msg send --thread-id。

参考文档

  • references/message_content.md:各消息类型的 content JSON 结构详解
  • references/card_schema.md:interactive 发送格式与历史卡片排障;新增卡片构造优先用 feishu-cli-card

消息书签(msg flag,v1.23+ 新增)

服务端称 message flag,用于把消息加 Feed 标记,把消息推上用户 Feed/书签。 对应 HTTP API POST/GET/PATCH /open-apis/im/v1/flags。需 User Access Token:list 需要 im:feed.flag:read,create/cancel 需要 im:feed.flag:write。

命令速查

  • feishu-cli msg flag create <message_id> — 创建消息层书签(默认 --item-type default --flag-type message)
  • feishu-cli msg flag create <message_id> --flag-type feed — feed 层书签,自动读取 chat_mode 判断 thread / msg_thread
  • feishu-cli msg flag create <message_id> --item-type msg_thread --flag-type feed — feed 层书签(显式指定普通群线程)
  • feishu-cli msg flag list [--page-size 50] [--page-token xxx] — 列当前用户的书签
  • feishu-cli msg flag cancel <message_id> [--item-type ... --flag-type ...] — 默认尽量取消消息层 + feed 层;显式传 item/flag 时只取消指定层

关键枚举(服务端真值,绝勿按 0/1/2 顺序臆造)

CLI flag 用字符串,底层映射到 OpenAPI 整数枚举:

字段CLI 字符串OpenAPI 整数含义
--item-typedefault0普通消息
--item-typethread4topic-style 话题群
--item-typemsg_thread11普通群消息线程
--flag-typemessage2消息层书签(默认)
--flag-typefeed1feed 层(侧边栏书签)

⚠️ 反向陷阱:网上某些第三方教程(含部分 lark-cli 旧版示例)把 flag_type: 1=message / 2=feed 写反了。本项目以飞书 OpenAPI 官方真值为准(1=feed / 2=message,见上表)。list 命令输出里也是这套真值,写代码处理 JSON 时认上面这张表。 list 命令不接受 --flag-type/--item-type 作为入参(list 是全量返回),只能在输出 flag_items[*].flag_type 字段上过滤。要看自己有哪些书签直接 feishu-cli msg flag list -o json。

支持的组合(其余服务端拒绝):

  • default + message:消息层书签,最常见
  • thread + feed:topic-style 话题群 feed 层
  • msg_thread + feed:普通群消息线程 feed 层

源码引用:internal/client/flag.go:23-28(本仓库权威,对齐 lark-cli shortcuts/im 的 ItemType/FlagType 定义)。

Score

0–100
57/ 100

Grade

C

Popularity17/30

789 installs — growing adoption. Source repo has 1,207 GitHub stars.

Completeness19/30

Documented: full SKILL.md body, one-line install. Missing: description, category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Feishu Cli Msg skill score badge previewScore badge

Markdown

[![Feishu Cli Msg skill](https://www.remoteopenclaw.com/skills/riba2534/feishu-cli/feishu-cli-msg/badges/score.svg)](https://www.remoteopenclaw.com/skills/riba2534/feishu-cli/feishu-cli-msg)

HTML

<a href="https://www.remoteopenclaw.com/skills/riba2534/feishu-cli/feishu-cli-msg"><img src="https://www.remoteopenclaw.com/skills/riba2534/feishu-cli/feishu-cli-msg/badges/score.svg" alt="Feishu Cli Msg skill"/></a>

Feishu Cli Msg FAQ

How do I install the Feishu Cli Msg skill?

Run “npx skills add https://github.com/riba2534/feishu-cli --skill feishu-cli-msg” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Feishu Cli Msg skill do?

>- The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Feishu Cli Msg skill free?

Yes. Feishu Cli Msg is a free, open-source skill published from riba2534/feishu-cli. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Feishu Cli Msg work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Feishu Cli Msg works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →

Categories

Command ExecutionExternal DownloadsData ExfiltrationPrompt Injection
View on GitHub

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.7M installsInstall
frontend-design logo

frontend-design

anthropics/skills

719K installsInstall
grill-me logo

grill-me

mattpocock/skills

698K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

594K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

591K installsInstall
vercel-react-best-practices logo

vercel-react-best-practices

vercel-labs/agent-skills

590K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Free guide
  • Learn
  • OpenClaw for Creators
  • OpenClaw for Founders
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed