openbotx
An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler,...
CDP browser control at localhost:9222. Use when you need to inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session (e.g. logged into X, Gmail).
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install gostlightai/cdp-browserInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
CLI for Chrome/Chromium at localhost:9222. Inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session.
Repo: https://github.com/gostlightai/cdp-browser
Prerequisites: Chromium running with --remote-debugging-port=9222. Docker Compose or a local Chrome with remote debugging enabled.
Run from the skill dir (bin/ scripts):
| Command | Description |
|---|---|
status |
List all tabs (JSON from CDP) |
tabs |
Same as status |
new <url> |
Open new tab |
goto <tabId> <url> |
Navigate tab to URL |
snapshot <tabId> |
Full-page screenshot (PNG) |
close-popup <tabId> |
Dismiss dialogs/modals |
scroll <tabId> <px|sel> [down|up] |
Scroll by pixels or selector |
query <tabId> getUrl |
Return current page URL |
query <tabId> getText [selector] |
Return element text (or body) |
query <tabId> getHtml [selector] |
Return element HTML (or body) |
tweet-draft <tabId> "text" |
Fill compose box only; does NOT post |
tweet-post <tabId> --confirm "text" |
Post tweet (requires --confirm as second arg) |
tweet <tabId> "text" |
Alias for tweet-draft (fills compose only) |
--confirm as second arg (strict). Use when user explicitly approves ("go ahead", "post it", or Telegram confirm button).tweet.confirmButton is enabled in config, the agent can run tweet-draft --save-pending to write pending state, then send a message with an inline "Confirm Post" button. On confirm, the agent runs tweet-post --confirm.The Telegram "Confirm Post" button only works if config exists. Copy the example and place it in your workspace:
# From the skill dir (e.g. ~/.openclaw/workspace/skills/cdp-browser):
cp .cdp-...
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
CDP browser control skill for OpenClaw. CLI for Chrome/Chromium at localhost:9222.
Repo: https://github.com/gostlightai/cdp-browser
cd skills/cdp-browser
npm install
Chromium running with --remote-debugging-port=9222 (Docker Compose or local Chrome).
See SKILL.md for commands and usage. Run bin/ scripts from the skill dir.
To enable the "Confirm Post" inline button in Telegram, copy the example config:
cp ~/.openclaw/workspace/skills/cdp-browser/.cdp-browser.json.example ~/.openclaw/workspace/.cdp-browser.json
Without it, tweet-draft works but the agent sends plain text only; user confirms via "go ahead" in chat.
--confirm as second arg; posts only when user approvesSee SECURITY.md for security considerations and mitigations.
# cdp-browser
CLI for Chrome/Chromium at localhost:9222. Inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session.
**Repo:** https://github.com/gostlightai/cdp-browser
**Prerequisites:** Chromium running with `--remote-debugging-port=9222`. Docker Compose or a local Chrome with remote debugging enabled.
## Commands
Run from the skill dir (`bin/` scripts):
| Command | Description |
|---------|-------------|
| `status` | List all tabs (JSON from CDP) |
| `tabs` | Same as status |
| `new <url>` | Open new tab |
| `goto <tabId> <url>` | Navigate tab to URL |
| `snapshot <tabId>` | Full-page screenshot (PNG) |
| `close-popup <tabId>` | Dismiss dialogs/modals |
| `scroll <tabId> <px\|sel> [down\|up]` | Scroll by pixels or selector |
| `query <tabId> getUrl` | Return current page URL |
| `query <tabId> getText [selector]` | Return element text (or body) |
| `query <tabId> getHtml [selector]` | Return element HTML (or body) |
| `tweet-draft <tabId> "text"` | Fill compose box only; does NOT post |
| `tweet-post <tabId> --confirm "text"` | Post tweet (requires `--confirm` as second arg) |
| `tweet <tabId> "text"` | Alias for tweet-draft (fills compose only) |
## Tweet flow
- **tweet-draft** (default): Fills the compose box; user reviews in browser and posts manually.
- **tweet-post**: Requires `--confirm` as second arg (strict). Use when user explicitly approves ("go ahead", "post it", or Telegram confirm button).
- **Optional Telegram confirm:** When `tweet.confirmButton` is enabled in config, the agent can run `tweet-draft --save-pending` to write pending state, then send a message with an inline "Confirm Post" button. On confirm, the agent runs `tweet-post --confirm`.
### Config (required for Telegram confirm button)
The Telegram "Confirm Post" button **only works if config exists**. Copy the example and place it in your workspace:
```bash
# From the skill dir (e.g. ~/.openclaw/workspace/skills/cdp-browser):
cp .cdp-...# cdp-browser CDP browser control skill for OpenClaw. CLI for Chrome/Chromium at localhost:9222. **Repo:** https://github.com/gostlightai/cdp-browser ## Install ```bash cd skills/cdp-browser npm install ``` ## Prerequisites Chromium running with `--remote-debugging-port=9222` (Docker Compose or local Chrome). ## Usage See [SKILL.md](SKILL.md) for commands and usage. Run `bin/` scripts from the skill dir. ## Config (Telegram confirm button) To enable the "Confirm Post" inline button in Telegram, copy the example config: ```bash cp ~/.openclaw/workspace/skills/cdp-browser/.cdp-browser.json.example ~/.openclaw/workspace/.cdp-browser.json ``` Without it, tweet-draft works but the agent sends plain text only; user confirms via "go ahead" in chat. ## Tweet flow - **tweet-draft** — fills compose only (safe default) - **tweet-post** — requires `--confirm` as second arg; posts only when user approves ## Security See [SECURITY.md](SECURITY.md) for security considerations and mitigations.
An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler,...
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
OpenClaw skill for 知识星球 / ZSXQ digests with token-first auth and browser recovery.
🌐 OpenClaw skill for Browser-Use — AI-powered browser automation for complex multi-step workflows (login, form filling, scraping, posting)