{
  "schemaVersion": "1.0",
  "item": {
    "slug": "cdp-browser",
    "name": "Cdp Browser",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/gostlightai/cdp-browser",
    "canonicalUrl": "https://clawhub.ai/gostlightai/cdp-browser",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/cdp-browser",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cdp-browser",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "README.md",
      "SECURITY.md",
      "SKILL.md",
      "cdp.js",
      "package-lock.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/cdp-browser"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/cdp-browser",
    "agentPageUrl": "https://openagent3.xyz/skills/cdp-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cdp-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cdp-browser/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "cdp-browser",
        "body": "CLI for Chrome/Chromium at localhost:9222. Inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session.\n\nRepo: https://github.com/gostlightai/cdp-browser\n\nPrerequisites: Chromium running with --remote-debugging-port=9222. Docker Compose or a local Chrome with remote debugging enabled."
      },
      {
        "title": "Commands",
        "body": "Run from the skill dir (bin/ scripts):\n\nCommandDescriptionstatusList all tabs (JSON from CDP)tabsSame as statusnew <url>Open new tabgoto <tabId> <url>Navigate tab to URLsnapshot <tabId>Full-page screenshot (PNG)close-popup <tabId>Dismiss dialogs/modalsscroll <tabId> <px|sel> [down|up]Scroll by pixels or selectorquery <tabId> getUrlReturn current page URLquery <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 posttweet-post <tabId> --confirm \"text\"Post tweet (requires --confirm as second arg)tweet <tabId> \"text\"Alias for tweet-draft (fills compose only)"
      },
      {
        "title": "Tweet flow",
        "body": "tweet-draft (default): Fills the compose box; user reviews in browser and posts manually.\ntweet-post: Requires --confirm as second arg (strict). Use when user explicitly approves (\"go ahead\", \"post it\", or Telegram confirm button).\nOptional 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."
      },
      {
        "title": "Config (required for Telegram confirm button)",
        "body": "The Telegram \"Confirm Post\" button only works if config exists. Copy the example and place it in your workspace:\n\n# From the skill dir (e.g. ~/.openclaw/workspace/skills/cdp-browser):\ncp .cdp-browser.json.example ~/.openclaw/workspace/.cdp-browser.json\n\nLocation: ~/.openclaw/workspace/.cdp-browser.json (or $OPENCLAW_WORKSPACE/.cdp-browser.json)\n\nKeyDefaultDescriptiontweet.confirmButtonfalseWhen true, agent sends draft with inline \"Confirm Post\" button in Telegram. User clicks to approve or says \"go ahead\".\n\nWithout this config, the agent uses plain tweet-draft (no button); user confirms via text only."
      },
      {
        "title": "Telegram confirm button (agent instructions)",
        "body": "When tweet.confirmButton is true (config present) and you are in a Telegram session:\n\nDraft: Run tweet-draft --save-pending <tabId> \"text\" from the skill dir. This fills the compose box and writes ~/.openclaw/workspace/.cdp-browser/pending-tweet.json.\nSend with button: Run from the skill dir:\n./scripts/send-tweet-confirm.sh <chat_id> \"<tweet_text>\"\n\nOr use openclaw message send directly with --buttons '[[{\"text\":\"Confirm Post\",\"callback_data\":\"cdp:tweet:confirm\"}]]'. Use the current session's reply target as <chat_id>.\nOn confirm: When the user clicks the button, OpenClaw delivers callback_data: cdp:tweet:confirm. Or the user says \"go ahead\"/\"post it\". Treat either as approval. Then:\n\nRead ~/.openclaw/workspace/.cdp-browser/pending-tweet.json for text and tabId\nRun tweet-post <tabId> --confirm \"<text>\"\nEdit or delete the message with the button (optional)\nDelete the pending file"
      },
      {
        "title": "Scripts",
        "body": "cdp.js — Fetch-only wrapper for CDP HTTP API (/json, /json/list, /json/new); no shell.\npw.js — Playwright connect to browser; runs snapshot/goto/scroll/query/tweet-draft/tweet-post. Compose launcher: SideNav_NewTweet_Button, /compose/post, Post only (avoids reply buttons). Post button: tweetButton, tweetButtonInline."
      },
      {
        "title": "Security",
        "body": "See SECURITY.md for mitigations and operational notes."
      }
    ],
    "body": "cdp-browser\n\nCLI for Chrome/Chromium at localhost:9222. Inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session.\n\nRepo: https://github.com/gostlightai/cdp-browser\n\nPrerequisites: Chromium running with --remote-debugging-port=9222. Docker Compose or a local Chrome with remote debugging enabled.\n\nCommands\n\nRun from the skill dir (bin/ scripts):\n\nCommand\tDescription\nstatus\tList all tabs (JSON from CDP)\ntabs\tSame as status\nnew <url>\tOpen new tab\ngoto <tabId> <url>\tNavigate tab to URL\nsnapshot <tabId>\tFull-page screenshot (PNG)\nclose-popup <tabId>\tDismiss dialogs/modals\nscroll <tabId> <px|sel> [down|up]\tScroll by pixels or selector\nquery <tabId> getUrl\tReturn current page URL\nquery <tabId> getText [selector]\tReturn element text (or body)\nquery <tabId> getHtml [selector]\tReturn element HTML (or body)\ntweet-draft <tabId> \"text\"\tFill compose box only; does NOT post\ntweet-post <tabId> --confirm \"text\"\tPost tweet (requires --confirm as second arg)\ntweet <tabId> \"text\"\tAlias for tweet-draft (fills compose only)\nTweet flow\ntweet-draft (default): Fills the compose box; user reviews in browser and posts manually.\ntweet-post: Requires --confirm as second arg (strict). Use when user explicitly approves (\"go ahead\", \"post it\", or Telegram confirm button).\nOptional 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.\nConfig (required for Telegram confirm button)\n\nThe Telegram \"Confirm Post\" button only works if config exists. Copy the example and place it in your workspace:\n\n# From the skill dir (e.g. ~/.openclaw/workspace/skills/cdp-browser):\ncp .cdp-browser.json.example ~/.openclaw/workspace/.cdp-browser.json\n\n\nLocation: ~/.openclaw/workspace/.cdp-browser.json (or $OPENCLAW_WORKSPACE/.cdp-browser.json)\n\nKey\tDefault\tDescription\ntweet.confirmButton\tfalse\tWhen true, agent sends draft with inline \"Confirm Post\" button in Telegram. User clicks to approve or says \"go ahead\".\n\nWithout this config, the agent uses plain tweet-draft (no button); user confirms via text only.\n\nTelegram confirm button (agent instructions)\n\nWhen tweet.confirmButton is true (config present) and you are in a Telegram session:\n\nDraft: Run tweet-draft --save-pending <tabId> \"text\" from the skill dir. This fills the compose box and writes ~/.openclaw/workspace/.cdp-browser/pending-tweet.json.\nSend with button: Run from the skill dir:\n./scripts/send-tweet-confirm.sh <chat_id> \"<tweet_text>\"\n\nOr use openclaw message send directly with --buttons '[[{\"text\":\"Confirm Post\",\"callback_data\":\"cdp:tweet:confirm\"}]]'. Use the current session's reply target as <chat_id>.\nOn confirm: When the user clicks the button, OpenClaw delivers callback_data: cdp:tweet:confirm. Or the user says \"go ahead\"/\"post it\". Treat either as approval. Then:\nRead ~/.openclaw/workspace/.cdp-browser/pending-tweet.json for text and tabId\nRun tweet-post <tabId> --confirm \"<text>\"\nEdit or delete the message with the button (optional)\nDelete the pending file\nScripts\ncdp.js — Fetch-only wrapper for CDP HTTP API (/json, /json/list, /json/new); no shell.\npw.js — Playwright connect to browser; runs snapshot/goto/scroll/query/tweet-draft/tweet-post. Compose launcher: SideNav_NewTweet_Button, /compose/post, Post only (avoids reply buttons). Post button: tweetButton, tweetButtonInline.\nSecurity\n\nSee SECURITY.md for mitigations and operational notes."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/gostlightai/cdp-browser",
    "publisherUrl": "https://clawhub.ai/gostlightai/cdp-browser",
    "owner": "gostlightai",
    "version": "2.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/cdp-browser",
    "downloadUrl": "https://openagent3.xyz/downloads/cdp-browser",
    "agentUrl": "https://openagent3.xyz/skills/cdp-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cdp-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cdp-browser/agent.md"
  }
}