{
  "schemaVersion": "1.0",
  "item": {
    "slug": "markdown-browser-skills-openclaw",
    "name": "Markdown Browser",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/johnortegahyc/markdown-browser-skills-openclaw",
    "canonicalUrl": "https://clawhub.ai/johnortegahyc/markdown-browser-skills-openclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/markdown-browser-skills-openclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=markdown-browser-skills-openclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "browser.js",
      "package.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. 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. 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/markdown-browser-skills-openclaw"
    },
    "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/markdown-browser-skills-openclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Markdown Browser Skills",
        "body": "This skill is an orchestration layer, not a replacement fetcher. It always keeps official web_fetch as the fetch source of truth."
      },
      {
        "title": "MECE Architecture",
        "body": "Fetch layer (official, exclusive)\n\nUse OpenClaw web_fetch to retrieve the page.\nDo not call direct HTTP fetch inside this skill for normal operation.\n\nPolicy layer (these skills)\n\nParse Content-Signal and compute policy_action.\nCurrent action focuses on ai-input semantics: allow_input, block_input, needs_review.\n\nPrivacy layer (these skills)\n\nRedact path/fragment/query values in output URL fields.\nKeep URL shape useful for debugging without leaking sensitive values.\n\nNormalization layer (these skills)\n\nIf contentType=text/markdown, keep content as-is.\nIf contentType=text/html, convert with turndown as fallback enhancement.\nFor other content types, pass through text."
      },
      {
        "title": "Execution Order",
        "body": "Call official web_fetch.\nPass the result JSON into this wrapper.\nOptionally pass Content-Signal and x-markdown-tokens header values if available.\nUse the returned normalized object for downstream agent logic."
      },
      {
        "title": "Wrapper Tool",
        "body": "process_web_fetch_result({ web_fetch_result, content_signal_header, markdown_tokens_header })\n\nInput:\n\nweb_fetch_result (required): JSON payload returned by OpenClaw web_fetch.\ncontent_signal_header (optional): raw Content-Signal header string.\nmarkdown_tokens_header (optional): raw x-markdown-tokens header value.\n\nOutput:\n\ncontent\nformat (markdown | html-fallback | text)\ntoken_estimate (number | null)\ncontent_signal\npolicy_action\nsource_url (redacted)\nstatus_code\nfallback_used"
      },
      {
        "title": "CLI Usage",
        "body": "# Install runtime dependency once inside the skill directory\nnpm install --omit=dev\n\n# 1) Obtain a web_fetch payload first (from OpenClaw runtime)\n# 2) Save it as /tmp/web_fetch.json\n# 3) Run wrapper post-processing\nnode browser.js \\\n  --input /tmp/web_fetch.json \\\n  --content-signal \"ai-input=yes, search=yes, ai-train=no\" \\\n  --markdown-tokens \"1820\""
      }
    ],
    "body": "Markdown Browser Skills\n\nThis skill is an orchestration layer, not a replacement fetcher. It always keeps official web_fetch as the fetch source of truth.\n\nMECE Architecture\nFetch layer (official, exclusive)\nUse OpenClaw web_fetch to retrieve the page.\nDo not call direct HTTP fetch inside this skill for normal operation.\nPolicy layer (these skills)\nParse Content-Signal and compute policy_action.\nCurrent action focuses on ai-input semantics: allow_input, block_input, needs_review.\nPrivacy layer (these skills)\nRedact path/fragment/query values in output URL fields.\nKeep URL shape useful for debugging without leaking sensitive values.\nNormalization layer (these skills)\nIf contentType=text/markdown, keep content as-is.\nIf contentType=text/html, convert with turndown as fallback enhancement.\nFor other content types, pass through text.\nExecution Order\nCall official web_fetch.\nPass the result JSON into this wrapper.\nOptionally pass Content-Signal and x-markdown-tokens header values if available.\nUse the returned normalized object for downstream agent logic.\nWrapper Tool\n\nprocess_web_fetch_result({ web_fetch_result, content_signal_header, markdown_tokens_header })\n\nInput:\n\nweb_fetch_result (required): JSON payload returned by OpenClaw web_fetch.\ncontent_signal_header (optional): raw Content-Signal header string.\nmarkdown_tokens_header (optional): raw x-markdown-tokens header value.\n\nOutput:\n\ncontent\nformat (markdown | html-fallback | text)\ntoken_estimate (number | null)\ncontent_signal\npolicy_action\nsource_url (redacted)\nstatus_code\nfallback_used\nCLI Usage\n# Install runtime dependency once inside the skill directory\nnpm install --omit=dev\n\n# 1) Obtain a web_fetch payload first (from OpenClaw runtime)\n# 2) Save it as /tmp/web_fetch.json\n# 3) Run wrapper post-processing\nnode browser.js \\\n  --input /tmp/web_fetch.json \\\n  --content-signal \"ai-input=yes, search=yes, ai-train=no\" \\\n  --markdown-tokens \"1820\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/johnortegahyc/markdown-browser-skills-openclaw",
    "publisherUrl": "https://clawhub.ai/johnortegahyc/markdown-browser-skills-openclaw",
    "owner": "johnortegahyc",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/markdown-browser-skills-openclaw",
    "agentUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/markdown-browser-skills-openclaw/agent.md"
  }
}