{
  "schemaVersion": "1.0",
  "item": {
    "slug": "markdown-convert",
    "name": "Markdown.new Skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/joelchance/markdown-convert",
    "canonicalUrl": "https://clawhub.ai/joelchance/markdown-convert",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/markdown-convert",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=markdown-convert",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "scripts/markdown_new_fetch.py",
      "references/markdown-new-api.md",
      "agents/openai.yaml"
    ],
    "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/markdown-convert"
    },
    "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-convert",
    "agentPageUrl": "https://openagent3.xyz/skills/markdown-convert/agent",
    "manifestUrl": "https://openagent3.xyz/skills/markdown-convert/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/markdown-convert/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": "Markdown.new",
        "body": "Use this skill to convert public URLs into LLM-ready Markdown via markdown.new."
      },
      {
        "title": "Path Resolution (Critical)",
        "body": "Resolve relative paths like scripts/... and references/... from the skill directory, not workspace root.\nIf current directory is unknown, use an absolute script path.\n\npython3 ~/.codex/skills/markdown-new/scripts/markdown_new_fetch.py 'https://example.com'\n\ncd ~/.codex/skills/markdown-new\npython3 scripts/markdown_new_fetch.py 'https://example.com'\n\nAvoid this pattern from an arbitrary workspace root:\n\npython3 scripts/markdown_new_fetch.py 'https://example.com'"
      },
      {
        "title": "Workflow",
        "body": "Validate the input URL is public http or https.\nRun scripts/markdown_new_fetch.py with --method auto first.\nRe-run with --method browser if output misses JS-rendered content.\nEnable --retain-images only when image links are required.\nCapture response metadata (x-markdown-tokens, x-rate-limit-remaining, and JSON metadata when present) for downstream planning."
      },
      {
        "title": "Quick Start",
        "body": "Commands below assume current directory is the skill root (~/.codex/skills/markdown-new).\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' > page.md\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' --method browser --retain-images --output page.md\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' --deliver-md"
      },
      {
        "title": "Method Selection",
        "body": "auto: default. Let markdown.new use its fastest successful pipeline.\nai: force Workers AI HTML-to-Markdown conversion.\nbrowser: force headless browser rendering for JS-heavy pages.\n\nUse auto first, then retry with browser only when needed."
      },
      {
        "title": "Delivery Mode",
        "body": "Use --deliver-md to force file output in .md format.\nIn delivery mode, content is wrapped as:\n\n<url>\n...markdown...\n</url>\n\n\nIf --output is omitted, the script auto-generates a filename from the URL."
      },
      {
        "title": "API Modes",
        "body": "Prefix mode:\n\nhttps://markdown.new/https://example.com?method=browser&retain_images=true\n\n\nPOST mode:\n\nPOST https://markdown.new/\nJSON body: {\"url\":\"https://example.com\",\"method\":\"auto\",\"retain_images\":false}\n\nPrefer POST mode for automation and explicit parameters."
      },
      {
        "title": "Limits And Safety",
        "body": "Treat 429 as rate limiting (documented limit: 500 requests/day/IP).\nConvert only publicly accessible pages.\nRespect robots.txt, terms of service, and copyright constraints.\nDo not treat markdown.new output as guaranteed complete for every page; verify critical extractions."
      },
      {
        "title": "References",
        "body": "references/markdown-new-api.md"
      }
    ],
    "body": "Markdown.new\n\nUse this skill to convert public URLs into LLM-ready Markdown via markdown.new.\n\nPath Resolution (Critical)\nResolve relative paths like scripts/... and references/... from the skill directory, not workspace root.\nIf current directory is unknown, use an absolute script path.\npython3 ~/.codex/skills/markdown-new/scripts/markdown_new_fetch.py 'https://example.com'\n\ncd ~/.codex/skills/markdown-new\npython3 scripts/markdown_new_fetch.py 'https://example.com'\n\n\nAvoid this pattern from an arbitrary workspace root:\n\npython3 scripts/markdown_new_fetch.py 'https://example.com'\n\nWorkflow\nValidate the input URL is public http or https.\nRun scripts/markdown_new_fetch.py with --method auto first.\nRe-run with --method browser if output misses JS-rendered content.\nEnable --retain-images only when image links are required.\nCapture response metadata (x-markdown-tokens, x-rate-limit-remaining, and JSON metadata when present) for downstream planning.\nQuick Start\n\nCommands below assume current directory is the skill root (~/.codex/skills/markdown-new).\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' > page.md\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' --method browser --retain-images --output page.md\n\npython3 scripts/markdown_new_fetch.py 'https://example.com' --deliver-md\n\nMethod Selection\nauto: default. Let markdown.new use its fastest successful pipeline.\nai: force Workers AI HTML-to-Markdown conversion.\nbrowser: force headless browser rendering for JS-heavy pages.\n\nUse auto first, then retry with browser only when needed.\n\nDelivery Mode\nUse --deliver-md to force file output in .md format.\nIn delivery mode, content is wrapped as:\n<url>\n...markdown...\n</url>\nIf --output is omitted, the script auto-generates a filename from the URL.\nAPI Modes\nPrefix mode:\nhttps://markdown.new/https://example.com?method=browser&retain_images=true\nPOST mode:\nPOST https://markdown.new/\nJSON body: {\"url\":\"https://example.com\",\"method\":\"auto\",\"retain_images\":false}\n\nPrefer POST mode for automation and explicit parameters.\n\nLimits And Safety\nTreat 429 as rate limiting (documented limit: 500 requests/day/IP).\nConvert only publicly accessible pages.\nRespect robots.txt, terms of service, and copyright constraints.\nDo not treat markdown.new output as guaranteed complete for every page; verify critical extractions.\nReferences\nreferences/markdown-new-api.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/joelchance/markdown-convert",
    "publisherUrl": "https://clawhub.ai/joelchance/markdown-convert",
    "owner": "joelchance",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/markdown-convert",
    "downloadUrl": "https://openagent3.xyz/downloads/markdown-convert",
    "agentUrl": "https://openagent3.xyz/skills/markdown-convert/agent",
    "manifestUrl": "https://openagent3.xyz/skills/markdown-convert/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/markdown-convert/agent.md"
  }
}