{ "schemaVersion": "1.0", "item": { "slug": "x-manual-surf-notes", "name": "X Manual Surf Notes (手动刷帖笔记)", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/kaima2022/x-manual-surf-notes", "canonicalUrl": "https://clawhub.ai/kaima2022/x-manual-surf-notes", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/x-manual-surf-notes", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=x-manual-surf-notes", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/browser-scrape-snippets.md", "references/listing.md" ], "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/x-manual-surf-notes" }, "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/x-manual-surf-notes", "agentPageUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/agent", "manifestUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/agent.json", "briefUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/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": "适用场景", "body": "用户明确要求：不要爬取 / 不要搜索，而是像人一样用浏览器刷 X 首页推荐（For You）。\n产出：把刷到的帖子以中文记录到文档中（持续追加），并去重。" }, { "title": "前置条件（必须满足）", "body": "使用 browser 工具，profile=\"chrome\"（Chrome 扩展 relay）。\n用户已在目标 tab 点击扩展图标，徽标 ON（已附加）。\n用户已登录 X（否则 For You 没意义/内容不完整）。" }, { "title": "输出文件（默认）", "body": "追加到：/home/makai/.openclaw/workspace/projects/x-ai-surf/x-ai-notes.md\n每次追加一个批次区块：\n\n批次时间（GMT+8）\n来源：X Home / For You\n操作：下滑加载 + 点进详情\n条目数：N" }, { "title": "工作流（低 token 版，推荐）", "body": "默认测试 N=5；正式刷 N>=50。\n\n聚焦 tab：确认当前是 https://x.com/home。\n下滑加载：滚动 1~3 次（每次 ~800-1400px），等内容加载。\n采样候选帖子：从当前视窗抽取若干 status 链接，做 base-url 归一化（去掉 /photo/1、/analytics 等后缀）。\n逐条点进详情（模拟人）：\n\n打开 status URL\n如有 “Show more/显示更多” 则点击展开\n抓取：作者、时间（datetime）、正文（含 thread 则只取主帖 + 明显的第一条自回复，别贪多）\n返回 Home（或直接打开下一条）\n\n\n中文化：\n\n如果正文是英文：用模型生成 一条中文转述（不要逐字硬翻；保留关键信息、产品名、数字、链接）。\n如果已包含中文：可轻微润色，但别改意思。\n\n\n去重规则：\n\n以 https://x.com//status/ 为唯一键；同批次、跨批次都不重复写。\n如果是同一事件不同人转发：允许记录，但评论要标“转述/二手”。\n\n\n写入文档：追加一个批次，格式固定：\n\n### 运行批次：YYYY-MM-DD HH:mm（GMT+8）\n- 本批来源：浏览器模拟（X 首页 For You）\n- 操作：Home → 下滑加载 → 点击帖子详情 → 采集 → 中文转述 → 去重 → 追加\n- 本批条目：N\n\n#### 条目\n1) 时间：YYYY-MM-DD HH:mm:ss\n 内容：@handle｜中文转述（1-3 句）\n 链接：https://x.com/.../status/...\n 评论：一句话判断价值/可信度/下一步跟踪\n\n---" }, { "title": "评论写法（强约束，省 token）", "body": "每条评论只写一句，三选一：\n\n值得跟：为什么（发布/开源/论文/产品更新/一手信号）\n待核验：缺什么信息，下一步点哪里（引用/原文/链接）\n噪音：为什么噪音（梗/情绪/无细节）" }, { "title": "常见坑", "body": "X 页面频繁导航会导致 evaluate 上下文丢失：优先用 browser.navigate + wait，每条独立抓取。\n抓正文时别把“浏览量/按钮文案”当正文；以 article 的主要文本为准，必要时清洗。" }, { "title": "运行参数建议", "body": "测试：N=5\n正式：每批 N=50~80（保证信息密度；避免无意义灌水）" } ], "body": "X 手动冲浪 → 中文笔记（浏览器模拟）\n适用场景\n用户明确要求：不要爬取 / 不要搜索，而是像人一样用浏览器刷 X 首页推荐（For You）。\n产出：把刷到的帖子以中文记录到文档中（持续追加），并去重。\n前置条件（必须满足）\n使用 browser 工具，profile=\"chrome\"（Chrome 扩展 relay）。\n用户已在目标 tab 点击扩展图标，徽标 ON（已附加）。\n用户已登录 X（否则 For You 没意义/内容不完整）。\n输出文件（默认）\n追加到：/home/makai/.openclaw/workspace/projects/x-ai-surf/x-ai-notes.md\n每次追加一个批次区块：\n批次时间（GMT+8）\n来源：X Home / For You\n操作：下滑加载 + 点进详情\n条目数：N\n工作流（低 token 版，推荐）\n\n默认测试 N=5；正式刷 N>=50。\n\n聚焦 tab：确认当前是 https://x.com/home。\n下滑加载：滚动 1~3 次（每次 ~800-1400px），等内容加载。\n采样候选帖子：从当前视窗抽取若干 status 链接，做 base-url 归一化（去掉 /photo/1、/analytics 等后缀）。\n逐条点进详情（模拟人）：\n打开 status URL\n如有 “Show more/显示更多” 则点击展开\n抓取：作者、时间（datetime）、正文（含 thread 则只取主帖 + 明显的第一条自回复，别贪多）\n返回 Home（或直接打开下一条）\n中文化：\n如果正文是英文：用模型生成 一条中文转述（不要逐字硬翻；保留关键信息、产品名、数字、链接）。\n如果已包含中文：可轻微润色，但别改意思。\n去重规则：\n以 https://x.com//status/ 为唯一键；同批次、跨批次都不重复写。\n如果是同一事件不同人转发：允许记录，但评论要标“转述/二手”。\n写入文档：追加一个批次，格式固定：\n### 运行批次：YYYY-MM-DD HH:mm（GMT+8）\n- 本批来源：浏览器模拟（X 首页 For You）\n- 操作：Home → 下滑加载 → 点击帖子详情 → 采集 → 中文转述 → 去重 → 追加\n- 本批条目：N\n\n#### 条目\n1) 时间：YYYY-MM-DD HH:mm:ss\n 内容：@handle｜中文转述（1-3 句）\n 链接：https://x.com/.../status/...\n 评论：一句话判断价值/可信度/下一步跟踪\n\n---\n\n评论写法（强约束，省 token）\n\n每条评论只写一句，三选一：\n\n值得跟：为什么（发布/开源/论文/产品更新/一手信号）\n待核验：缺什么信息，下一步点哪里（引用/原文/链接）\n噪音：为什么噪音（梗/情绪/无细节）\n常见坑\nX 页面频繁导航会导致 evaluate 上下文丢失：优先用 browser.navigate + wait，每条独立抓取。\n抓正文时别把“浏览量/按钮文案”当正文；以 article 的主要文本为准，必要时清洗。\n运行参数建议\n测试：N=5\n正式：每批 N=50~80（保证信息密度；避免无意义灌水）" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kaima2022/x-manual-surf-notes", "publisherUrl": "https://clawhub.ai/kaima2022/x-manual-surf-notes", "owner": "kaima2022", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/x-manual-surf-notes", "downloadUrl": "https://openagent3.xyz/downloads/x-manual-surf-notes", "agentUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/agent", "manifestUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/agent.json", "briefUrl": "https://openagent3.xyz/skills/x-manual-surf-notes/agent.md" } }