{ "schemaVersion": "1.0", "item": { "slug": "mupeng-web-claude", "name": "Web Claude", "source": "tencent", "type": "skill", "category": "开发巄具", "sourceUrl": "https://clawhub.ai/mupengi-bot/mupeng-web-claude", "canonicalUrl": "https://clawhub.ai/mupengi-bot/mupeng-web-claude", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/mupeng-web-claude", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mupeng-web-claude", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/mupeng-web-claude" }, "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/mupeng-web-claude", "agentPageUrl": "https://openagent3.xyz/skills/mupeng-web-claude/agent", "manifestUrl": "https://openagent3.xyz/skills/mupeng-web-claude/agent.json", "briefUrl": "https://openagent3.xyz/skills/mupeng-web-claude/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": "Unified Web Search šŸ§", "body": "Reliable web search via 3-tier fallback strategy: Brave API ā†’ DuckDuckGo ā†’ claude.ai browser" }, { "title": "Tier 1: web_search (Brave API) ā€” āš” Fast and Reliable (Recommended)", "body": "Use OpenClaw built-in web_search tool.\n\nweb_search(query=\"search query\", count=5, freshness=\"pw\")\n\nPros:\n\nFast response (1-2s)\nStructured JSON results\nfreshness parameter support (pd=24h, pw=1 week, pm=1 month)\nsearch_lang, country parameters for Korean/regional search\n\nCons:\n\nRequires Brave API key\nmissing_brave_api_key error without key" }, { "title": "Tier 2: duckduckgo-search ā€” šŸ”’ Privacy-focused (Fallback)", "body": "Use DuckDuckGo API when Brave fails.\n\npython -c \"\nfrom duckduckgo_search import DDGS\n\nwith DDGS() as ddgs:\n results = list(ddgs.text('query', region='wt-wt', max_results=5))\n for r in results:\n print(f\\\"{r['title']}: {r['href']}\\\")\n\"\n\nPros:\n\nNo API key required\nPrivacy-friendly\nVarious search types (text, news, images, videos)\n\nCons:\n\nLower result quality than Brave\nRequest limits (blocks if too many consecutive requests)" }, { "title": "Tier 3: web-claude (Browser) ā€” šŸ§  Analysis+Search (Last Resort)", "body": "Trigger web search in claude.ai browser tab.\n\n1. browser navigate ā†’ https://claude.ai/new\n2. browser act type ā†’ \"search question\"\n3. browser act press ā†’ Enter\n4. sleep 15-30s\n5. browser snapshot ā†’ extract response\n\nPros:\n\nNo API key required\nclaude.ai auto web search + analyze + summarize\nUseful for complex research\n\nCons:\n\nSlow (15-30s)\nRequires browser (port 18800, openclaw profile)\nDaily message limit (free account)\nAutomation detection risk" }, { "title": "Auto-fallback Logic", "body": "if web_search available:\n try web_search(query)\n if success: return results\n \nif web_search failed or unavailable:\n try duckduckgo-search\n if success: return results\n \nif both failed:\n fallback to web-claude browser method" }, { "title": "Search Results Auto-cache", "body": "All search results automatically saved to memory/research/ folder:\n\nFilename Convention:\n\nmemory/research/search-YYYY-MM-DD-HH-MM-[keyword].md\n\nSaved Content:\n\nSearch query\nTimestamp\nSearch method used (Brave/DuckDuckGo/claude.ai)\nSearch results (links + summaries)\nExtracted insights\n\nExample:\n\n# Web Search: AI Agent Market Size\n\n- **Search Time:** 2026-02-14 07:56 KST\n- **Search Method:** web_search (Brave API)\n- **Query:** \"AI agent market size 2026\"\n\n## Results\n\n1. **AI Agent Market to Reach $47B by 2030** - TechCrunch\n https://techcrunch.com/...\n - CAGR 43.2% growth forecast\n - Enterprise agents account for 60%\n\n2. **Korean AI Market Exceeds 1 Trillion KRW** - Chosun Ilbo\n https://chosun.com/...\n - Q1 2026 basis\n - Led by generative AI\n\n...\n\n## Insights\n\n- AI agent market growing rapidly\n- Enterprise automation is core driver\n- Korean market also active" }, { "title": "General Search", "body": "\"Search for latest AI agent trends\"\n\"Find 2026 Korean SaaS investment status\"\n\nā†’ Auto-attempts Tier 1 Brave ā†’ Tier 2 DDG ā†’ Tier 3 claude.ai" }, { "title": "Force Specific Method", "body": "# Brave only\n\"Search with web_search: AI market size\"\n\n# DuckDuckGo only\n\"Search with duckduckgo: privacy-focused\"\n\n# claude.ai browser only\n\"Analyze with web-claude: complex market research\"" }, { "title": "Using freshness Parameter", "body": "# Last 24 hours news\nweb_search(..., freshness=\"pd\")\n\n# Last week\nweb_search(..., freshness=\"pw\")\n\n# Last month\nweb_search(..., freshness=\"pm\")" }, { "title": "Korean Search", "body": "web_search(query=\"query\", search_lang=\"ko\", country=\"KR\")" }, { "title": "Prerequisites", "body": "OpenClaw browser running (port 18800)\nclaude.ai logged in (openclaw profile)" }, { "title": "Automation Steps", "body": "1. browser navigate ā†’ https://claude.ai/new (or existing tab)\n2. browser snapshot ā†’ save targetId\n3. Find input field (contenteditable div or textarea)\n4. browser act type ā†’ enter question\n5. browser act press ā†’ Enter\n6. sleep 15-30s (wait for response)\n7. browser snapshot ā†’ extract response text\n8. Return result to caller + save to memory/research/" }, { "title": "Tips", "body": "Clear search intent: Include time keywords like \"latest data\", \"as of 2026\", \"current\"\nExplicit request: Specify \"search and tell me\"\nRecommend new chat: Prevent previous context pollution\nAutomation detection caution: Don't ask consecutive questions too quickly" }, { "title": "competitor-watch", "body": "Use this unified search skill when monitoring competitors:\n\nquick-check: Prioritize web_search\ndeep-dive: Combine web_search + duckduckgo\nComplex analysis: web-claude fallback" }, { "title": "cardnews", "body": "Use search results for card news research:\n\nTopic research ā†’ unified search\nSearch results ā†’ cardnews content planning" }, { "title": "yt-digest", "body": "Search for related info after YouTube summary:\n\nVideo topic ā†’ additional web search\nSearch results ā†’ supplementary insights" }, { "title": "When to Use Which Method", "body": "SituationRecommended MethodNeed fast searchweb_search (Brave)No Brave keyduckduckgo-searchPrivacy importantduckduckgo-searchNeed analysis+summaryweb-claudeComplex researchweb-claudeImage/video searchduckduckgo-searchLatest news (24h)web_search (freshness=\"pd\")" }, { "title": "Cautions", "body": "web_search: Requires Brave API key (auto-fallback if unavailable)\nduckduckgo: Blocks if too many consecutive requests (wait 1s between requests)\nweb-claude: Daily message limit, requires browser\nSearch result cache: memory/research/ folder auto-created\n\nšŸ§ Built by ė¬“ķŽ­ģ“ ā€” Mupengism ecosystem skill" } ], "body": "Unified Web Search šŸ§\n\nReliable web search via 3-tier fallback strategy: Brave API ā†’ DuckDuckGo ā†’ claude.ai browser\n\nSearch Strategy\nTier 1: web_search (Brave API) ā€” āš” Fast and Reliable (Recommended)\n\nUse OpenClaw built-in web_search tool.\n\nweb_search(query=\"search query\", count=5, freshness=\"pw\")\n\n\nPros:\n\nFast response (1-2s)\nStructured JSON results\nfreshness parameter support (pd=24h, pw=1 week, pm=1 month)\nsearch_lang, country parameters for Korean/regional search\n\nCons:\n\nRequires Brave API key\nmissing_brave_api_key error without key\nTier 2: duckduckgo-search ā€” šŸ”’ Privacy-focused (Fallback)\n\nUse DuckDuckGo API when Brave fails.\n\npython -c \"\nfrom duckduckgo_search import DDGS\n\nwith DDGS() as ddgs:\n results = list(ddgs.text('query', region='wt-wt', max_results=5))\n for r in results:\n print(f\\\"{r['title']}: {r['href']}\\\")\n\"\n\n\nPros:\n\nNo API key required\nPrivacy-friendly\nVarious search types (text, news, images, videos)\n\nCons:\n\nLower result quality than Brave\nRequest limits (blocks if too many consecutive requests)\nTier 3: web-claude (Browser) ā€” šŸ§  Analysis+Search (Last Resort)\n\nTrigger web search in claude.ai browser tab.\n\n1. browser navigate ā†’ https://claude.ai/new\n2. browser act type ā†’ \"search question\"\n3. browser act press ā†’ Enter\n4. sleep 15-30s\n5. browser snapshot ā†’ extract response\n\n\nPros:\n\nNo API key required\nclaude.ai auto web search + analyze + summarize\nUseful for complex research\n\nCons:\n\nSlow (15-30s)\nRequires browser (port 18800, openclaw profile)\nDaily message limit (free account)\nAutomation detection risk\nAuto-fallback Logic\nif web_search available:\n try web_search(query)\n if success: return results\n \nif web_search failed or unavailable:\n try duckduckgo-search\n if success: return results\n \nif both failed:\n fallback to web-claude browser method\n\nSearch Results Auto-cache\n\nAll search results automatically saved to memory/research/ folder:\n\nFilename Convention:\n\nmemory/research/search-YYYY-MM-DD-HH-MM-[keyword].md\n\n\nSaved Content:\n\nSearch query\nTimestamp\nSearch method used (Brave/DuckDuckGo/claude.ai)\nSearch results (links + summaries)\nExtracted insights\n\nExample:\n\n# Web Search: AI Agent Market Size\n\n- **Search Time:** 2026-02-14 07:56 KST\n- **Search Method:** web_search (Brave API)\n- **Query:** \"AI agent market size 2026\"\n\n## Results\n\n1. **AI Agent Market to Reach $47B by 2030** - TechCrunch\n https://techcrunch.com/...\n - CAGR 43.2% growth forecast\n - Enterprise agents account for 60%\n\n2. **Korean AI Market Exceeds 1 Trillion KRW** - Chosun Ilbo\n https://chosun.com/...\n - Q1 2026 basis\n - Led by generative AI\n\n...\n\n## Insights\n\n- AI agent market growing rapidly\n- Enterprise automation is core driver\n- Korean market also active\n\nUsage\nGeneral Search\n\"Search for latest AI agent trends\"\n\"Find 2026 Korean SaaS investment status\"\n\n\nā†’ Auto-attempts Tier 1 Brave ā†’ Tier 2 DDG ā†’ Tier 3 claude.ai\n\nForce Specific Method\n# Brave only\n\"Search with web_search: AI market size\"\n\n# DuckDuckGo only\n\"Search with duckduckgo: privacy-focused\"\n\n# claude.ai browser only\n\"Analyze with web-claude: complex market research\"\n\nUsing freshness Parameter\n# Last 24 hours news\nweb_search(..., freshness=\"pd\")\n\n# Last week\nweb_search(..., freshness=\"pw\")\n\n# Last month\nweb_search(..., freshness=\"pm\")\n\nKorean Search\nweb_search(query=\"query\", search_lang=\"ko\", country=\"KR\")\n\nBrowser Method (web-claude) Details\nPrerequisites\nOpenClaw browser running (port 18800)\nclaude.ai logged in (openclaw profile)\nAutomation Steps\n1. browser navigate ā†’ https://claude.ai/new (or existing tab)\n2. browser snapshot ā†’ save targetId\n3. Find input field (contenteditable div or textarea)\n4. browser act type ā†’ enter question\n5. browser act press ā†’ Enter\n6. sleep 15-30s (wait for response)\n7. browser snapshot ā†’ extract response text\n8. Return result to caller + save to memory/research/\n\nTips\nClear search intent: Include time keywords like \"latest data\", \"as of 2026\", \"current\"\nExplicit request: Specify \"search and tell me\"\nRecommend new chat: Prevent previous context pollution\nAutomation detection caution: Don't ask consecutive questions too quickly\nIntegration with Other Skills\ncompetitor-watch\n\nUse this unified search skill when monitoring competitors:\n\nquick-check: Prioritize web_search\ndeep-dive: Combine web_search + duckduckgo\nComplex analysis: web-claude fallback\ncardnews\n\nUse search results for card news research:\n\nTopic research ā†’ unified search\nSearch results ā†’ cardnews content planning\nyt-digest\n\nSearch for related info after YouTube summary:\n\nVideo topic ā†’ additional web search\nSearch results ā†’ supplementary insights\nWhen to Use Which Method\nSituation\tRecommended Method\nNeed fast search\tweb_search (Brave)\nNo Brave key\tduckduckgo-search\nPrivacy important\tduckduckgo-search\nNeed analysis+summary\tweb-claude\nComplex research\tweb-claude\nImage/video search\tduckduckgo-search\nLatest news (24h)\tweb_search (freshness=\"pd\")\nCautions\nweb_search: Requires Brave API key (auto-fallback if unavailable)\nduckduckgo: Blocks if too many consecutive requests (wait 1s between requests)\nweb-claude: Daily message limit, requires browser\nSearch result cache: memory/research/ folder auto-created\n\nšŸ§ Built by ė¬“ķŽ­ģ“ ā€” Mupengism ecosystem skill" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/mupengi-bot/mupeng-web-claude", "publisherUrl": "https://clawhub.ai/mupengi-bot/mupeng-web-claude", "owner": "mupengi-bot", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/mupeng-web-claude", "downloadUrl": "https://openagent3.xyz/downloads/mupeng-web-claude", "agentUrl": "https://openagent3.xyz/skills/mupeng-web-claude/agent", "manifestUrl": "https://openagent3.xyz/skills/mupeng-web-claude/agent.json", "briefUrl": "https://openagent3.xyz/skills/mupeng-web-claude/agent.md" } }