[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PBMK52C20FC3GCFW0DK48P":3,"skill-same:01M6PBMK52C20FC3GCFW0DK48P":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":31,"commitSha":54,"skillDirectory":55,"forksCount":13,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6PBMK52C20FC3GCFW0DK48P","pi-web-search",null,"Give Pi Agents a safe web-search and fetch workflow using the installed pi-web-access package.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fpi-web-search\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"web","pi","search","pi web search","web search","https","pi-agent","web-search","main","community","fetch","access","safe","package","license","workflow","research","codex","github","2026-11-10 10:12:30",false,"---\nname: pi-web-search\ndescription: \"Give Pi Agents a safe web-search and fetch workflow using the installed pi-web-access package.\"\ncategory: research\nrisk: safe\nsource: community\nsource_repo: davidondrej\u002Fskills\nsource_type: community\ndate_added: \"2026-07-07\"\nauthor: davidondrej\ntags: [web-search, pi-agent, research]\ntools: [claude, codex]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Web Search\n\n## When to Use\n\n- Use when a Pi Agent task needs current web information, page fetches, PDFs, YouTube, or GitHub content.\n- Use when Pi should use its own web-access package instead of another agent browser tool.\n\nThe `pi-web-access` package is installed globally. Zero-config via Exa MCP (no API key), with fallback Exa → Perplexity → Gemini.\n\n## CRITICAL: always pass `workflow: \"none\"`\n\nEvery `web_search` call MUST include `workflow: \"none\"`. This skips the interactive browser curator popup (the user does not want it opening). No exceptions — single query or batched `queries`, always set `workflow: \"none\"`.\n\n```\nweb_search({ queries: [\"query 1\", \"query 2\"], workflow: \"none\" })\n```\n\n## Tools\n\n- `web_search` — search the web; returns synthesized answers with citations. Can be called many times per turn. **Always pass `workflow: \"none\"`.**\n- `code_search` — zero-key Exa code-context. Use for library\u002FAPI\u002Fcode lookups instead of generic `web_search`.\n- `fetch_content` — fetch URL(s) → markdown; handles PDFs, YouTube, GitHub.\n- `get_search_content` — big pages (>30k chars) are truncated in responses but stored in full; call this to pull the rest on demand so they don't blow context.\n\n## fetch_content specifics\n\n- **GitHub URLs are cloned, not scraped** — you get real files + a local path to explore with `read`\u002F`bash` (private repos need the `gh` CLI). Use this for dev work.\n- **PDFs** → auto-extracted to markdown in `~\u002FDownloads\u002F`, readable in sections (text-only, no OCR).\n- **YouTube\u002Fvideo** → full raw transcripts + frame extraction. Needs a `GEMINI_API_KEY` (not zero-config); frame extraction also needs `ffmpeg`\u002F`yt-dlp`.\n\n## Routing — match the user's phrasing\n\nAlways use the `web_search` tool. These counts are HARD MINIMUMS — count your queries before answering and do not stop short:\n\n- **\"web search\"** → **at least 2** queries, varied keywords\u002Fangles, then synthesize.\n- **\"extensive web research\"** → **at least 4** queries, totally different keywords and angles.\n- **\"deep research\"** → **at least 8** queries, totally different keywords and angles, run across 2–3 successive batches (refine angles after each batch), to learn as much as possible about the topic.\n\nA single batched `web_search` call counts each query in `queries[]` toward the total. If your first batch is under the minimum, fire another batch before synthesizing.\n\n## Fallback \u002F alternative: DeepAPI web search\n\nIf the Exa → Perplexity → Gemini chain fails, or you need ranked results with URLs:\n\n```bash\ntest -n \"$DEEPAPI_API_KEY\" || { echo \"DEEPAPI_API_KEY is not set\"; exit 1; }\ncurl -s --max-time 60 \"https:\u002F\u002Fdeepapi.co\u002Fv1\u002Fsearch\u002Fweb\" \\\n  -H \"Authorization: Bearer $DEEPAPI_API_KEY\" -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Idempotency-Key: $(uuidgen)\" \\\n  -d '{\"query\": \"your search terms\", \"maxResults\": 5, \"maxCostUsd\": \"0.05\"}'\n```\n\nResults are in `.output` (title, url, snippet per item). Query under 500 chars. Full details: `deepapi` skill.\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n","# Web Search\n\n## When to Use\n\n- Use when a Pi Agent task needs current web information, page fetches, PDFs, YouTube, or GitHub content.\n- Use when Pi should use its own web-access package instead of another agent browser tool.\n\nThe `pi-web-access` package is installed globally. Zero-config via Exa MCP (no API key), with fallback Exa → Perplexity → Gemini.\n\n## CRITICAL: always pass `workflow: \"none\"`\n\nEvery `web_search` call MUST include `workflow: \"none\"`. This skips the interactive browser curator popup (the user does not want it opening). No exceptions — single query or batched `queries`, always set `workflow: \"none\"`.\n\n```\nweb_search({ queries: [\"query 1\", \"query 2\"], workflow: \"none\" })\n```\n\n## Tools\n\n- `web_search` — search the web; returns synthesized answers with citations. Can be called many times per turn. **Always pass `workflow: \"none\"`.**\n- `code_search` — zero-key Exa code-context. Use for library\u002FAPI\u002Fcode lookups instead of generic `web_search`.\n- `fetch_content` — fetch URL(s) → markdown; handles PDFs, YouTube, GitHub.\n- `get_search_content` — big pages (>30k chars) are truncated in responses but stored in full; call this to pull the rest on demand so they don't blow context.\n\n## fetch_content specifics\n\n- **GitHub URLs are cloned, not scraped** — you get real files + a local path to explore with `read`\u002F`bash` (private repos need the `gh` CLI). Use this for dev work.\n- **PDFs** → auto-extracted to markdown in `~\u002FDownloads\u002F`, readable in sections (text-only, no OCR).\n- **YouTube\u002Fvideo** → full raw transcripts + frame extraction. Needs a `GEMINI_API_KEY` (not zero-config); frame extraction also needs `ffmpeg`\u002F`yt-dlp`.\n\n## Routing — match the user's phrasing\n\nAlways use the `web_search` tool. These counts are HARD MINIMUMS — count your queries before answering and do not stop short:\n\n- **\"web search\"** → **at least 2** queries, varied keywords\u002Fangles, then synthesize.\n- **\"extensive web research\"** → **at least 4** queries, totally different keywords and angles.\n- **\"deep research\"** → **at least 8** queries, totally different keywords and angles, run across 2–3 successive batches (refine angles after each batch), to learn as much as possible about the topic.\n\nA single batched `web_search` call counts each query in `queries[]` toward the total. If your first batch is under the minimum, fire another batch before synthesizing.\n\n## Fallback \u002F alternative: DeepAPI web search\n\nIf the Exa → Perplexity → Gemini chain fails, or you need ranked results with URLs:\n\n```bash\ntest -n \"$DEEPAPI_API_KEY\" || { echo \"DEEPAPI_API_KEY is not set\"; exit 1; }\ncurl -s --max-time 60 \"https:\u002F\u002Fdeepapi.co\u002Fv1\u002Fsearch\u002Fweb\" \\\n  -H \"Authorization: Bearer $DEEPAPI_API_KEY\" -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Idempotency-Key: $(uuidgen)\" \\\n  -d '{\"query\": \"your search terms\", \"maxResults\": 5, \"maxCostUsd\": \"0.05\"}'\n```\n\nResults are in `.output` (title, url, snippet per item). Query under 500 chars. Full details: `deepapi` skill.\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n",{"name":5,"risk":35,"tags":47,"tools":48,"author":50,"source":32,"license":14,"category":39,"date_added":51,"description":7,"source_repo":52,"source_type":32,"license_source":53},[30,29,39],[49,40],"claude","davidondrej","2026-07-07","davidondrej\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fpi-web-search","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill pi-web-search",{"tool":65,"command":66},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill pi-web-search",{"tool":68,"command":69},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill pi-web-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fpi-web-search\u002FSKILL.md",true,[],[74,100,124,142,169,192],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":83,"publishedAt":42},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[84,85,86,87,88,89,76,90,91,34,92,93,32,31,94,95,96,97,98,99],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","configure","only","active","critical","scope","scripts","relevant","implementing",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":42},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[107,108,109,110,111,112,113,114,115,116,117,118,119,93,120,32,121,122,95,123],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":42},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[131,132,133,35,41,40,39,37,28,134,33,135,136,32,31,137,138,139,140,141],"transcript","youtube transcript","youtube","text","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":159,"publishedAt":42},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[148,151,154],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[131,132,133,160,35,161,41,40,37,25,162,163,164,33,165,32,31,166,167,168],"youtube transcript skills","gemini","api","Video","browse","api-integration","free","card","channels",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":179,"publishedAt":42},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[175,178],{"categoryNo":176,"categoryName":177,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},[133,180,181,111,35,38,182,183,184,37,163,185,186,187,188,31,189,137,190,191],"youtube notetaker","notetaker","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":199,"publishedAt":42},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[198],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},[200,133,201,202,35,161,25,203,204,162,163,164,33,205,165,32,31,166,206,140],"youtube full","full","google","server","dlp","credits","automatic"]