[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F60PFXGBZ15RK01V421008":3,"skill-same:01M7F60PFXGBZ15RK01V421008":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7F60PFXGBZ15RK01V421008","terminal-web-research",null,"Use when web tools fail: keyless terminal research routes.","chaorenex1\u002Fhermes-home-content","chaorenex1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23194925?v=4","01M7F5NA1D1D02R2MEMYQN2NZT","chan chan","01M7F5NA20KTHMTY2015CYM1TZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Fterminal-web-research\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\r\nname: terminal-web-research\r\ndescription: \"Use when web tools fail: keyless terminal research routes.\"\r\nversion: 1.0.0\r\nauthor: Masía\r\nlicense: MIT\r\nplatforms: [windows, linux, macos]\r\nmetadata:\r\n  hermes:\r\n    tags: [Research, Search, Fallback, Curl, APIs]\r\n    category: web\r\n    related_skills: [blocked-page-recovery, grounded-citations, search-rule-engineering]\r\n---\r\n\r\n# Terminal Web Research (web tools down \u002F blocked)\r\n\r\nCompanion to `blocked-page-recovery` (per-URL archive recovery). This skill is\r\nthe routing layer: what to reach for when `web_search`\u002F`web_extract` are\r\nunavailable, misconfigured, or the search engines block direct fetches — and\r\nfor \"does X exist \u002F which port exists\" reconnaissance, where structured APIs\r\nbeat scraping outright.\r\n\r\n## When to Use\r\n\r\n- `web_search`\u002F`web_extract` error out, time out, or are unconfigured, and\r\n  the task still needs web facts.\r\n- A search engine or site challenges direct fetches (bot page, empty body, or\r\n  a multi-KB HTTP 200 interstitial).\r\n- \"Does a Python port \u002F SDK \u002F alternative for X exist?\" reconnaissance, where\r\n  org and registry APIs answer in one call.\r\n- A JS-heavy content page needs rendering and the browser tools are not\r\n  available to carry it.\r\n\r\n## Route order\r\n\r\n1. **Structured APIs first** when the question is about software, packages,\r\n   repos, or orgs (§2) — fastest and most reliable, no anti-bot surface.\r\n2. **Keyless SERP route** for prose \u002F news \u002F docs discovery (§1).\r\n3. **r.jina.ai** to render content pages that block plain curl (§3).\r\n4. **Real browser** only when it is connected and the page is JS-heavy; the\r\n   routes above should otherwise carry the task.\r\n\r\nWhen `web_search`\u002F`web_extract` error with a provider-config message (\"no\r\nregistered web search provider has that name\"), the permanent fix is the user\r\npicking a provider via `hermes tools` — note it, but do not stall the task on\r\nit; the terminal routes below complete the research anyway.\r\n\r\n## 1. Keyless SERP routes (preference order)\r\n\r\n```bash\r\nUA=\"Mozilla\u002F5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\u002F537.36 (KHTML, like Gecko) Chrome\u002F126 Safari\u002F537.36\"\r\ncurl -s -m 30 -A \"$UA\" \"https:\u002F\u002Flite.duckduckgo.com\u002Flite\u002F?q=\u003Curl-encoded>\" -o lite.html\r\ncurl -s -m 40 \"https:\u002F\u002Fr.jina.ai\u002Fhttps:\u002F\u002Fwww.bing.com\u002Fsearch?q=\u003Curl-encoded>\" -o serp.md\r\n```\r\n\r\n- `lite.duckduckgo.com\u002Flite\u002F` accepted a first query when\r\n  `html.duckduckgo.com` was already serving its \"anomaly\" bot page, and\r\n  returns full desktop result HTML. Result hrefs are wrapped as\r\n  `uddg=\u003Curlencoded-url>` plus an `&rut=` tail — decode with\r\n  `urllib.parse.unquote`, then strip the tail.\r\n- `www.bing.com\u002Fsearch` via plain curl returns a ~200-byte bot wall; route\r\n  global Bing SERPs through `r.jina.ai` (comes back as markdown with titles\r\n  and URLs), or use `cn.bing.com\u002Fsearch`, which stays curl-friendly.\r\n- `r.jina.ai` keyless calls are rate-limited and flaky but often succeed —\r\n  attempt once WITHOUT a key; add `Authorization: Bearer $JINA_API_KEY` only\r\n  after a 401\u002FTurnstile.\r\n- Challenge detection: tiny body plus markers `anomaly`, `captcha`, `robot`,\r\n  `unusual traffic` = blocked. Switch route once; never retry unchanged.\r\n\r\n## 2. Structured APIs (skip SERPs entirely)\r\n\r\nAll keyless, all runnable straight from the terminal:\r\n\r\n- Enumerate an org's repos (settles \"is there an official SDK?\" in one call):\r\n  `gh api \"search\u002Frepositories?q=org:\u003Corg>&per_page=50\" --jq '.items[] | .full_name + \"  *\" + (.stargazers_count|tostring) + \"  \" + ((.description \u002F\u002F \"\") | .[0:130])'`\r\n- Find ports \u002F alternatives \u002F prior art:\r\n  `gh api \"search\u002Frepositories?q=\u003Ctopic>+language:python&sort=stars&per_page=10\" --jq '.items[] | .full_name + \"  *\" + (.stargazers_count|tostring) + \"  \" + ((.description \u002F\u002F \"\")|.[0:130])'`\r\n- Repo facts and README:\r\n  `gh api repos\u002F\u003Co>\u002F\u003Cr> --jq '{full_name, description, stars: .stargazers_count, language, homepage, pushed_at}'`\r\n  and `gh api repos\u002F\u003Co>\u002F\u003Cr>\u002Freadme --jq '.content' | base64 -d | head -80`\r\n- PyPI metadata: `curl -s https:\u002F\u002Fpypi.org\u002Fpypi\u002F\u003Cpkg>\u002Fjson` — read\r\n  `.info.{version,summary,requires_python,project_urls}` and the `.releases`\r\n  keys. A \u003C100 B reply = name absent; a ~1 KB reply can be an unrelated\r\n  package — read the summary before citing it.\r\n- Prefer `gh api` over python-urllib for GitHub on Windows hosts (TLS quirks).\r\n- Before recommending a community port, check the project's own docs for what\r\n  its official SDK does and does not cover (e.g. a docs \"SDK\" page stating\r\n  in-process TypeScript-only is the evidence that a Python port is warranted).\r\n\r\n## 3. Rendering blocked content pages\r\n\r\n`r.jina.ai\u002F\u003Curl>` renders any page as markdown, JS SPAs included — try it\r\nbefore escalating to a browser. For durable, timestamped copies of a single\r\nblocked URL, use the archive ladder in `blocked-page-recovery` instead\r\n(snapshot provenance matters when citing).\r\n\r\n## Windows host (git-bash) rules\r\n\r\n- Write curl artifacts as `cd \u003Cresearch-dir> && curl -o out.html`; `curl -o`\r\n  onto a `~`-expanded or `\u002Fc\u002F...` path fails (\"No such file or directory\") —\r\n  native binaries do not get MSYS path translation; a `C:\u002F...` path also works.\r\n- Truncated terminal output prints its full-log path\r\n  (`...\\hermes\\cache\\terminal-output\\out-*.log`); read it with `read_file`\r\n  instead of re-running the command.\r\n- Parse in `execute_code` (Python `re`\u002F`json` + a small strip_html helper)\r\n  rather than shell one-liners; keep all artifacts in one per-topic research\r\n  directory so later steps and aggregation can reuse them.\r\n\r\n## Pitfalls\r\n\r\n- Don't dump raw HTML or long text to stdout — save to a file, parse\r\n  programmatically; stdout truncates.\r\n- Don't trust status codes or byte sizes: challenge pages are multi-KB HTTP\r\n  200s — validate content markers (expected title words, strings).\r\n- Don't cite existence from a search snippet: confirm through the registry \u002F\r\n  repo API response itself (its fields are the evidence).\r\n- Don't alternate between two blocked routes — change the endpoint, the\r\n  proxy, or move to an API once, then stop with a precise blocker if all fail.\r\n- Answer \"is there an X for Y\" questions with a verified pointer per candidate\r\n  (repo, package, version, last-push date) — a list of names without evidence\r\n  is not a satisfying answer.\r\n","# Terminal Web Research (web tools down \u002F blocked)\r\n\r\nCompanion to `blocked-page-recovery` (per-URL archive recovery). This skill is\r\nthe routing layer: what to reach for when `web_search`\u002F`web_extract` are\r\nunavailable, misconfigured, or the search engines block direct fetches — and\r\nfor \"does X exist \u002F which port exists\" reconnaissance, where structured APIs\r\nbeat scraping outright.\r\n\r\n## When to Use\r\n\r\n- `web_search`\u002F`web_extract` error out, time out, or are unconfigured, and\r\n  the task still needs web facts.\r\n- A search engine or site challenges direct fetches (bot page, empty body, or\r\n  a multi-KB HTTP 200 interstitial).\r\n- \"Does a Python port \u002F SDK \u002F alternative for X exist?\" reconnaissance, where\r\n  org and registry APIs answer in one call.\r\n- A JS-heavy content page needs rendering and the browser tools are not\r\n  available to carry it.\r\n\r\n## Route order\r\n\r\n1. **Structured APIs first** when the question is about software, packages,\r\n   repos, or orgs (§2) — fastest and most reliable, no anti-bot surface.\r\n2. **Keyless SERP route** for prose \u002F news \u002F docs discovery (§1).\r\n3. **r.jina.ai** to render content pages that block plain curl (§3).\r\n4. **Real browser** only when it is connected and the page is JS-heavy; the\r\n   routes above should otherwise carry the task.\r\n\r\nWhen `web_search`\u002F`web_extract` error with a provider-config message (\"no\r\nregistered web search provider has that name\"), the permanent fix is the user\r\npicking a provider via `hermes tools` — note it, but do not stall the task on\r\nit; the terminal routes below complete the research anyway.\r\n\r\n## 1. Keyless SERP routes (preference order)\r\n\r\n```bash\r\nUA=\"Mozilla\u002F5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\u002F537.36 (KHTML, like Gecko) Chrome\u002F126 Safari\u002F537.36\"\r\ncurl -s -m 30 -A \"$UA\" \"https:\u002F\u002Flite.duckduckgo.com\u002Flite\u002F?q=\u003Curl-encoded>\" -o lite.html\r\ncurl -s -m 40 \"https:\u002F\u002Fr.jina.ai\u002Fhttps:\u002F\u002Fwww.bing.com\u002Fsearch?q=\u003Curl-encoded>\" -o serp.md\r\n```\r\n\r\n- `lite.duckduckgo.com\u002Flite\u002F` accepted a first query when\r\n  `html.duckduckgo.com` was already serving its \"anomaly\" bot page, and\r\n  returns full desktop result HTML. Result hrefs are wrapped as\r\n  `uddg=\u003Curlencoded-url>` plus an `&rut=` tail — decode with\r\n  `urllib.parse.unquote`, then strip the tail.\r\n- `www.bing.com\u002Fsearch` via plain curl returns a ~200-byte bot wall; route\r\n  global Bing SERPs through `r.jina.ai` (comes back as markdown with titles\r\n  and URLs), or use `cn.bing.com\u002Fsearch`, which stays curl-friendly.\r\n- `r.jina.ai` keyless calls are rate-limited and flaky but often succeed —\r\n  attempt once WITHOUT a key; add `Authorization: Bearer $JINA_API_KEY` only\r\n  after a 401\u002FTurnstile.\r\n- Challenge detection: tiny body plus markers `anomaly`, `captcha`, `robot`,\r\n  `unusual traffic` = blocked. Switch route once; never retry unchanged.\r\n\r\n## 2. Structured APIs (skip SERPs entirely)\r\n\r\nAll keyless, all runnable straight from the terminal:\r\n\r\n- Enumerate an org's repos (settles \"is there an official SDK?\" in one call):\r\n  `gh api \"search\u002Frepositories?q=org:\u003Corg>&per_page=50\" --jq '.items[] | .full_name + \"  *\" + (.stargazers_count|tostring) + \"  \" + ((.description \u002F\u002F \"\") | .[0:130])'`\r\n- Find ports \u002F alternatives \u002F prior art:\r\n  `gh api \"search\u002Frepositories?q=\u003Ctopic>+language:python&sort=stars&per_page=10\" --jq '.items[] | .full_name + \"  *\" + (.stargazers_count|tostring) + \"  \" + ((.description \u002F\u002F \"\")|.[0:130])'`\r\n- Repo facts and README:\r\n  `gh api repos\u002F\u003Co>\u002F\u003Cr> --jq '{full_name, description, stars: .stargazers_count, language, homepage, pushed_at}'`\r\n  and `gh api repos\u002F\u003Co>\u002F\u003Cr>\u002Freadme --jq '.content' | base64 -d | head -80`\r\n- PyPI metadata: `curl -s https:\u002F\u002Fpypi.org\u002Fpypi\u002F\u003Cpkg>\u002Fjson` — read\r\n  `.info.{version,summary,requires_python,project_urls}` and the `.releases`\r\n  keys. A \u003C100 B reply = name absent; a ~1 KB reply can be an unrelated\r\n  package — read the summary before citing it.\r\n- Prefer `gh api` over python-urllib for GitHub on Windows hosts (TLS quirks).\r\n- Before recommending a community port, check the project's own docs for what\r\n  its official SDK does and does not cover (e.g. a docs \"SDK\" page stating\r\n  in-process TypeScript-only is the evidence that a Python port is warranted).\r\n\r\n## 3. Rendering blocked content pages\r\n\r\n`r.jina.ai\u002F\u003Curl>` renders any page as markdown, JS SPAs included — try it\r\nbefore escalating to a browser. For durable, timestamped copies of a single\r\nblocked URL, use the archive ladder in `blocked-page-recovery` instead\r\n(snapshot provenance matters when citing).\r\n\r\n## Windows host (git-bash) rules\r\n\r\n- Write curl artifacts as `cd \u003Cresearch-dir> && curl -o out.html`; `curl -o`\r\n  onto a `~`-expanded or `\u002Fc\u002F...` path fails (\"No such file or directory\") —\r\n  native binaries do not get MSYS path translation; a `C:\u002F...` path also works.\r\n- Truncated terminal output prints its full-log path\r\n  (`...\\hermes\\cache\\terminal-output\\out-*.log`); read it with `read_file`\r\n  instead of re-running the command.\r\n- Parse in `execute_code` (Python `re`\u002F`json` + a small strip_html helper)\r\n  rather than shell one-liners; keep all artifacts in one per-topic research\r\n  directory so later steps and aggregation can reuse them.\r\n\r\n## Pitfalls\r\n\r\n- Don't dump raw HTML or long text to stdout — save to a file, parse\r\n  programmatically; stdout truncates.\r\n- Don't trust status codes or byte sizes: challenge pages are multi-KB HTTP\r\n  200s — validate content markers (expected title words, strings).\r\n- Don't cite existence from a search snippet: confirm through the registry \u002F\r\n  repo API response itself (its fields are the evidence).\r\n- Don't alternate between two blocked routes — change the endpoint, the\r\n  proxy, or move to an API once, then stop with a precise blocker if all fail.\r\n- Answer \"is there an X for Y\" questions with a verified pointer per candidate\r\n  (repo, package, version, last-push date) — a list of names without evidence\r\n  is not a satisfying answer.\r\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":39,"description":7},"Masía","1.0.0",{"hermes":27},{"tags":28,"category":34,"related_skills":35},[29,30,31,32,33],"Research","Search","Fallback","Curl","APIs","web",[36,37,38],"blocked-page-recovery","grounded-citations","search-rule-engineering",[40,41,42],"windows","linux","macos","main","a3f3199bb87ec3c91248f68a39d88527e1847ae9","skills\u002F.archive\u002Fterminal-web-research","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content","https:\u002F\u002Fgithub.com\u002Fchaorenex1","https:\u002F\u002Fblog.aduib.com","A programmer whose only hobby in life is coding","2026-10-20 00:34:32",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add chaorenex1\u002Fhermes-home-content --skill terminal-web-research",{"tool":57,"command":58},"bunx","bunx skills add chaorenex1\u002Fhermes-home-content --skill terminal-web-research",{"tool":60,"command":61},"pnpm","pnpm dlx skills add chaorenex1\u002Fhermes-home-content --skill terminal-web-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Fterminal-web-research\u002FSKILL.md",true,[],[66,73,79,86,93,100],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7F8GF32YD5MBQW2TGSRH1YP","web-retrieval-resilience","Web tools fail or search rules break: repair or fall back.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-retrieval-resilience\u002FSKILL.md",[],[],{"skillNo":74,"name":36,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7F8FP46QESQMCZ1KBT3TW3R","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7F8ER6VXHBNVRQBZS7X08SE","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7F8E4BQJ38KVQVM3MT20PYV","unreal-world-builder","开放世界与环境专家——精通 UE5 World Partition、Landscape、程序化植被、HLOD 和大规模关卡流式加载，打造无缝开放世界体验","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-world-builder\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7F8D747SQW2FTP7GBSX38BR","unreal-technical-artist","Unreal Engine 视觉管线专家——精通材质编辑器、Niagara 特效、程序化内容生成和 UE5 项目的美术到引擎管线","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-technical-artist\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7F8CKHYJVZVBTN0321J88T2","unreal-systems-engineer","性能与混合架构专家——精通 C++\u002FBlueprint 边界、Nanite 几何体、Lumen GI 和 Gameplay Ability System，面向 AAA 级 Unreal Engine 项目","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-systems-engineer\u002FSKILL.md",[],[]]