{"slug":"tavily","title":"tavily","summary":"AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-08-23T09:00:38.744291Z","repo":{"url":"https://github.com/KCNyu/clawock","stars":15,"forks":0,"license":"MIT","updatedAt":"2026-09-25T07:36:11Z"},"bodyHtml":"<hr>\n<h2>name: tavily\ndescription: AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.\nhomepage: <a href=\"https://tavily.com\">https://tavily.com</a>\nmetadata: {\"clawdbot\":{\"emoji\":\"\uD83D\uDD0D\",\"requires\":{\"bins\":[\"node\"],\"env\":[\"TAVILY_API_KEY\"]},\"primaryEnv\":\"TAVILY_API_KEY\"}}</h2>\n<h1>Tavily Search</h1>\n<p>AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.</p>\n<h2>Search</h2>\n<pre><code>node {baseDir}/scripts/search.mjs \"query\" --bucket research\nnode {baseDir}/scripts/search.mjs \"query\" -n 10 --bucket research\nnode {baseDir}/scripts/search.mjs \"query\" --deep --bucket research\nnode {baseDir}/scripts/search.mjs \"query\" --topic news --bucket research\n</code></pre>\n<h2>Options</h2>\n<ul>\n<li><code>-n &lt;count&gt;</code>: Number of results (default: 5, max: 20)</li>\n<li><code>--deep</code>: Use advanced search for deeper research (slower, more comprehensive)</li>\n<li><code>--topic &lt;topic&gt;</code>: Search topic - <code>general</code> (default) or <code>news</code></li>\n<li><code>--days &lt;n&gt;</code>: For news topic, limit to last n days</li>\n<li><code>--bucket &lt;name&gt;</code>: <strong>Which monthly budget bucket to charge</strong> — <code>brief</code> / <code>report</code> / <code>intraday</code> / <code>research</code> / <code>extract</code> / <code>default</code>. Ad-hoc/manual research uses <code>--bucket research</code>. <strong>Omitting it charges the small <code>default</code> bucket (60/mo)</strong>, which is exhausted quickly on purpose.</li>\n</ul>\n<h2>Budget (免费档 1000 credits/月, 全局共享)</h2>\n<p>basic 搜索 1 credit，<code>--deep</code> 2，extract 1/5 URL。硬护栏在 <code>lib/ledger.mjs</code>（本地月度账本，reservation 式扣费，超限 <strong>exit 0</strong> 优雅降级返回 \"unavailable\" — <strong>别当报错</strong>，退回内置搜索）。账本在仓库外 <code>/root/.openclaw/tavily-credit-ledger.json</code>；查真实账单：<code>curl -H \"Authorization: Bearer $TAVILY_API_KEY\" https://api.tavily.com/usage</code>（注意有延迟，不能当实时闸）。</p>\n<h2>Extract content from URL</h2>\n<pre><code>node {baseDir}/scripts/extract.mjs \"https://example.com/article\" --bucket extract\n</code></pre>\n<p><code>--bucket</code> works the same as for search (charges that monthly bucket; omit → <code>default</code>). extract costs 1 credit per 5 URLs.</p>\n<p>Notes:</p>\n<ul>\n<li>Needs <code>TAVILY_API_KEY</code> from <a href=\"https://tavily.com\">https://tavily.com</a></li>\n<li>Tavily is optimized for AI - returns clean, relevant snippets</li>\n<li>Use <code>--deep</code> for complex research questions</li>\n<li>Use <code>--topic news</code> for current events</li>\n</ul>\n","files":[{"path":"lib/ledger.mjs","sizeBytes":14491,"isText":false},{"path":"lib/ledger.test.mjs","sizeBytes":5082,"isText":false},{"path":"_meta.json","sizeBytes":132,"isText":true},{"path":"scripts/extract.mjs","sizeBytes":2809,"isText":false},{"path":"scripts/search.mjs","sizeBytes":5435,"isText":false},{"path":"scripts/search.test.fetchmock.mjs","sizeBytes":1083,"isText":false},{"path":"scripts/search.test.mjs","sizeBytes":2936,"isText":false},{"path":"SKILL.md","sizeBytes":2188,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"notes-only","suspicious":0,"notes":2,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-08-23T09:06:48.340108Z","sha256":"5C5AEBBEFC4E851B53880A4F92F00DE7C487B78FBD5C54603CE790CF197B85AA","sizeBytes":15243},"review":null,"source":{"repositoryUrl":"https://github.com/KCNyu/clawock","path":"skills/tavily-search","license":"MIT","commit":"d504fce9bd4bf8b44a0239a21f94978319394c5e","subtreeSha":"7CD2CF49C0D4FD7464500B713925CC4CC28EBA8FB180388B5C4FBAADDD62D8B4","lastSyncedAt":"2026-09-25T07:38:16.512244Z"},"reviewedAt":"2026-08-23T09:21:25.169298Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/KCNyu/clawock/tree/master/skills/tavily-search"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install kcnyu-clawock@llmmart"},{"target":"git","command":"git clone https://github.com/KCNyu/clawock.git"}]}