Use TinyFish for web search, fetching URLs, reading pages, current information, source-backed answers, research, docs, pricing/product pages, extraction, scraping, and browser automation. Use whenever the user asks to search, find, look up, research, compare, get information from the web, summarize

TinyFish CLI You have access to the TinyFish CLI ( tinyfish ) — a suite of web tools you can call from the terminal. If not installed: npm install g @tiny fish/cli If not authenticated: tinyfish auth login source openclaw or set TINYFISH API KEY env var. When This Skill Should Trigger Use TinyFish whenever a request depends on live web information or page content. Do not wait for the user to say "TinyFish" or "scrape". Strong triggers include: Search or discovery: search, find, look up, research, compare, latest, current, news, docs, pricing, product details, best options. URL/page reading: fetch, read, summarize, extract from this page, inspect this URL, get the content, pull links or metadata. Source backed answers: answer using web sources, verify a fact, check whether something changed, gather information from the web. Website work: interact with a site, click through pages, fill forms, log in, collect structured data, handle bot protected pages. Default to the lightest tool that can answer: No URL and the user needs web information: search , then fetch the best result(s) if more detail is needed. URL provided and only content is needed: fetch . Page interaction or dynamic extraction is needed: agent . Raw CDP/Playwright style control is needed: browser . Picking the Right Tool TinyFish has four tools. Start with the lightest one that can do the job and escalate only when needed. Tool When to use Speed Cost search You need to find URLs, current facts, docs, pricing, product details, or a quick source backed answer Fastest Lowest fetch You have URLs and need clean page content, summaries, article text, docs, product pages, links, or metadata Fast Low agent You need to interact with a page — click, fill forms, navigate, extract structured data from dynamic sites Slower Higher browser Agent isn't enough — you need raw programmatic browser control via CDP Slowest Highest Common Patterns Research: search → fetch Search for a topic, then fetch the best results to read their full content. Deep extraction: search → agent Search to find the right site, then use agent to interact with it and extract structured data. Escalation: fetch → agent Try fetch first. If the page is dynamic/JS heavy and fetch returns empty or incomplete content, escalate to agent. Full control: agent → browser If agent can't handle a complex multi step workflow, spin up a raw browser session and automate it yourself via CDP. Commands tinyfish search query Web search. Returns ranked results with titles, URLs, and snippets. Returns 10 results by default Use location and language for geo targeted results Default output is JSON; pretty for human readable tinyfish fetch content get Fetch clean, extracted content from one or more URLs. Strips ads, nav, boilerplate — returns just the content. Accepts multiple URLs in a single call — they are fetched in parallel server side format markdown (default) — clean readable text format json — structured document tree links — include all extracted links from the page image links — include extracted image URLs Response includes: url , final url , title , language , author , published date , text , latency ms tinyfish agent run Run a browser automation using a natural language goal. The agent opens a real browser, navigates, clicks, fills forms, and extracts data. Flag Purpose url <url Target URL (bare hostnames get https:// auto prepended) sync Wait for full result without streaming steps async Submit and return immediately pretty Human readable output Output: Default streams data: {...} SSE lines. The final result is the event where type == "COMPLETE" and status == "COMPLETED" — the extracted data is in the resultJson field. Read the raw output directly; no script side parsing is needed. Always specify the JSON structure you want in the goal: Parallel extraction — when hitting multiple independent sites, make separate calls. Do NOT combine into one goal. Good — parallel calls (run simultaneously): Bad — single combined call: Managing runs: Batch operations — submit many runs from a CSV file ( url,goal columns): tinyfish browser session create Spin up a remote browser instance. Returns a CDP WebSocket URL for programmatic control. url optionally navigates to a page after creation Returns session id , cdp url (WebSocket), and base url Use the cdp url with Playwright, Puppeteer, or any CDP client General Notes Match the user's language : Respond in whatever language the user writes in. All commands support pretty for human readable output. Default is JSON. Use debug on the root command or set TINYFISH DEBUG=1 to log HTTP requests to stderr.

use-tinyfish