Use Tinyfish
TinyFish is a CLI for web scraping and automation that escalates gracefully from simple fetches to full browser control. Start with search to find URLs, use fetch for clean content extraction from static pages, jump to agent when you need natural language instructions to click buttons or fill forms, and only reach for the CDP browser session when you need raw programmatic control. The agent command is the standout here: you pass a URL and a plain English goal like "extract all products as JSON" and it handles the interaction. Works well for bot-protected sites. The tool selection ladder (search → fetch → agent → browser) is smart, keeps costs down, and the parallel execution model means you fire off separate commands for independent sites rather than cramming everything into one brittle goal.
- skills.sh installs
- 3.5K
- GitHub stars
- 2.3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add tinyfish-io/tinyfish-cookbook --skill use-tinyfish --agent claude-codeInstalls into .claude/skills of the current project.
Files
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:
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/tinyfish-io/tinyfish-cookbook
- Categories
- Documentation, Data Science & ML, Automation & Workflows
- First seen
- Jun 3, 2026
Recommended
More Documentation
crawltavily-ai/skillsCrawl any website and save pages as local markdown files. Use when you need to download documentation, knowledge bases, or web content for offline access or ana3.5Kskills.sh installs
ce-commit-push-preveryinc/compound-engineering-pluginCommit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.3.5Kskills.sh installs
neat-freakkkkkhazix/khazix-skillsKnowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code a3.5Kskills.sh installs
fullstack-devminimax-ai/skillsFull-stack backend architecture and frontend-backend integration guide. TRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding ba3.5Kskills.sh installs
good-strategy-bad-strategywondelai/skillsFormulate and audit real strategy using Richard Rumelt's "Good Strategy Bad Strategy": an honest diagnosis, a guiding policy, and coherent action instead of goa3.5Kskills.sh installs
scholar-evaluationaffaan-m/eccStructured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedb3.4Kskills.sh installs