{
  "markdown": "# Tavily Agent Skills\n\nWeb search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.\n\n## Installation\n\n### Recommended: guided CLI setup\n\nInstall the [Tavily CLI](https://github.com/tavily-ai/tavily-cli):\n\n```bash\ncurl -fsSL https://cli.tavily.com/install.sh | bash\n```\n\nOn a fresh interactive desktop install, the installer starts `tvly init`\nautomatically. Otherwise run it after installation:\n\n```bash\ntvly init\n\n# Prefer to open the sign-in link yourself\ntvly init --no-browser\n```\n\n`tvly init` authenticates, detects Claude Code, Codex, and Cursor, installs\nthese skills, and verifies a live search. It reuses an existing credential and\nis safe to rerun. Skills installed this way are pinned to the CLI release, so\nrun `tvly update` before `tvly init` when refreshing them.\n\n`tvly search` and `tvly extract` also work without authentication, subject to\na keyless rate-limit cap. Use `tvly init --skip-auth` to keep keyless mode while\ninstalling the skills. `map`, `crawl`, and `research` require authentication.\n\nBrowser-based OAuth is the preferred interactive sign-in method. `--no-browser`\nsimply prints the sign-in link instead of opening it automatically; the flow\nstill returns to a localhost callback on the machine running `tvly`. In remote\nsessions, make sure that callback is reachable (SSH may require port\nforwarding). For unattended agents or CI, authenticate beforehand or provide\n`TAVILY_API_KEY` securely so the process does not wait for human input.\n\n### Manual skill installation\n\nFor other agents, or when you only want to install the skills:\n\n```bash\nnpx skills add https://github.com/tavily-ai/skills\n```\n\nInstall the CLI separately if needed:\n\n```bash\nuv tool install tavily-cli   # or: pip install tavily-cli\n```\n\nThen use `tvly init --skip-skills` for guided authentication and verification,\nor `tvly login` when you only need to authenticate.\n\n### Keep the CLI current\n\n```bash\ntvly update --check\ntvly update\n```\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| **[tavily-search](skills/tavily-search/SKILL.md)** | Search the web with LLM-optimized results. Supports domain filtering, time ranges, and multiple search depths. |\n| **[tavily-extract](skills/tavily-extract/SKILL.md)** | Extract clean markdown/text content from specific URLs. Handles JS-rendered pages. |\n| **[tavily-crawl](skills/tavily-crawl/SKILL.md)** | Crawl websites and extract content from multiple pages. Save as local markdown files. |\n| **[tavily-map](skills/tavily-map/SKILL.md)** | Discover all URLs on a website without extracting content. Faster than crawling. |\n| **[tavily-research](skills/tavily-research/SKILL.md)** | Comprehensive AI-powered research with citations. Multi-source synthesis in 30-120s. |\n| **[tavily-dynamic-search](skills/tavily-dynamic-search/SKILL.md)** | Filter and deduplicate large search or extraction results without flooding agent context. |\n| **[tavily-cli](skills/tavily-cli/SKILL.md)** | Overview skill with workflow guide, install/auth instructions. |\n| **[tavily-best-practices](skills/tavily-best-practices/SKILL.md)** | Reference docs for building production-ready Tavily integrations. |\n\n## Workflow\n\nStart simple, escalate when needed:\n\n1. **Search** — Find pages on a topic (`tvly search \"query\" --json`)\n2. **Extract** — Get content from a specific URL (`tvly extract \"https://...\" --json`)\n3. **Map** — Discover URLs on a site (`tvly map \"https://...\" --json`)\n4. **Crawl** — Bulk extract from a site section (`tvly crawl \"https://...\" --output-dir ./docs/`)\n5. **Research** — Deep multi-source analysis (`tvly research \"topic\" --model pro`)\n",
  "bytes": 3665,
  "sha": "21808dc4b1deee7ee1cc5f002c36b60786a62fefb841cfc4093bd93b8361a43a",
  "repo_slug": "tavily-ai/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_tavily_ai_skills_tavily_crawl_597a6a29/readme"
}