{
  "markdown": "# XCrawl Skills\n\nReusable XCrawl skill definitions for multi-agent runtimes, focused on API-first web data workflows.\nCanonical repository: `https://github.com/xcrawl-api/xcrawl-skills`\n\nEnglish | [中文](README.zh-CN.md)\n\n## What Is XCrawl\n\nXCrawl is a web data infrastructure product for search, scraping, URL mapping, and site crawling.\nThis repository provides production-oriented skill definitions that help agents call XCrawl APIs consistently.\n\n## What This Repository Provides\n\n- Ready-to-use skills for common XCrawl workflows\n- API-oriented instructions with request/response parameter documentation\n- cURL and Node examples suitable for runtime execution\n- A consistent contract for multi-agent orchestration\n\n## Skill Catalog\n\n- `xcrawl`: Default XCrawl entry skill for direct lookup and single-URL extraction\n- `xcrawl-scrape`: Single-URL extraction and structured data workflows\n- `xcrawl-map`: Site URL discovery and scope planning workflows\n- `xcrawl-crawl`: Bulk site crawling and async result handling workflows\n- `xcrawl-search`: Query-based discovery with location/language controls\n\n## Quick Start\n\n### 1. Prerequisites\n\n- An XCrawl API key\n- Register at `https://dash.xcrawl.com/` and activate the free `1000` credits plan\n- Runtime binaries: `curl` and `node`\n- Access to this repository\n\n### 2. Configure Local API Key\n\nCreate local config file:\n\nPath: `~/.xcrawl/config.json`\n\n```json\n{\n  \"XCRAWL_API_KEY\": \"<your_api_key>\"\n}\n```\n\nSkills in this repo are designed to read `XCRAWL_API_KEY` from this local file.\n\n### 3. Choose a Skill\n\nOpen one of:\n\n- `skills/xcrawl/SKILL.md`\n- `skills/xcrawl-scrape/SKILL.md`\n- `skills/xcrawl-map/SKILL.md`\n- `skills/xcrawl-crawl/SKILL.md`\n- `skills/xcrawl-search/SKILL.md`\n\nEach skill includes:\n\n- Applicable scenarios\n- Request parameters\n- Response parameters\n- cURL / Node examples\n\n### 4. Run Requests\n\nUse the examples in each `SKILL.md` directly, then adapt request payloads for your business scenario.\n\n## Example User Intents\n\n- \"Scrape this page in sync mode and return markdown + links.\"\n- \"Map only `/docs/` URLs under this domain with a limit of 2000.\"\n- \"Start a bounded crawl (depth 2, limit 100) and poll until completed.\"\n- \"Search in US English and return top 20 results for this query.\"\n\n## Cross-Agent Contract\n\nEach skill can be executed through a runtime adapter layer.\n\n- Input normalization: `goal`, `inputs`, `constraints`, `credentials_ref`, `runtime_context`\n- Output normalization: `status`, `request_payload`, `raw_response` or async pair, `task_ids`, `error`\n\nDefault behavior is raw passthrough: return upstream API response bodies as-is.\n\n## Shared XCrawl Conventions\n\n- Base URL: `https://run.xcrawl.com`\n- Local config file: `~/.xcrawl/config.json`\n- API key field in local config: `XCRAWL_API_KEY`\n- Auth header: `Authorization: Bearer <XCRAWL_API_KEY>`\n- Main endpoints:\n  - `POST /v1/scrape` and `GET /v1/scrape/{scrape_id}`\n  - `POST /v1/map`\n  - `POST /v1/crawl` and `GET /v1/crawl/{crawl_id}`\n  - `POST /v1/search`\n\n## Support\n\n- [XCrawl Homepage](https://www.xcrawl.com/)\n- [XCrawl Documentation](https://docs.xcrawl.com/)\n",
  "bytes": 3120,
  "sha": "5a698663e9628811f07d7cf21b4b6cf88d05dd973579021bca28c12296e52ab7",
  "repo_slug": "xcrawl-api/xcrawl-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_xcrawl_api_xcrawl_skills_xcrawl_map_b5e4c4ee/readme"
}