← Back to Skills Marketplace
1329
Downloads
0
Stars
9
Active Installs
3
Versions
Install in OpenClaw
/install xcrawl-scrape
Description
Use this skill for XCrawl scrape tasks, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema.
Usage Guidance
This skill is internally consistent with a client for the XCrawl scraping API. Before installing: (1) Confirm you trust xcrawl.com and your API key issuer; (2) Consider storing your API key in a secure secret manager rather than an unencrypted ~/.xcrawl/config.json file; (3) Be cautious with webhook URLs you supply — they will receive scraped content; (4) Review any use of skip_tls_verification or proxies in request options (these lower network security); (5) Remember this skill runs curl/node commands at runtime (so the agent will need those tools available). If any of the above is unacceptable, don't install or ask the publisher for alternative auth/storage methods.
Capability Analysis
Type: OpenClaw Skill
Name: xcrawl-scrape
Version: 1.0.2
The xcrawl-scrape skill is a standard integration for the XCrawl web scraping service (run.xcrawl.com). It uses curl and node to interact with the API, requiring an API key stored in ~/.xcrawl/config.json. The logic is consistent with its stated purpose, and no malicious patterns such as data exfiltration or unauthorized execution were identified.
Capability Assessment
Purpose & Capability
The name/description (XCrawl scraping: single-URL fetch, sync/async, JSON extraction) aligns with the actual instructions which call https://run.xcrawl.com/v1/scrape. The declared tool dependencies (curl or node) and the local config file (~/.xcrawl/config.json) are coherent for an API-key based client.
Instruction Scope
SKILL.md instructs only to read the local config file for XCRAWL_API_KEY, then make HTTP requests to the XCrawl API using curl or node. It does not instruct reading other user files, scanning the system, or transmitting unrelated data. The webhook feature exists as part of the API (user-specified callback URL) — expected for async scrape workflows but a user-controlled sink.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is downloaded or written by an installer. That minimizes install-time risk.
Credentials
No global environment variables or external credentials are requested. The skill requires a single locally stored API key (~/.xcrawl/config.json), which is proportionate to calling a paid scraping API. Note: storing an API key as plaintext in a home directory is sensitive but is a user configuration choice rather than a requirement of the skill.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It does request runtime execution permissions for curl/node (consistent with examples). There is no instruction to modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xcrawl-scrape - After installation, invoke the skill by name or use
/xcrawl-scrape - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
xcrawl-scrape v1.0.2
- Added a note about credits: users need an XCrawl account with activated free credits before running requests.
- Provided registration guidance: users should sign up at https://dash.xcrawl.com/ and activate the free 1000 credits plan.
- No breaking changes to API usage or workflow.
v1.0.1
xcrawl-scrape 1.0.1
- Supports both sync and async scraping modes, with flexible output format selection (markdown, links, json, etc.).
- Requires local API key config at ~/.xcrawl/config.json (no environment variables or global dependencies).
- Only uses curl and node as runtime tools.
- Returns raw upstream API responses, supporting custom extraction via prompt or json_schema.
v1.0.0
Initial release of xcrawl-scrape skill:
- Supports single-page extraction using the Xcrawl Scrape API.
- Allows users to fetch content by URL with selectable formats (markdown, html, links, summary, or screenshot).
- Provides both synchronous (`mode=sync`) and asynchronous (`mode=async`) scrape modes, including status polling by `scrape_id`.
- Enables structured data extraction via flexible prompt or strict `json_schema`.
- Returns upstream API response bodies as-is without summarization, unless requested.
- Offers helper scripts and usage examples for Bash, Python, and Node.
Metadata
Frequently Asked Questions
What is XCrawl Scrape?
Use this skill for XCrawl scrape tasks, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema. It is an AI Agent Skill for Claude Code / OpenClaw, with 1329 downloads so far.
How do I install XCrawl Scrape?
Run "/install xcrawl-scrape" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is XCrawl Scrape free?
Yes, XCrawl Scrape is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does XCrawl Scrape support?
XCrawl Scrape is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created XCrawl Scrape?
It is built and maintained by wykings (@wykings); the current version is v1.0.2.
More Skills