hx-crawl4ai-advisor

Guides Crawl4AI planning, installation, and validation on HX-17 under HX governance rules.

Updated Sep 9, 2026
One-click install
npx skills add https://github.com/HX-Infratstructure/HX-Eco-System --skill hx-crawl4ai-advisor-hx-infratstructure
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hx-crawl4ai-advisor
Source: https://github.com/HX-Infratstructure/HX-Eco-System/tree/main/skills/crawl4ai/hx-crawl4ai-advisor
Command: npx skills add https://github.com/HX-Infratstructure/HX-Eco-System --skill hx-crawl4ai-advisor-hx-infratstructure

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Applying Crawl4AI inside the HX Eco-System risks importing vendor Docker quickstarts, community skill defaults, or cloud/LLM assumptions that conflict with the native-Linux HX-17 architecture. This Skill enforces a strict authority order so Crawl4AI work stays aligned with HX control documents, smoke-test authority, and owner decisions. ## Core Features & Use Cases - Authority-ordered guidance: Resolves conflicts between HX architecture, official Crawl4AI 0.9.x documentation, the official assistant skill, and the Brett Davies community skill using explicit ACCEPT/ADAPT/REFERENCE_ONLY/REJECT_FOR_HX/OWNER_DECISION_REQUIRED labels. - Deployment boundary enforcement: Keeps Crawl4AI, its browser runtime, and the MCP companion native on HX-17 (192.168.50.217) with systemd, rejecting container, cloud, proxy, and credential defaults. - Validation alignment: Anchors work to the D3 deterministic raw-HTML smoke proof and D4 MCP companion proof without redefining PASS criteria. - Use Case: When planning the HX-17 Crawl4AI installation, use this Skill to decide which upstream features (CLI, AsyncWebCrawler, CSS/XPath extraction, MCP bridge) are acceptable and which require an owner decision before any runbook is written. ## Quick Start Ask the agent to plan the HX-17 Crawl4AI native installation and flag any upstream defaults that require an owner decision.

Frequently Asked Questions about hx-crawl4ai-advisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan a Crawl4AI installation on HX-17?▼

Follow the Skill's authority order: HX control documents first, then live HX-17 evidence, then official Crawl4AI 0.9.x docs. Package version, Python environment, browser runtime, and service layout remain owner decisions until the HX-17 runbook pins them.

Can Crawl4AI be deployed with Docker in the HX Eco-System?▼

No. HX mandates native Linux deployment with systemd for long-running services, so Docker, Podman, and Kubernetes quickstarts are labeled REJECT_FOR_HX. The official Docker-based MCP bridge is treated as source evidence only, not an approved deployment.

Is the brettdavies crawl4ai-skill compatible with current Crawl4AI?▼

It is classified as community expert reference verified against Crawl4AI 0.8.9, while the current official release is 0.9.3. Its CLI, extraction, and batch patterns may be adapted only after checking current official behavior, and its LLM defaults are rejected.

Does Crawl4AI BASE validation require an external LLM?▼

No. The D3 smoke proof uses deterministic inline raw: HTML processed by AsyncWebCrawler with no external website, LLM, proxy, or API key. LLM extraction requires an owner-approved HX model/provider path before use.

What does the HX-17 Crawl4AI smoke test verify?▼

D3 runs crawl4ai-doctor, processes deterministic inline HTML via AsyncWebCrawler with raw: input, and verifies exact Markdown tokens. D4 then independently validates the assigned Crawl4AI MCP companion after an accepted D3 PASS.

When should Crawl4AI work stop and escalate to the owner?▼

Stop when package versions, browser runtime, service layout, MCP implementation, network policy, credentials, or LLM providers are unpinned, or when a recommendation introduces containers, cloud services, or persistent sessions without owner authority.