A sophisticated multi-agent AI orchestration skill that provides deep product research, price comparisons, and service verification for the Saudi Arabian market.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install personal-shopper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install personal-shopper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Jack Al-Alam (جاك العلم)?
Jack Al-Alam is a professional-grade personal shopper designed for Openclaw Skills. It utilizes a complex multi-agent architecture to navigate the specific retail landscape of Saudi Arabia, providing users with data-driven recommendations in Arabic. Unlike standard search agents, it acts as an orchestrator that spawns specialized sub-agents—such as Advocates, Skeptics, and Bargain Hunters—to ensure every recommendation is vetted for quality, price, and local availability.
The skill focuses on delivering high-value insights by checking major KSA retailers like amazon.sa, noon.com, and jarir.com while simultaneously verifying local services in Riyadh. It removes the guesswork from shopping by calculating effective prices after coupons, cashback, and installments, presenting the results in a mobile-friendly HTML report.
Jack Al-Alam (جاك العلم) Use Cases
- Comparing high-end electronics like laptops and monitors across all major Saudi retailers.
- Finding the best deals on daily essentials and groceries using local delivery apps like Nana or Danube.
- Identifying the highest-rated local services in Riyadh, such as salons, repair shops, or restaurants, with verified reviews.
- Uncovering hidden gems and underdog brands that offer better value than mainstream market leaders.
- Planning major purchases by analyzing price trends and upcoming sales events like Ramadan or White Friday.
How Jack Al-Alam (جاك العلم) Works
- The Router analyzes the user's request to classify the category (electronics, clothing, services, etc.) and selects the most efficient execution path.
- specialized sub-agents are spawned; for standard products, an Advocate seeks the best quality while a Skeptic finds non-mainstream alternatives.
- A Bargain Hunter agent performs sequential checks for active coupons on Almowafir, cashback via STC Pay or Al Rajhi, and installment options through Tabby or Tamara.
- All candidate data is passed to the Court agent, which applies a strict weighted scoring framework (0-100) based on value, quality signals, and source trust.
- The Renderer agent builds a final, polished RTL HTML report in Arabic, embedding screenshots of the product pages and providing a clear final recommendation.
Jack Al-Alam (جاك العلم) Setup
To integrate this skill into your Openclaw Skills deployment, ensure the agent has directory permissions for generating reports and capturing visual evidence.
# Create the required directory structure for reports and evidence
mkdir -p shopping-reports/screenshots
# Ensure the following domains are in your network allowlist:
# *.amazon.sa, *.noon.com, *.jarir.com, *.extra.com, lite.duckduckgo.com
The skill requires no external credentials as it relies on public web fetching and specialized search patterns to navigate Saudi eCommerce sites.
Jack Al-Alam (جاك العلم) Data Schema & Taxonomy
The skill organizes its output into structured artifacts and localized metadata for maximum clarity:
| Data Type | Format | Storage Location |
|---|---|---|
| Shopping Reports | HTML (Arabic, RTL) | shopping-reports/{date}-{slug}.html |
| Product Evidence | PNG Screenshots | shopping-reports/screenshots/ |
| Scoring Data | JSON | Internal state for Court validation |
Each product recommendation includes a name, SAR price, source URL, store name, and a 'kill-doubt' reasoning string that explains the specific trade-offs of the choice.
Jack Al-Alam (جاك العلم) Advanced Features
- Multi-Agent Orchestration: Uses a parallel execution model to reduce latency while performing deep research across multiple store tiers.
- Mainstream Brand Filtering: A unique Skeptic agent mode that explicitly ignores dominant brands to find high-performance alternatives.
- Automated Verification: Includes a spot-check mechanism where the Court agent re-fetches random source URLs to ensure data accuracy and prevent hallucinations.
- Visual Trust System: Automatically captures and base64-embeds screenshots of product pages into the final report to provide immediate visual verification.
- Context Compaction: Optimized for Openclaw Skills to manage high-token workflows (up to 250K tokens) by intelligently pruning intermediate research data.
SKILL.md
Loading
Related Openclaw Skills
Adobe Master Automator
A cross-platform automation bridge for the Adobe Creative Cloud suite using ExtendScript and native OS scripting hosts.
SUIROLL
A provably fair giveaway tool for AI agents on the Sui blockchain using VRF and Moltbook authentication.
KarmaBank
A decentralized credit system that enables AI agents to secure interest-free USDC loans based on their Moltbook reputation and karma scores.
KarmaBank
KarmaBank enables AI agents to secure interest-free USDC loans based on their Moltbook reputation and network activity.
Prompt Architect
An expert-level prompt engineering skill that converts raw concepts, images, and documents into structured, framework-based LLM instructions.
Visual Prompt Engine
A data-driven engine that creates high-quality, non-repetitive AI image prompts based on real-world design trends and structured visual vocabularies.
METADATA
Featured*
