A professional business intelligence skill for retail environments that provides automated period-over-period sales analysis and performance diagnostics.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install retail-sales-performance-analysis
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 retail-sales-performance-analysis 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 Retail Sales Performance Analysis?
The Retail Sales Performance Analysis skill is a robust data diagnostic tool designed for the modern retail landscape. It enables Openclaw Skills users to perform deep-dive comparisons between current and previous sales periods, identifying the root causes of performance fluctuations. Whether you are managing a single storefront or a fleet of sales clerks, this skill translates raw transactional data into actionable business intelligence.
By quantifying attribution—such as whether a revenue drop is due to lower foot traffic (order count) or reduced basket sizes (average transaction value)—it removes guesswork from retail management. It serves as a digital consultant that not only flags anomalies like sharp sales declines or low attachment rates but also provides structured recommendations to improve operational efficiency.
Retail Sales Performance Analysis Use Cases
- Comprehensive store-level performance tracking including revenue, order volume, and average ticket size.
- Individual sales clerk performance audits featuring ranking and capability radar charts.
- Comparative analysis between multiple store locations or staff members to identify top performers.
- Root cause attribution to determine if sales changes are driven by order volume or customer spend.
- Risk identification and proactive alerting for significant performance drops or low attachment ratios.
How Retail Sales Performance Analysis Works
- The user triggers the skill by asking about sales performance or specific performance dips.
- The skill extracts parameters such as the subject (store or clerk ID), the desired time window, and comparison metrics.
- It fetches real-time data from the BI dashboard API, mapping raw fields to standardized financial and efficiency metrics.
- It calculates period-over-period changes and applies mathematical attribution formulas to identify primary drivers.
- The system runs the results through an anomaly detection engine to identify risks (e.g., discounts exceeding thresholds).
- A structured JSON report is generated, containing core metrics, findings, and strategic recommendations.
Retail Sales Performance Analysis Setup
To integrate this skill into your environment, ensure you have the necessary API client configuration. You can initialize the analysis via a Python script or through the CLI as part of your Openclaw Skills workflow.
# Ensure your API client is configured in the workspace
cp .env.example .env
# The skill relies on the following path for data fetching:
# ~/.openclaw/workspace-front-door/
Retail Sales Performance Analysis Data Schema & Taxonomy
The skill organizes data into structured categories to ensure clarity across different retail dimensions:
Metric Taxonomy
| Category | Metrics Included | Purpose |
|---|---|---|
| Financial | net_money, effective_order_count | Core revenue and transaction volume tracking. |
| Efficiency | customer_unit_price, attach_qty_ratio, piece_price | Measuring sales quality and upselling capability. |
| Membership | new_customer_count, new_member_purchase_share | Tracking loyalty growth and new customer contribution. |
Output Structure
- subject_info: Details of the store or clerk being analyzed.
- core_metrics: Comparative data (current vs. previous) with trend indicators.
- attribution: Mathematical breakdown of growth drivers.
- findings: A list of facts, anomalies, and hypotheses with confidence levels.
Retail Sales Performance Analysis Advanced Features
- Multi-subject comparison support for benchmarking stores against regional averages.
- Automated attribution modeling to distinguish between transaction-driven and price-driven growth.
- Heuristic-based anomaly detection with severity levels (High/Medium) for proactive risk management.
- High-fidelity integration with existing retail BI dashboards via standardized API mapping.
- Detailed diagnostic output including evidence-based hypotheses for performance fluctuations.
SKILL.md
Loading
Related Openclaw Skills
Frontend Code Review
An automated auditing tool that reviews frontend code for architecture, type safety, security, and accessibility, generating detailed Markdown reports.
Complex Task Executor
A structured methodology for AI agents to plan, execute, and review complex operations while automatically persisting lessons learned into long-term memory.
Weekly Report Skill
An automated reporting agent that aggregates data and publishes structured weekly reports directly to Enterprise WeChat (WeCom) documents.
Financial Product Workflow
A comprehensive AI-driven framework for financial product managers to navigate the entire product lifecycle from strategic planning to automated operation.
Kandy
Kandy is a powerful real-time communications platform integration that enables AI agents to manage voice, video, and messaging workflows seamlessly.
Obsidian Vault Context
A skill that transforms an Obsidian vault into a shared, persistent workspace where AI agents and users collaborate via markdown files rather than just chat.
Featured*
