Walmart Sales Data Deep Analyzer
Analyze Walmart sales data to uncover trends between store sales and unemployment, generating insightful visualizations and a polished HTML report.
The skill only processes user-supplied CSV files, generating local plots and an HTML report, with no external network requests or sensitive data operations. No malicious or overreaching behavior is evident. However, the skill documentation requires invoking tools like execute_skill_script_file and html_interpreter, without clarifying user confirmation mechanisms or permission isolation. The provenance and security of dependencies are not addressed. Thus, not the highest score, with deductions for unclear permission control, confirmation, and dependency security.
Static review cannot execute the scripts, so the claimed analysis functionality is unverified. The scripts implicitly assume column names like 'Unemployment' and 'Weekly_Sales'; mismatched data will cause errors without clear feedback. Dependencies like pandas and seaborn are common but no installation instructions are provided. No test suite exists for the skill, and there is no error handling for abnormal input. Low score due to lack of execution verification and weak failure feedback.
The skill's goal is clear: analyze Walmart sales vs. unemployment and generate charts and HTML report. However, boundaries are unclear, e.g., data size limits or specific format requirements. Trigger conditions are based on user-provided CSV, without stating non-fit scenarios (e.g., other retail data). Environment fit: scripts include Chinese font support (font_setup.py), but core function relies on local libraries; no mention of mainland China network accessibility. Medium-low score due to unclear boundaries and triggers.
Documentation is well-structured with features, usage, workflow, and script/template listing. But version, changelog, and maintenance responsibility are missing. Dependency installation (e.g., pandas, seaborn) is not listed, causing setup friction. Known limitations, such as reliance on column names, are not disclosed. License is MIT at repository level but not per-skill. Medium score due to incomplete versioning and dependency notes.
The skill claims to produce a deep-analysis HTML report. The analysis includes correlation, regression, etc., and output seems directly usable, but unverified via execution. Placeholders in the report must be filled dynamically; otherwise they show 'NA', affecting completeness. Compared to manual analysis, the value is automation, but marginal benefit is not quantified. Low score due to no execution evidence and output completeness reliant on manual filling.
Evidence is limited to the skill's self-description and script source. No independent test results or third-party verification. The repository has tests for other modules, but not for this skill. No CI workflow covers this skill. Very low score due to lack of verifiable evidence.
- The skill has not been executed and verified; the report generation may not work or produce expected outputs.
- The skill assumes CSV columns named 'Unemployment' and 'Weekly_Sales'; mismatched data will cause raw errors without friendly messages.
- Placeholders in the report template, if not dynamically filled, render as 'NA', degrading report quality.
- Dependencies like pandas and seaborn are not documented with installation guidance; they may be missing in the target environment.
- Known limitations and scope boundaries are not declared, which may lead to misuse on incompatible datasets.
What does this skill do, and when should you use it?
This skill is tailored for data analysts and business decision-makers, providing a complete workflow for Walmart sales analysis from a CSV file. It automatically generates a correlation heatmap, a sales-vs-unemployment scatter plot with regression line, time-series trends for specific stores, and a store average comparison. All charts are bundled into a responsive HTML report with detailed interpretations and business recommendations. It is ideal for quickly exploring the relationship between sales and macroeconomic factors.
Reads a CSV file containing Store, Date, Weekly_Sales, and Unemployment columns; runs Python scripts to produce five visualizations: correlation heatmap, sales vs unemployment scatter, time-series trend, store average comparison, and an integrated HTML report. It uses the execute_skill_script_file tool to run generate_html_report.py and the html_interpreter tool to render the final report. The report requires dynamic placeholder filling and language localization.
- Retail analysts who want to quickly measure the correlation between store sales and local unemployment rates.
- Regional operations managers comparing average store performance against local unemployment to inform regional strategies.
- Data scientists validating hypotheses about consumption resilience under economic pressure using scatter plots with regression lines.
- Management teams needing an automated, visually rich quarterly sales analysis report with narrative insights.
- BI teams tracking sales and unemployment trends for selected stores to identify seasonal or macro patterns.
What are this skill's strengths and limitations?
- One-click generation of a comprehensive HTML report with multiple charts and analyses
- Automatically creates correlation heatmaps, scatter plots, time-series, and comparisons
- Includes business-ready interpretation and recommendations
- Supports multilingual output and responsive design
- Specific to Walmart sales data and the Store/Weekly_Sales schema
- Depends on DB-GPT environment and specific tools; not standalone
- No evidence of support for data sources other than CSV
- Report quality hinges on manual placeholder filling; missing placeholders render as 'NA'
How do you install this skill?
This skill is part of the DB-GPT repository and requires DB-GPT to be installed. Installation options include a one-line installer (curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash) or pip install dbgpt-app. The skill is located at skills/walmart-sales-analyzer. Refer to DB-GPT documentation (docs.dbgpt.cn) for detailed steps.
How do you use this skill?
In a DB-GPT session, the user provides a Walmart sales CSV file with at least Store, Date, Weekly_Sales, and Unemployment columns. The skill runs generate_html_report.py to create charts and a base report, then calls html_interpreter with a populated data payload to render the report. All placeholders must be filled dynamically and translated to the user's language. Ensure the CSV format is correct.