A specialized data analysis skill for performing complex period-over-period, year-over-year, and trend variance analysis on historical datasets.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install historical-data-compare-claw
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 historical-data-compare-claw 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 Historical Data Comparison Claw?
The Historical Data Comparison skill is a powerful analytical component within the Openclaw Skills ecosystem designed to bridge the gap between raw data and actionable business insights. By automating the comparison of multi-period datasets from Excel, CSV, or database exports, it enables users to instantly understand performance shifts across various time dimensions.
This skill goes beyond simple subtraction by providing deep-dive root cause analysis and multi-dimensional breakdown. It empowers decision-makers with a clear view of variables, highlighting whether changes are seasonal noise, emerging trends, or critical anomalies requiring immediate intervention.
Historical Data Comparison Claw Use Cases
- Performing Year-over-Year (YoY) and Month-over-Month (MoM) growth analysis.
- Investigating sudden drops in revenue or KPI fluctuations through dimension breakdown.
- Generating automated monthly or quarterly performance reports for executive stakeholders.
- Tracking rolling trends to eliminate short-term noise and identify long-term trajectories.
- Analyzing contribution margins across regions, categories, or channels to identify growth drivers.
How Historical Data Comparison Claw Works
- Data Ingestion: The skill reads provided files (Excel, CSV) and validates the structure, identifying date columns and metric columns.
- Quality Check: It automatically scans for missing values, outliers, and duplicates to ensure data integrity before calculation.
- Baseline Selection: Determines the comparison baseline based on user intent (e.g., current period vs. previous period or same period last year).
- Automated Calculation: Executes variance and percentage change calculations using standardized logic or custom Python scripts.
- Insight Synthesis: Evaluates the magnitude of change against thresholds to classify results as Alerts, Observations, or Normal trends.
- Report Generation: Produces a structured report featuring conclusions, overview tables, and actionable recommendations.
Historical Data Comparison Claw Setup
To utilize this skill within the Openclaw Skills framework, ensure your environment has Python 3 installed. You can execute standardized comparisons using the included utility script:
python3 scripts/compare.py <file_path> --date-col <column_name> --metric-cols <col1,col2> --compare <yoy|mom|both> --period <monthly|quarterly|daily>
Historical Data Comparison Claw Data Schema & Taxonomy
The skill expects structured time-series data and organizes outputs according to the following taxonomy:
| Field Type | Description | Example |
|---|---|---|
| Date Dimension | Time-based columns used for grouping | Date, Month, Quarter, Year |
| Metric Columns | Quantitative values for comparison | Revenue, Volume, Ratio |
| Comparison Result | Calculated variance fields | Growth Rate, Absolute Change |
| Attribution | Dimensional breakdown data | Region, Category, Channel |
Historical Data Comparison Claw Advanced Features
- Multi-agent support for feeding analysis results into downstream communication or visualization agents.
- Automated root cause attribution to identify which specific sub-dimension contributed most to a total variance.
- Flexible output formatting optimized for Instant Messaging (Emoji/Lists) or Formal Documentation (Markdown Tables/PDF).
- Customizable variance thresholds (e.g., ±10%) to trigger specific executive alerts.
- Support for rolling averages (3/6/12 periods) to smooth out volatile data sets.
SKILL.md
Loading
Related Openclaw Skills
Orche: Multi-Phase Orchestration Engine
Orche is a robust multi-agent orchestration framework that systematically executes complex tasks through a rigorous Query-Plan-Execute-Verify lifecycle.
Evolution Predictor
An advanced analytical engine that predicts optimal next steps for AI agent growth by identifying stagnation levels and innovation gaps.
Baidu Drive Storage Skill
A powerful AI agent skill for seamless file management, transfer, and sharing on Baidu Drive directly through natural language commands.
AI Workflow Optimizer
An expert system designed to 10x your productivity by optimizing prompts, designing automated workflows, and selecting the right AI tools.
Security Audit Assistant
A lightweight, zero-install security scanner that audits server configurations and provides executable one-click fixes.
AnnounceKit
An automated integration for AnnounceKit that enables AI agents to manage product changelogs, roadmap issues, and user feedback.
Featured*
