trend_analysis

Convert dated observations into structured trend objects with deterministic JSON output.

1|Updated Mar 23, 2026

Search Tags:#evidence #time-series #direction #data-validation #trend-analysis #json-output

Ready to run

npx skills add https://github.com/hellonish/singularity --skill trend-analysis-hellonish

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: trend_analysis
Source: https://github.com/hellonish/singularity/tree/main/SKILLS/tier2_analysis/trend_analysis
Command: npx skills add https://github.com/hellonish/singularity --skill trend-analysis-hellonish

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Trend Analysis identifies directional trends across time-series data by converting scattered dated observations into structured, action-ready trend intelligence.

Core Features & Use Cases

Ingests dated data and validates temporal markers.
Orders data chronologically to create clean time series.
Infers primary direction: increasing, decreasing, stable, volatile, or cyclical.
Extracts concrete, date-anchored evidence for each identified trend.
Calibrates a confidence level based on data quality and coverage.

Quick Start

Provide a dated dataset to the Trend Analysis skill and request a JSON of identified trends.

Frequently Asked Questions about trend_analysis

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

FAQPage Schema

How do I identify directional trends in time-series data?▼

Identifying directional trends in time-series data requires ordering dated observations chronologically to infer patterns like increasing, decreasing, stable, volatile, or cyclical. The process extracts date-anchored evidence to validate each identified trend.

What is the best way to quantify time-based trends from dated reports?▼

Quantifying time-based trends from dated reports involves converting scattered observations into structured trend objects. This method calibrates confidence levels based on data quality and validates temporal markers to ensure accurate directional inference.

How do I extract date-anchored evidence for a trend analysis?▼

Extracting date-anchored evidence for trend analysis requires validating temporal markers within your dataset and ordering data chronologically. This creates a clean time series that reveals explicit evidence supporting increasing, decreasing, or cyclical directions.

Does time-series trend analysis work with JSON output?▼

Yes, time-series trend analysis can produce a deterministic JSON output. It converts dated observations into structured trend objects, ensuring identified directions and supporting evidence are formatted as action-ready intelligence.

Can I use trend analysis for volatile or cyclical data patterns?▼

Yes, you can use trend analysis for volatile or cyclical data patterns. The process infers primary directions beyond simple linear trends, identifying stable, volatile, and cyclical behaviors while calibrating confidence levels based on data coverage.