skills.rest
radarist
radaristOFFICIAL
Explore all skills by this author →
WebsiteGitHub

trend-analysis

Validates trend claims and projects time series with logistic fits and Trend Impact Analysis.

4|1|Updated Jul 30, 2026
Search Tags:#time series#forecasting#trend analysis#foresight#s-curve#logistic fit#trend impact analysis
One-click install
npx skills add https://github.com/radarist/structured-analytic-skills --skill trend-analysis-radarist
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trend-analysis
Source: https://github.com/radarist/structured-analytic-skills/tree/main/skills/trend-analysis
Command: npx skills add https://github.com/radarist/structured-analytic-skills --skill trend-analysis-radarist

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Trend claims like "X is taking over" are often based on single sources, spikes, or hype. This Skill turns a trend claim into an evidence-checked statement, quantifies its rate and curvature from a time series, and projects it with explicit assumptions instead of silent extrapolation. ## Core Features & Use Cases - Trend validation: Checks fad markers (single source, spike shape, no mechanism) against at least two independent series before any projection, returning a VALIDATED, UNCERTAIN, or FAD MARKERS verdict. - Quantification and projection: Computes rate, curvature, and S-curve position, then projects via naive extrapolation, OLS linear, exponential, logistic fit, or Gordon's Trend Impact Analysis with probability-weighted events. - Deterministic companion tool: scripts/trend.py (stdlib only) performs all arithmetic — CAGR, doubling time, spike detection, curve fitting, TIA adjustment — with --demo and --selftest modes. - Use Case: Given five years of EV market-share data, validate the trend, fit naive and logistic curves, adjust the 2030 baseline for events like subsidy rollback, and ship a trend card with signposts and confidence. ## Quick Start Use the trend-analysis skill to validate whether heat-pump adoption in Europe is a real trend and project it to 2030 with an assumption sheet.

Frequently Asked Questions about trend-analysis

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

FAQPage Schema
How do I validate whether a trend is real or a fad?▼

Restate the claim as a falsifiable statement with quantity, population, and horizon, then gather at least two independent time series spanning about five years. Check fad markers — single source, spike shape, no mechanism — and name the structural driver before issuing a VALIDATED, UNCERTAIN, or FAD MARKERS verdict.

How do I extrapolate a time series to 2030 with Python?▼

Run scripts/trend.py with the project command on a period,value CSV or inline series, choosing naive, linear, exponential, or logistic models. It reports per-model projections with a ±2·RMSE band, horizon multiple, and optional Trend Impact Analysis event adjustments.

What is Trend Impact Analysis and when should I use it?▼

Trend Impact Analysis is Theodore Gordon's method of adjusting a surprise-free baseline projection by probability-weighted future events. Use it when identifiable events could bend the curve; each event needs a probability and an impact, and the adjustment arithmetic must be shown.

When should I not use trend extrapolation?▼

Do not extrapolate reflexive systems like elections or asset prices, series with fewer than about five observations, or unvalidated trends. Publication and citation curves belong to research-momentum analysis, and hype-cycle placement is a separate method.

Why is a fitted logistic ceiling unreliable on early data?▼

When observations cover only the lower half of the S-curve, the saturation level K is poorly identified and can shift sharply with one more data point, per Meade and Islam 2006. The tool flags this case and recommends fixing the ceiling externally with the --ceiling option.

Related Skills

Explore More Data & Analytics Skills→
ManfronEnricoManfronEnrico

forecasting-time-series-data

Forecast future values from historical time series data using ARIMA, Prophet, or Exponential Smoothing.

Community
Intermediate
lyndonkllyndonkl
142

environmental-scanning-foresight

Analyze PESTLE forces, detect weak signals, and develop future scenarios.

Community
Advanced
ericgandradeericgandrade
65

deep-research

Perform multi-source web research and generate cited reports.

Community
Advanced
risingdreamrisingdream
28

rt-collins

Diagnose organizational strategy failures using Flywheel and Hedgehog Concept questions.

Community
Advanced