Prophet Forecasting

Prophet Forecasting is a Data skill for Claude Code, published by asgard-ai-platform in skills.

228 stars28 forkson asgard-ai-platform/skillsAdded 2026/09/03Repository updated 2026/06/06

ai-agentanthropicclaudeclaude-agent-skillsclaude-codecoding-agentknowledge-basemcpmethodologyopen-sourceprompt-engineeringskillstaiwan

Install in seconds

Install Prophet Forecasting

Copy Prophet Forecasting into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/asgard-ai-platform/skills/tree/main/algo-forecast-prophet ~/.claude/skills/algo-forecast-prophet

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/asgard-ai-platform/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: algo-forecast-prophet/SKILL.md in asgard-ai-platform/skills
Installs to: ~/.claude/skills/algo-forecast-prophet
Collection: One of 25 skills cataloged from this repository
Category: Data — 710 skills

What Prophet Forecasting does

Prophet Forecasting builds business time series forecasts with trend, seasonality, holidays, and changepoints. Use it for daily or weekly metrics when you need a quick forecast with built-in handling for missing data and validation.

Prophet Forecasting is cataloged under Data on DirSkills. Prophet Forecasting comes from a repository tagged ai-agent, anthropic, claude, claude-agent-skills and claude-code.

Documentation

README

Excerpt

Prophet Forecasting

Overview

Prophet (Meta) decomposes time series into trend + seasonality + holidays + error. Uses an additive (or multiplicative) model fitted with Stan. Handles missing data, outliers, and holiday effects natively. Designed for business time series at daily/weekly granularity.

When to Use

Trigger conditions:

Forecasting business metrics (sales, traffic, engagement) at daily/weekly frequency
Data with strong seasonal patterns and known holiday effects
Need quick, reasonable forecasts without deep time series expertise

When NOT to use:

For high-frequency data (sub-hourly) — Prophet is designed for daily+
When you need causal/explanatory models (Prophet is descriptive)
For very short time series (< 2 seasonal cycles)

Algorithm

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Prophet Forecasting

What else does asgard-ai-platform publish alongside Prophet Forecasting?
Prophet Forecasting is one of 25 skills that DirSkills catalogs from asgard-ai-platform/skills, the repository it ships in. Its siblings there include ARIMA Time Series Model, Ad Bidding Strategies and Ad Budget Allocation. Each one is a separate skill with its own page in this directory, installs the same way Prophet Forecasting does, and is maintained by asgard-ai-platform in that same repository. The rest of the collection is listed on the asgard-ai-platform/skills page.
How does Prophet Forecasting compare to other Data skills?
Prophet Forecasting ranks #649 by stars among the 710 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Prophet Forecasting against them. Open each page to compare what they document and how they install.