ai-agent

Prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
20,350 stars4,636 forksPythonUpdated 8/8/2026100% free · open source
What it does

Prophet is a tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

When to use it
  • You have a business metric with daily, weekly, or yearly seasonal patterns
  • Your growth is linear or non-linear and you want to forecast future trends
  • You need to handle multiple seasons and holidays in your forecasting model
Ready-to-paste prompt
m = Prophet(); m.fit(pd.DataFrame({'ds': ['2022-01-01', '2022-01-02'], 'y': [10, 20]})); future = m.make_future_dataframe(periods=30); forecast = m.predict(future)
Heads up: Make sure your date column is in a format that can be parsed by Prophet, such as 'YYYY-MM-DD', and is named 'ds' as this is the default expected column name
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/prophet && curl -fsSL https://workflowstacks.com/api/skills/prophet/claude-skill -o ~/.claude/skills/prophet/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Prophet works
Codeflow
Free to inspect

Prophet is a medium Python project (~8.1k lines across 31 code files, plus 13 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size
Medium codebase
~8.1k lines · 31 code files · ~1 h to skim
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Docker
No API keys detected
Python 63%R 35%Stan 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    examples/example_air_passengers.csv
    A worked example — copy this to get going
What's in each folder
docs/Documentation215 files
examples/Examples you can copy9 files
R/Folder103 files
python/Folder29 files
python_shim/Folder15 files
notebooks/Research & notebooks11 files
.github/CI / automation (GitHub Actions)2 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
facebook
Language
Python
Category
ai-agent
Published
11/16/2016

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.