forecast-scaffold

v0.4.26

General-purpose forecasting scaffold: turn questions into calibrated, tracked probability forecasts. Question hygiene, reference-class-first research, ensembled estimates, and a record -> resolve -> Brier learning loop.

Claude Code2 Skills

By Edison YiLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes: Claude Code
Parsed components: 2 skill or MCP entries
Source updated: Aug 28, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install plugin

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install forecast-scaffold@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/edisonymy/forecast-scaffold

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

forecast-scaffold/

├── .claude-plugin/plugin.json
├── skills/calibrate/SKILL.md
└── skills/forecast/SKILL.md

Included Skills2

calibrateskills/calibrate/SKILL.md

Close the forecasting learning loop — resolve recorded forecasts whose date has passed, score calibration (Brier score, over/under-confidence direction), and turn misses into lessons. Use when asked "how are my forecasts doing", "resolve my predictions", "what's my calibration/Brier score", at the start of a review session, or on a schedule. Reads and writes the same journal the forecast skill records to.

forecastskills/forecast/SKILL.md

Produce a calibrated probability forecast for any question about the future or any uncertain claim — "will X happen", "what are the odds", "how likely is it" — and record it to a scorable journal. Also use to operationalize a vague question into a resolvable one (exact resolution criterion + date), or to break a big question into fast-resolving sub-questions. Effort auto-scales (auto/low/medium/high). Pairs with the calibrate skill, which resolves and Brier-scores what this records.

Plugin manifests1

.claude-plugin/plugin.json

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "forecast-scaffold",
  "displayName": "Forecast Scaffold",
  "description": "General-purpose forecasting scaffold: turn questions into calibrated, tracked probability forecasts. Question hygiene, reference-class-first research, ensembled estimates, and a record -> resolve -> Brier learning loop.",
  "version": "0.4.26",
  "author": {
    "name": "Edison Yi",
    "url": "https://github.com/edisonymy"
  },
  "homepage": "https://github.com/edisonymy/forecast-scaffold",
  "repository": "https://github.com/edisonymy/forecast-scaffold",
  "license": "MIT",
  "keywords": [
    "forecasting",
    "superforecasting",
    "calibration",
    "brier-score",
    "prediction",
    "metaculus",
    "probability"
  ]
}