How do I install the Forge Prediction skill?

Run npx skillmds@latest add forgeyclap/forge-prediction-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Forge Prediction safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Forge Prediction?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Forge Prediction free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Forge Prediction?

ForgeyClap (@forgeyclap) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Forge Prediction by forgeyclap — Agent Skill

Name: Forge Prediction
Author: ForgeyClap

Forge Prediction

Forge playbook for prediction, sports-data, and analysis systems (incl. Telegram tip delivery). Use when building forecasting, sports betting analysis, odds/value models, or statistical prediction with confidence labels — keywords: prediction, forecast, sports, betting, odds, value bet, model, backtest, statistics, confidence, Telegram tips, bot. Enforces uncertainty labels, backtesting, and NO automatic real-money betting.

ForgeyClap Updated Sep 22, 2026

File contents

Forge playbook — Prediction / sports-data

Hard rules

Never claim certainty. Every output carries a confidence/risk label.
No automatic real-money betting / no auto-stake code path.
Backtest before trusting any model; show sample size.
Verify data-source quality; track all assumptions.
Telegram token in env only; one message format, tested.

Team (conditional)

Lead: mle-reviewer + planner. Specialists: mle-reviewer, python-reviewer, silent-failure-hunter (data gaps look like clean zeros), database-reviewer (data store).

Skills / commands / MCP

systematic-debugging, /test-coverage. For delivery, defer to forge-n8n or a Telegram layer (Telegram bots fold in here).

Fan-out & flow

L3. Parallel: data ingestion ∥ model/stat logic ∥ delivery formatting. Serial: ingest → backtest → value/odds calc → uncertainty labeling → delivery.

Domain gates

Data sources + quality verified; statistical logic reviewed; backtesting done; odds/value checked; confidence/risk labels on every output; assumptions documented; data freshness check.

Ship-readiness (unique)

Backtest results shown with sample size; every output labeled with confidence/risk; assumptions + data-quality notes attached; no auto-bet path; Telegram message format tested. The ship-readiness prediction + Telegram checklists are advisory; optionally run codex-reviewer (Codex) on important code — not a blocker.

Frequently asked questions