HeatStackTurn AI momentum into engineering evidence.

Start with a transparent live Skill index, understand the mechanism, then use an eighteen-module Forge curriculum to build something you can test, recover, and explain.

Inspect today’s ranking Continue the project

No account · no remote code sandbox · progress and evidence stay in your browser

Reading the latest live ranking…

Today's signal

Today’s four questions

AI Curiosity Lab

The selection is stable for the day—no refresh roulette.

01Why does the same Skill behave differently across coding agents?02Why is an agent more than running a model in a loop?03Why are multi-agent systems often slower, costlier, and harder to debug?04Why can a model still “forget” earlier text despite having a context window?

Ask why

Why does the same Skill behave differently across coding agents?

A 15-minute explanation

The same Skill behaves differently across coding agents because each agent defines, loads, executes, and integrates Skills differently. A Skill is not a portable program but is deeply coupled to the host agent's architecture, tooling, and model capabilities.

Why this matters in a real product

In real-world engineering, this difference means teams cannot directly deploy a Skill written for one platform to another. For example, an 'auto code review' Skill built for OpenAI Codex, relying on its dynamic scheduling and strict sandbox, must be adapted for explicit invocation in Claude Code, with error handling redesigned for its command-line interaction style. Conversely, a Skill leveraging Claude Code's long context window with many examples may fail in Codex due to RAG chunking. Teams must maintain multiple Skill versions and establish per-platform testing pipelines to ensure reliability and safety in AI-assisted development. Product managers planning AI coding assistant features must clarify Skill boundaries and avoid promising cross-platform consistency to users.

Ask why

Choose a path

Today, do only one step

The same Forge core grows through three scenario packs.

01Software deliveryInspect a repository, plan a safe change, edit files, run tests, and retain rollback evidence.02Office researchRead documents and tables, retrieve evidence, and produce a cited decision brief.03Content & musicOrganize ideas, track metadata, and turn a release plan into reusable content assets.

18 MODULES