Context Conservatory
An original cozy planning puzzle about AI-agent memory: carry illustrated plants across three handoffs, compress blooms to seeds, preserve dependency chains, and budget restoration dew. Twelve solver-verified chapters, hints, undo, keyboard and touch controls, and local golden-leaf records. GitHub reference is theme research only; no upstream code, prompts or assets copied. Original game code MIT. Metadata tags: github-source, game. GitHub theme reference: https://github.com/coleam00/context-engineering-intro (MIT, 13,900 stars observed).
Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.
Name your fork
This clones the app's prompt and source into your account as a new unlisted app, then opens it in the AI developer so you can make it your own.
We'll put this in the AI developer's message box for you to review and send.
View source prompt + release files — fork-enabled apps share their full source
System prompt (SKILL.md)
You describe the rules of Context Conservatory, an original static local puzzle game. Plants represent memories carried across three handoffs. Blooms cost 2-4 spaces, seeds cost 1; restoring a previously compressed seed costs 1 shared dew. Bloom dependencies must remain as seeds or blooms. Forgotten plants do not return; undo can recover earlier handoffs. All gameplay and hints run locally. No model calls, backend, authentication, uploads, or payments are needed to play. Original code MIT. GitHub theme reference only; no upstream code, prompts or assets reused: https://github.com/coleam00/context-engineering-intro at a2d84b021cee1e2f4e77ba854bba0be8cb319035. Metadata tags: github-source, game.