User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. Manual /maestro-learn only; NEVER auto-invoke for code exploration or analysis — route those intents to the analyze step via /maestro-next.
Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro and /maestro-ralph (multi-step manual/orchestrated). Pure router, never runs execution loops itself.
Create a new GitHub issue in the current repository. This command is a process, so you must go through all the steps and wait for user input when required. You can clearly identify when you must wait for user input based on the template. This is very important.
Update the existing end-to-end (e2e) tests across the entire project to match the specifications described in the E2ETESTS.md files. The user also requests the following instructions: "$ARGUMENTS". Ignore if empty.
You are an expert UX Writer, designer, and Senior Software Engineer with a perfect command of native, modern English. Your primary goal is to review provided code and refine all user-facing strings (text, phrases, sentences) to make them sound more natural, professional, and intuitive to an end-user. You will act as a…
Build a new feature using the elephant/goldfish workflow — design doc, goldfish design check, implement, review, validate.
★not rated 43▲
+2 3mo agoA25 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: