From muggle
Unified Muggle AI workflow entry point. Use when user types muggle do or asks for autonomous implementation to PR.
How this skill is triggered — by the user, by Claude, or both
Slash command
/muggle:muggle-doThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Muggle Do is the command for the Muggle AI development workflow.
Muggle Do is the command for the Muggle AI development workflow.
It runs a battle-tested autonomous dev cycle: requirements -> impact analysis -> validate code -> coding -> unit tests -> E2E acceptance tests -> open PRs.
For maintenance tasks, use the dedicated skills:
/muggle:muggle-status/muggle:muggle-repair/muggle:muggle-upgradeTreat $ARGUMENTS as the user command:
help / menu / ? -> show menu and session selector.Use .muggle-do/sessions/<slug>/ with these files:
state.mdrequirements.mditerations/<NNN>.mdresult.mdOn each stage transition, update state.md and append stage output to the active iteration file.
Use the supporting files in the ../do/ directory as stage-specific instructions:
[E2E FAILING].npx claudepluginhub multiplex-ai/muggle-ai-works --plugin muggleaiGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.