How this skill is triggered — by the user, by Claude, or both
Slash command
/development:buildThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute the implementation plan for "$ARGUMENTS" task-by-task, following test-driven development discipline.
Execute the implementation plan for "$ARGUMENTS" task-by-task, following test-driven development discipline.
Read .metapowers/development/$ARGUMENTS/01-plan.md. If this file does not exist, tell the user:
No plan exists for "$ARGUMENTS". Run
/development:plan $ARGUMENTSfirst, or use--skip-checksto bypass.
If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/development/$ARGUMENTS/skip-log.md.
For each task in the plan:
Write the failing test first:
Implement the minimal code to pass:
Verify:
Commit:
Log progress — after each task, append to the execution log:
Write the artifact to .metapowers/development/$ARGUMENTS/02-build.md
The execution log written to .metapowers/development/$ARGUMENTS/02-build.md. Present a summary to the user highlighting:
npx claudepluginhub bromso/metapowers --plugin developmentGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.