How this skill is triggered — by the user, by Claude, or both
Slash command
/research:designThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Diverge on solutions for "$ARGUMENTS". Generate multiple solution concepts, evaluate feasibility, and prioritize the most promising approaches.
Diverge on solutions for "$ARGUMENTS". Generate multiple solution concepts, evaluate feasibility, and prioritize the most promising approaches.
Read .metapowers/research/$ARGUMENTS/01-discover.md and .metapowers/research/$ARGUMENTS/02-define.md.
If 02-define.md does not exist, tell the user:
Phase 2 (Define) has not been completed for "$ARGUMENTS". Run
/research:define $ARGUMENTSfirst, or use--skip-checksto bypass.
If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/research/$ARGUMENTS/skip-log.md.
Read context files:
.metapowers/research/$ARGUMENTS/01-discover.md for research findings.metapowers/research/$ARGUMENTS/02-define.md for problem statement, HMW questions, and success criteriaplugins/research/shared/double-diamond-guide.md for methodology referenceResearch existing solutions:
Generate solution concepts:
Evaluate each concept:
Prioritize and recommend:
Write the artifact to .metapowers/research/$ARGUMENTS/03-design.md with sections:
The solution concepts written to .metapowers/research/$ARGUMENTS/03-design.md. Present a summary to the user highlighting:
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub bromso/metapowers --plugin research