Stats
Actions
Tags
From superkit
Iterative/brownfield change — re-spec just the affected area so the audit trail stays intact, regenerate plan/tasks, then execute with superpowers. Guards against editing code without updating the spec.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superkit:enhanceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Make a change to existing code without breaking the spec trail. Dependency check first
Make a change to existing code without breaking the spec trail. Dependency check first
(bash "${CLAUDE_PLUGIN_ROOT}/scripts/check-deps.sh").
Scope the change. With the user, identify the affected area and whether it maps to
an existing spec (check /superkit:status) or needs a new one.
Re-spec the area — invoke speckit-specify for just this change (new spec or an
update to the existing one). Register/update it:
registry.sh add <id> "<title>" ... or registry.sh set <id> spec-path <path>;
set-status <id> specified.
Clarify / Plan / Tasks — invoke speckit-clarify, speckit-plan, speckit-tasks,
advancing status each time. Gate: specs/<id>/tasks.md non-empty.
Execute — superpowers:using-git-worktrees → superpowers:test-driven-development
→ superpowers:subagent-driven-development (don't re-plan) → superkit:iterate-to-green
→ superkit:conformance-check → requesting-code-review
→ finishing-a-development-branch. Advance status
executing → in-review → done.
If the user starts editing code directly without a spec update, stop and remind them:
reality diverging from spec.md kills the audit trail. Re-run step 2 for the changed area.
npx claudepluginhub joshuatrobertson/super-kit --plugin superkitGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.