| name | super-duper-fixer-tdd-cat |
| description | Expert review to debug, then fix using brainstorm+TDD workflow in an isolated git worktree with subagent-driven-development |
| argument-hint | [<scope|directive>] |
| user-invocable | true |
/expert-review debug, then fix using /super-tdd with /duper with /cat
Operator override: explore-only / do-not-fix-yet
If ARGUMENTS explicitly ban implementation ("explore only", "do not fix yet",
"brainstorm approaches, don't edit code", "leave implementation for a follow-up
session", or similar), skip /expert-review (nothing to debug
pre-implementation), skip /tdd (no test target yet), skip /duper (no worktree
needed when no edits are planned), and skip /cat (no implementation to
parallelize). Invoke /brainstorming directly, produce the design artifact
(visual-aid, prose, or spec-stub per operator preference), and STOP at the
design gate. Do not dispatch to TDD/implementation subagents. The brainstorm
artifact IS the deliverable; follow-up session picks up via /checkpoint-resume.
Rationalization counter: "the skill says to run the full flow, so I should" —
no, an explicit operator directive to explore-only overrides the default flow.
The full-flow sequence assumes an implementable target; exploration tasks have
no such target yet.
TDD execution mode (third axis)
This composition inherits the A/B TDD execution-mode axis defined in
skills/tdd-cat/SKILL.md: Mode A (split-phase: one RED/GREEN/REFACTOR
phase per subagent) vs Mode B (micro-cycle: full /tdd loop inside each
subagent). Ask it as the third question in /cat's combined pre-dispatch
AskUserQuestion — never default it silently.
