메뉴
Expert review to debug, then fix using brainstorming workflow with subagent-driven-development
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Render a single "where am I, what have I done, what's next" survey HTML page composing anchor cascade + tesseract shelf + git state + CHECKPOINT.md + TaskList. Read-only by design.
Subagent-driven development as the explicit combination of /subagent-driven-development (sequential, review-gated execution) and /dispatching-parallel-agents (independent fan-out). Opens with one combined pre-dispatch question to set the execution mode and the edit-approval mode, then dispatches accordingly.
Use when a discrete task boundary is crossed in multi-step work — step completion, subagent dispatch return, Skill-tool invocation return, /proceed gate passed, test-run completion, or file-write to a durable artifact (spec, plan, SKILL.md). Do not substitute an in-place TaskList update for this skill.
Use when resuming paused work, starting a session where a CHECKPOINT.md exists, or when the user says "continue from checkpoint", "resume", or "pick up where we left off"
Use when pausing work that will be resumed later, when switching contexts, or when the user asks to save a checkpoint. Creates a CHECKPOINT.md that captures full resumption context.
retry last operation attempted before the user interrupted the process, or otherwise continue last attempted tool use
| name | super-fixer-cat |
| description | Expert review to debug, then fix using brainstorming workflow with subagent-driven-development |
| argument-hint | [<scope|directive>] |
| user-invocable | true |
/expert-review debug the below, then fix using /super with /cat
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) 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.
