Menu
Suggest candidate approaches to a problem — research and lay out options, but never decide.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Design a target architecture for a new system — module boundaries, dependency rules, seams, and build order — from its requirements. Reports a blueprint; changes nothing.
Analyze an existing codebase's architecture and produce a sequenced refactoring plan — assess module boundaries, dependency structure, and layering, then lay out ordered, risk-tagged steps. Language-agnostic. Reports a plan; changes nothing.
Turn a goal or another command's output into an ordered task roadmap.
Find the root cause of a failure with the scientific method — reproduce, isolate, fix, then prove it.
Interview the user relentlessly about a plan or design until reaching shared understanding.
Run an extremely strict maintainability + single-source-of-truth review of code changes — abstraction quality, file sprawl, spaghetti-condition growth, and duplicate/competing implementations. Reports findings by default; `--fix` applies the mechanical, unambiguous ones — structural/code-judo restructurings rest on judgment and stay reported.
| name | ds-explore |
| description | Suggest candidate approaches to a problem — research and lay out options, but never decide. |
| disable-model-invocation | true |
When invoked, help the operator think through how to solve a problem by surfacing a few viable approaches with their trade-offs. You suggest; you do not decide and you do not implement. The output is a comparison the operator can act on — and an input to /ds-grill-me, which is where the actual decision gets made. (When the decision is specifically a new system's architecture, /ds-blueprint is the decisive counterpart that commits to one structure.)
--web — opt-in: do bounded web research (a few high-signal sources, each cited). Off by default; the command works from the project context and your own knowledge..project/PROJECT.md, .project/PLAN.md, .project/DECISIONS.md if present — honor recorded decisions and constraints, don't re-litigate them.--web: research, bounded — a handful of sources, cite each, no open-ended crawl.--web: work from the context and your knowledge. If that is too thin to produce good options, say so and suggest re-running with --web — do not pad with guesses./ds-grill-me will walk through..project/EXPLORE.md if .project/ exists, else EXPLORE.md in a fresh mktemp -d; return the path.PLAN.md, PROJECT.md, or DECISIONS.md. This command only reads and writes its own artifact.DECISIONS.md already settled..project/EXPLORE.md is a scratchpad — overwrite it. It is not part of the durable plan/state.The candidate approaches and open questions inline, plus the artifact path. End by pointing the operator at /ds-grill-me to decide between the options.