ワンクリックで
speckit-discovery-feasibility
Produce an evidence-backed feasibility study for a product or technical direction.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Produce an evidence-backed feasibility study for a product or technical direction.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Wrap core analysis with behavior-first vertical consistency checks.
Apply approved architecture refactors by updating plan and task artifacts directly.
Perform a framework-agnostic architecture review validating implementation against spec.md, plan.md, tasks.md, and the governance and architecture constitutions.
Perform an architecture-aware verification gate validating implementation against spec.md, plan.md, tasks.md, and the Architecture Constitution.
Run a single architecture workflow that prefers memory-first context and can incorporate security review when available.
Run implementation with memory context, then review the produced implementation against security and architecture constraints.
| name | speckit-discovery-feasibility |
| description | Produce an evidence-backed feasibility study for a product or technical direction. |
| compatibility | Requires spec-kit project structure with .specify/ directory |
| metadata | {"author":"github-spec-kit","source":"discovery:commands/feasibility.md"} |
$ARGUMENTS
The user may provide:
Infer optional fields only from repository context and conversation, and label all inferred values as assumptions. If the primary goal or feasibility question is absent, ask one concise clarifying question.
1. Normalize the input into: - Goal. - Context. - Known constraints. - Assumptions. - Success criteria.Assess feasibility across these dimensions:
Classify the evidence state:
Create or update feasibility.md by rendering .specify/templates/feasibility.md. Prefer the active feature directory when it exists. Otherwise create it under discovery/<short-name>/feasibility.md. This command is responsible for input normalization, evidence classification, decision classification, and template field population only.
Set Decision to exactly one of:
feasiblefeasible-with-risksnot-feasibleinconclusiveRecommend follow-up discovery work only when it directly reduces decision risk, such as /speckit.discovery.poc, /speckit.discovery.techselect, or /speckit.discovery.codebase.