ワンクリックで
sp-feasibility-study
Study the feasibility and viability of a proposed feature or architectural change.
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
Study the feasibility and viability of a proposed feature or architectural change.
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
| name | sp-feasibility-study |
| description | Study the feasibility and viability of a proposed feature or architectural change. |
| mode | agent |
| tools | ["codebase","githubRepo","terminalLastCommand"] |
| arguments | [{"name":"feature_description","description":"The plain English description of the feature or architectural change to study.","required":true},{"name":"issue_number","description":"The number of the GitHub issue to link the feasibility study to (optional).","required":true}] |
Study the feasibility and viability of the following proposed feature or architectural change:
$FEATURE_DESCRIPTION
Thoroughly research the feature description and explore the codebase to understand the context:
- Sync / offline patterns →
wiki/offline-first-architecture.md- UI components / Horizon design →
wiki/horizon-narrative-design-language.md- Reusable services or components →
wiki/core-services-catalog.md(relevant section only)- Data mapping →
wiki/data-mapping-strategy-and-architecture.md
If the feature touches state or persistent data:
wiki/offline-first-architecture.md for patterns.BigDecimal rather than Double or Float to prevent precision loss.If the feature touches the UI:
wiki/horizon-narrative-design-language.md if applicable.:core:design-system can be reused, or if new components are required.Assess potential issues:
add_issue_comment.Address and resolve existing review comments on a GitHub pull request.
Fetch, analyze, and resolve SonarQube quality gate failures, code smells, bugs, and coverage gaps.
Turn an idea, problem description, or bug report into a well-formed GitHub issue and create it on GitHub once approved.
Request follow-up work on a specific issue (e.g. bug fixes, additional requirements, visual regression, or debugging) in a new or existing conversation without prior context.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Plan a GitHub issue by investigating context and creating a detailed implementation plan. Present it to the user, and post it to the issue as a comment upon approval. No code changes.