ワンクリックで
spec-app-review
Review an application-type spec for completeness against UI rendering requirements and golden-path structure.
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
Review an application-type spec for completeness against UI rendering requirements and golden-path structure.
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
Define a normative Functional Requirement (FR) with complete specification.
Generate required integration test cases to cover integrations with all external services. These tests will be run in a real env with real services.
Define a normative Non-Functional Requirement (NFR) or quality constraint.
Write an authoritative Stakeholder Requirement (StR).
Write or format an ISO-compatible User Story (US) artifact.
Review requirements for quality, consistency, and completeness.
| name | spec-app-review |
| description | Review an application-type spec for completeness against UI rendering requirements and golden-path structure. |
Validate a component_type: application spec against what the spec-editor-ui actually renders and the structural requirements from specify.
spec/spec.md in the target repo. Verify component_type: application in frontmatter.The spec-editor-ui ApplicationDetailPage has 7 tabs. Each tab extracts data from specific sections/artifacts:
| Tab | Data Source |
|---|---|
| Overview | Purpose, In Scope, Out of Scope, Operational Boundaries, API Endpoints, Components (catalog), Standards (frontmatter) |
| Architecture | Mermaid diagrams (tagged logical/deployment), FR diagrams, Aggregated Objects (catalog) |
| Integration | Artifacts with tags: [integration] in frontmatter |
| Security | Trust Boundaries table, artifacts with tags: [security], Standards |
| Requirements | StR/US/FR/NFR tables parsed from spec.md |
| Decisions | ADR artifacts (artifact_type: ADR) or inline ADR sections |
| Spec | Raw markdown rendering |
These are the exact parser behaviors that determine whether content renders:
parseDelegations() only recognizes (Handled by X) or (Delegated to X) patterns. Other parentheticals won't extract delegation targets.parseBulletList() default pattern is bold-description (**Title** — Description). Plain bullets fall back to title-only.parseBulletList({ pattern: 'bold-colon' }) requires **Name**: detail format.parseTable() on section "Trust Boundaries" — expects 3 columns: Role, Capabilities, Restrictions.findDiagramByTag() matches %% @type: logical and %% @type: deployment comments in mermaid blocks.tags: [integration] in YAML frontmatter (case-insensitive).tags: [security] in YAML frontmatter.Use a known well-formed application spec in your org as a comparison reference when reviewing.