メニュー
Read-only workflow-artifact explanation for advanced coding models. Use when the user wants a spec, plan, tasks, lane state, cognition state, or compatibility artifact explained from what is actually on disk.
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
Advanced post-Review human acceptance workflow. Use after fresh approved Review closeout to restore a contextless human's understanding, guide one real product step at a time, and persist an explicit pass, fail, or blocked verdict.
Read-only cross-artifact consistency analysis for advanced coding models. Use when tasks exist and the specification, plan, and task boundaries need an independent gate before or during execution.
Existing-spec repair workflow for advanced coding models. Use when a specification package has planning-critical ambiguity, weak acceptance, contradictions, or new constraints that should be absorbed without recreating the feature.
Focused pre-plan feasibility research for advanced coding models. Use when a planning-ready specification still lacks a credible implementation chain, external evidence, or a disposable proof.
Lean design-system workflow for advanced coding models. Use for a new product UI, redesign, rebrand, shared visual language, or an audit/update of the root DESIGN.md contract.
Resumable product and technical discussion for advanced coding models. Use when a rough idea needs durable decisions and options before formal specification.
| name | spx-explain |
| description | Read-only workflow-artifact explanation for advanced coding models. Use when the user wants a spec, plan, tasks, lane state, cognition state, or compatibility artifact explained from what is actually on disk. |
Read references/project-learning.md and apply its consume-only policy.
Read references/project-cognition.md, using cognition intent ask, and
references/artifact-explanation.md.
Resolve the active feature or lane before guessing. Read the most downstream artifact that directly answers the question, then only its authoritative inputs and the live repository evidence needed to distinguish intent from current behavior.
Explain the artifact's purpose, important decisions, relationships, consequences, readiness, and unresolved gaps in the user's language. Prefer a compact mental model over section-by-section paraphrase. Clearly separate what the artifact claims, what the repository currently proves, and what remains unknown.
Remain read-only. Do not rewrite artifacts, update lifecycle state, create reports, or advance to another workflow unless the user separately requests action. On a follow-up about the same artifact, reuse still-current evidence and read only the delta.
