ワンクリックで
heuristic-eval
Run a structured heuristic evaluation against a prototype or feature, severity-rank the issues, and recommend fixes.
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
Run a structured heuristic evaluation against a prototype or feature, severity-rank the issues, and recommend fixes.
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
Run a cognitive walkthrough and create Beads issues from the findings. Converts walkthrough breakdowns (Q1-Q4 failures) into trackable Beads tasks with priorities and dependencies.
Build a conceptual model and create Beads issues from the findings. Converts ambiguities, overloaded concepts, and unclear states into trackable Beads tasks with priorities and dependencies.
Audit cross-screen consistency and create Beads issues from the findings. Converts consistency breaks and invariant violations into trackable Beads tasks with priorities and dependencies.
Audit failure paths and create Beads issues from the findings. Converts unhandled failure states, missing empty states, and broken recovery paths into trackable Beads tasks with priorities and dependencies.
Run a heuristic evaluation and create Beads issues from the findings. Converts Nielsen heuristic violations into trackable Beads tasks with priorities and dependencies.
Review information architecture and create Beads issues from the findings. Converts orphan screens, mislabeled navigation, and grouping problems into trackable Beads tasks with priorities and dependencies.
| name | heuristic-eval |
| description | Run a structured heuristic evaluation against a prototype or feature, severity-rank the issues, and recommend fixes. |
| disable-model-invocation | true |
Run a heuristic evaluation for this scope:
$ARGUMENTS
Use ultrathink. Use the actual prototype, repo, screenshots, routes, components, and docs. Do not give generic advice. Anchor every issue to a real part of the system where possible.
Write docs/hci/heuristic-evaluation.md unless the user asked for another path.
Create the directory if it does not exist.
| ID | Heuristic | Screen/flow/component | Evidence | Why it matters | Severity (0-4) | Recommendation |
End with:
Note: if a consistency-audit artifact exists for this scope, reference it for heuristic #4 rather than re-auditing consistency in full. Apply heuristic #4 only to findings not already covered.