The quick interview that captures a Domain's or major Feature's minimal (go-live) and final vision verbatim into its VISION.md. Use when a node shows VISION MISSING, a registry domain is ratified without a vision, gap analysis lacks a go-live bar, or on /domain-vision-interview <domain>.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Arman, 2026-08-20 (verbatim in /systems/platform/docs-system/VISION.md): "An agent comes to me and does a quick interview, and it's a big picture interview where the agent essentially extracts from me the minimal vision for the particular module and then the final vision. So the minimal vision would be what we have to have before we can go live — because we're not in production yet, and we're being held up by all this stuff. And then what's like the ultimate goal of this thing — and capturing those and documenting them allows for agents to be able to do a much better job of doing gap analysis."
Disambiguation: this is NOT the platform's Vision Interview System
(systems/masterwork/vision-interview/ — a Masterwork Approach, a product feature for users). This is
an internal docs-system skill: a short conversation with Arman about one Domain.
policies/domain-tree.md. One
interview covers ONE node — never a menu of domains in one sitting.grilling skill, kept shallow on purpose. The MINIMAL bar and the
FINAL vision both go in round 1 (both open-ended). No spec-depth branches.VISION.md (or extend it): two sections — Minimal vision (go-live
bar) and Final vision — all verbatim, attributed, dated; inferences marked
(inferred); nothing paraphrased. Update the registry node (vision recorded).VISION MISSING wherever the node carried it (register Notes, handoffs).まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Admin debug system wiring for the floating AdminIndicator's live debug data and Copy Full Context. Use when adding debug visibility to a route or feature, wiring useDebugContext or the debug panel, capturing console errors, or enabling the copy-context workflow for a page.
日本語の概要は準備中です。原文の説明を表示しています。
Compact two-icon Copy / Copy-for-AI controls (components/agent-copy). Use when adding copy buttons to a row, card, list, or record; merging duplicate Copy/JSON/AI controls; continuing the copy rollout; or writing a Copy-for-AI payload. NOT for markdown content actions (use rich-document-actions).
日本語の概要は準備中です。原文の説明を表示しています。
Disclosing a surface's existing fixed AI jobs in the shell's top Agents menu. Use when a page, panel, overlay, or window already runs a mandate behind a button, assist, automatic action, or mode; when the agent-disclosure guard names a file; or during a surface check.
日本語の概要は準備中です。原文の説明を表示しています。
The watch-fix-rerun method for making an existing platform agent or automated process efficient and correct: baseline its ledger, run one unit yourself, fix the class behind every wasted call, rerun, record. Use when asked to improve, optimize, watch, or 'make efficient' an agent, a sandbox session, a sync job, or any recurring automated process.
日本語の概要は準備中です。原文の説明を表示しています。
Redux state for agent execution and firing agent shortcuts. Use when editing features/agents/redux/, building agent UI, creating a conversation, touching assembleRequest or NDJSON stream state, wiring agent-state selectors, adding a per-conversation capability, or triggering a shortcut from a button, menu, or code (useShortcutTrigger, launchAgentExecution).
日本語の概要は準備中です。原文の説明を表示しています。
The provision for a call site: the exhaustive menu of values that place in the code can realistically produce. Use before creating or fixing a mandate or agent that reasons about more than its own input, when deciding whether an agent can answer at all with what it is sent, or when its output 'looks right' but nobody checked it could be. NOT for building the agent (use create-agent).
日本語の概要は準備中です。原文の説明を表示しています。