Prepare, execute and verify authorized Fusion CAD changes using resolved entities, explicit units and state-bound plans. Use for reviewed parameter, sketch, feature, assembly or configuration operations.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Inspect the selected document and exact operation schema. Resolve design intent, units, frame, occurrence context and configuration. Generated configuration instances and external sources are not implicitly editable.
Prepare one operation with fusion_changes_prepare; review inputs, effects, state and policy blockers. Execute the unchanged hash with a unique idempotency key under the existing scoped grant. Prepare dependent operations only after inspecting the previous result. Parameter batches have documented local atomicity; feature sequences and cross-system writes do not.
Preserve driving constraints and parametric history. Never convert to direct mode, break references, fetch latest versions or interrupt an active command as a convenience.
For offset planes, sweep, loft, draft, split-body and mirror, read the CAD feature contracts. Keep native geometry in one editable component, explicit cut/intersect participants, ordered loft sections and exact sweep-path membership. Mirror creates separate bodies; split does not preserve unsplit originals. Draft's optional tangent/symmetric flags expand its effect and must be part of the reviewed request. Reinspect changed construction planes or axes before using their handles.
Verify meaningful numerical postconditions and feature health. Reinspect stale state. For partial/unknown outcomes, inspect receipts and the model before any new write; never blindly replay. fusion_recovery_prepare does not silently undo user work.
Saving is a separate cloud effect. Unsupported variants stay explicit. Assisted native tools require their separate broad grant and have different guarantees. See workflow.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Analyze reviewed Grafana log evidence for event patterns, error-rate changes, and enrolled security markers. Use when a user needs bounded log analytics for an incident window, error-log comparison, anomaly triage, operational debugging, or a cautious check of approved security signals.
中文简介正在准备中。当前显示原文说明。
Run a read-only App Store-readiness preflight for a declared iOS target without claiming approval or submitting anything.
中文简介正在准备中。当前显示原文说明。
Audit whether a declared local review evaluation can support fair quality claims. Use only when the user explicitly asks to audit review-eval validity or use the bundled synthetic fixture.
中文简介正在准备中。当前显示原文说明。
Deterministically score comparable imported review-run lanes with root-cause metrics and uncertainty. Use only when the user explicitly asks to benchmark normalized local review runs or use the bundled synthetic fixture.
中文简介正在准备中。当前显示原文说明。
Stage and verify Fusion exports, drawing PDFs, flat-pattern DXF, viewport images and local renders. Use for engineering deliverables, not automatic publication or release.
中文简介正在准备中。当前显示原文说明。
Prepare a traceable local Fusion engineering review draft with source identities, artifacts and unresolved assurance gates. Not for sending, publication or release approval.
中文简介正在准备中。当前显示原文说明。