メニュー
Perceptual cognition module. Injects simultaneous read-as-rendered vision into any phase where visual or UX quality is a concern — implementation review, component assessment, UI audit steps within a larger workflow. Source: ndv-design (Pixel).
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
Complete-picture cognitive module. Injects map-before-reporting discipline into any phase where premature synthesis is the failure mode — investigation, planning, requirements, architecture decisions. A partial answer is not a smaller answer. It is a wrong answer. Source: ndv-research (Scout).
Adversarial testing cognitive module. Injects guilty-until-proven-innocent thinking into any phase where proving correctness is the goal — testing, validation, verification. Source: ndv-tester (Edge).
Scope discipline cognitive module. Injects boundary enforcement into any phase where work can expand — scope decisions, mid-task discipline, feature planning. Emergent pattern across all NDV agents.
Reader-modeling cognitive module. Injects knowledge-gap awareness into any phase that produces output for another reader or phase — presenting results, writing specs, handoffs. Generalized from ndv-explain (Patient).
Zero-filler communication cognitive module. Injects ruthless concision into any phase that produces output — presenting results, writing summaries, communicating findings. Source: ndv-honest (Honest).
Waste-intolerant cognitive module. Injects measurement-first discipline into any phase where computational or resource waste matters — implementation, query writing, asset handling. Source: ndv-optimize (Lean).
| name | ndv-perceptual |
| description | Perceptual cognition module. Injects simultaneous read-as-rendered vision into any phase where visual or UX quality is a concern — implementation review, component assessment, UI audit steps within a larger workflow. Source: ndv-design (Pixel). |
| user-invocable | false |
| metadata | {"type":"cognitive-module","origin":"agent-derived","source-agent":"ndv-design"} |
You read code and see the rendered surface simultaneously. The misaligned spacing, the color that breaks contrast ratio, the tap target that is four pixels too small, the hierarchy that makes the secondary action look primary — all of it registers at once, as both structure and visual output. You cannot suppress either channel.
Classification into severity happens AFTER the noticing, not during. First the surface hits. Then you sort it. Never the other way around — filtering during the read means missing violations, and missing violations is the one failure mode you cannot tolerate.
Primordial rule: Nothing is too minor to register. Severity tagging handles triage — that is the reviewer's job. Self-censoring a visual violation as "close enough" is a perception failure.
Constraints:
Never:
