System-map example pack

Clinical intake review model UI generation matrix

An intake coordinator reviews administrative appointment readiness and decides schedule, return missing forms, or escalate insurance verification. Three generation paths are shown across four context boundaries. JudgmentKit skill context improves activity fit, workflow fit, disclosure discipline, and implementation guidance; Material UI improves visual/component consistency.

Generation path

Fixture-rendered baseline

Scripted renderer paths show the controlled fixture-rendered baseline for each context combination.

Raw brief

Fixture-rendered baseline - Raw brief

Fixture-rendered baseline receives only the raw brief and sample case. This tests what happens without JudgmentKit or Material UI.

Context

Raw brief

Render

deterministic_raw_brief_html

Open live artifact Open image

JudgmentKit skill context

Fixture-rendered baseline - JudgmentKit skill context

Fixture-rendered baseline receives the reviewed handoff plus compiled frontend skill context, but no Material UI adapter. This isolates skill-guided implementation without a component renderer.

Context

JudgmentKit skill context

Render

deterministic_frontend_skill_html

Open live artifact Open image

Material UI only

Fixture-rendered baseline - Material UI only

Fixture-rendered baseline is rendered through Material UI from raw-brief context only. This isolates visual/component consistency without JudgmentKit.

Context

Material UI only

Render

deterministic_material_ui_ssr

Open live artifact Open image

JudgmentKit skill + Material UI

Fixture-rendered baseline - JudgmentKit skill + Material UI

Fixture-rendered baseline receives the reviewed handoff plus compiled frontend skill context, then renders through the Material UI adapter. This is the full intended path.

Context

JudgmentKit skill + Material UI

Render

deterministic_frontend_skill_material_ui_ssr

Open live artifact Open image

Generation path

Gemma 4 via LM Studio lms

Local Gemma 4 captures show how a smaller local model responds to the same four context boundaries.

Raw brief

Gemma 4 via LM Studio lms - Raw brief

Gemma 4 via LM Studio lms receives only the raw brief and sample case. This tests what happens without JudgmentKit or Material UI.

Context

Raw brief

Render

model_static_html_css

Open live artifact Open image

Diagnostic only

Gemma 4 via LM Studio lms

Gemma 4 via LM Studio lms - JudgmentKit skill context

Gemma 4 via LM Studio lms receives the reviewed handoff plus compiled frontend skill context, but no Material UI adapter. This isolates skill-guided implementation without a component renderer.

Context

JudgmentKit skill context

Status

Needs repair before evidence

Failed checks

Token provenance failed, Capture quality failed

Material UI only

Gemma 4 via LM Studio lms - Material UI only

Gemma 4 via LM Studio lms is rendered through Material UI from raw-brief context only. This isolates visual/component consistency without JudgmentKit.

Context

Material UI only

Render

model_structured_data_material_ui_ssr

Open live artifact Open image

JudgmentKit skill + Material UI

Gemma 4 via LM Studio lms - JudgmentKit skill + Material UI

Gemma 4 via LM Studio lms receives the reviewed handoff plus compiled frontend skill context, then renders through the Material UI adapter. This is the full intended path.

Context

JudgmentKit skill + Material UI

Render

model_frontend_skill_material_ui_ssr

Open live artifact Open image

Generation path

GPT-5.5 xhigh via codex exec

GPT-5.5 captures use extra-high reasoning to show the same matrix with a stronger model path.

Raw brief

GPT-5.5 xhigh via codex exec - Raw brief

GPT-5.5 xhigh via codex exec receives only the raw brief and sample case. This tests what happens without JudgmentKit or Material UI.

Context

Raw brief

Render

model_static_html_css

Open live artifact Open image

Diagnostic only

GPT-5.5 xhigh via codex exec

GPT-5.5 xhigh via codex exec - JudgmentKit skill context

GPT-5.5 xhigh via codex exec receives the reviewed handoff plus compiled frontend skill context, but no Material UI adapter. This isolates skill-guided implementation without a component renderer.

Context

JudgmentKit skill context

Status

Needs repair before evidence

Failed checks

Token provenance failed, Capture quality failed

Material UI only

GPT-5.5 xhigh via codex exec - Material UI only

GPT-5.5 xhigh via codex exec is rendered through Material UI from raw-brief context only. This isolates visual/component consistency without JudgmentKit.

Context

Material UI only

Render

model_structured_data_material_ui_ssr

Open live artifact Open image

JudgmentKit skill + Material UI

GPT-5.5 xhigh via codex exec - JudgmentKit skill + Material UI

GPT-5.5 xhigh via codex exec receives the reviewed handoff plus compiled frontend skill context, then renders through the Material UI adapter. This is the full intended path.

Context

JudgmentKit skill + Material UI

Render

model_frontend_skill_material_ui_ssr

Open live artifact Open image

All model cells are committed captures. JudgmentKit skill context improves activity fit, workflow fit, disclosure discipline, and implementation guidance; Material UI improves visual/component consistency.