feat(claude-design): add per-preset critique-iterate hint blocks

Thin ~12-line blocks in all eight presets, inserted after each file's last
lettered section and before ## Sources. Each carries only the differentiated
content: which design-critique sections dominate for that artifact type, which
are near-irrelevant, and which real prompt layer in 01-prompt-fundamentals.md
the findings route to in 9c. Shared mechanics stay in 05-critique-iterate.md.

Heading letter is per-file, not uniform: four presets end at (e) and four at
(f), so a literal (g) everywhere would leave an (e) -> (g) gap in four shipped
files. The canonical machine-checkable anchor is the letter-free substring
"Critique-iterate hint".

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NaybqQwqirrNmikJsUrbDg

skills/claude-design-facilitator/references/presets/designs.md

@@ -172,6 +172,16 @@ Expected follow-up turns:
 
 ---
 
+## (g) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Visual Hierarchy and Consistency. `designs` is the general case, so no section is dead weight here; expect the critique to spread across all of them and use `Priority Recommendations` to pick the one layer worth a turn.
+
+**Where findings route.** Visual Hierarchy findings route to Layer 1 Layout first — eye-flow problems are usually a region-order problem — and only then to Layer 4 Typography and Color. Consistency findings route to Layer 4 semantic color roles and the modular type scale, or to Layer 2a when the house-style spec was never concrete enough to constrain the drift.
+
+**One turn, one layer.** Because every section tends to fire on a general-purpose artifact, the risk is a re-prompt that rewrites all five layers at once and loses what worked. Carry the `What Works Well` items into Layer 5 as weights so the next turn preserves them.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration, launch post

skills/claude-design-facilitator/references/presets/frontier-design.md

@@ -138,6 +138,16 @@ When any of these triggers, update Section (b) to reflect verified material, rep
 
 ---
 
+## (g) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Consistency, and the craft judgment inside `Overall Impression`. Usability is near-irrelevant — a frontier artifact is judged on whether it escapes the convergent default, not on task completion.
+
+**Where findings route.** Consistency findings route to Layer 2a when the house-style spec was too loose to hold an unusual aesthetic together, and to Layer 4 for whichever dimension drifted — most often Motion and Backgrounds, the two this preset pushes hardest. Craft findings route to Layer 5 weighting. A critique that reads as "this looks like every other AI artifact" routes to Layer 3: the avoid-list was not carried into the turn.
+
+**This preset has the thinnest evaluation signal in the plugin** — see the honest-position section above. `design:critique` is often the only external read available on whether a frontier attempt landed, which raises the value of running Phase 9 here and lowers the confidence of any single finding. Treat one critique as one opinion, not as a verdict.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — Anthropic's verbatim one-sentence description (the entirety of Anthropic-published material on this preset)

skills/claude-design-facilitator/references/presets/marketing-collateral.md

@@ -206,6 +206,16 @@ Expected follow-up turns:
 
 ---
 
+## (f) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Visual Hierarchy — read as conversion order, not aesthetics — and `Overall Impression`. Usability is thin on a single-scroll marketing page: there is no task flow to fail.
+
+**Where findings route.** Anything about what the reader sees first, or about the CTA sitting below the fold, routes to Layer 1 Layout (region order and fold position) and Layer 1 Content (the CTA copy itself). Findings that name the artifact as generic or template-like route to Layer 3 — the AI-slop avoid-list was not carried into the turn, and marketing collateral is where the slop fingerprint is most visible to a reader. Consistency findings route to Layer 4 semantic color roles.
+
+**Watch for findings the prompt cannot fix.** Conversion is a claim about behaviour, not about the artifact. A critique asserting that a page "will not convert" is outside what any re-prompt can settle; name that to the operator rather than inventing a layer for it.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration

skills/claude-design-facilitator/references/presets/one-pagers.md

@@ -156,6 +156,16 @@ Expected follow-up turns:
 
 ---
 
+## (f) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Visual Hierarchy and Consistency, both usually surfacing as density problems. Usability is near-irrelevant — a one-pager is read, not operated.
+
+**Where findings route.** "Too much on the page" and "nothing dominates" route to Layer 1 Layout for the region set and to Layer 1 Content for the per-block word-count caps this preset already recommends. Trimming content is the higher-yield move of the two and the one operators reach for last. Consistency findings route to Layer 4, specifically the modular type scale — a one-pager that reads as flat is almost always missing scale steps rather than missing color.
+
+**A single-page artifact makes Layer 5 cheap to use.** There is one surface to grade, so an explicit weighting — functionality and craft over originality for an internal one-pager, the reverse for an external one — moves the next turn more than another Layer 4 spec will.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration, one-sentence description

skills/claude-design-facilitator/references/presets/pitch-decks.md

@@ -185,6 +185,16 @@ Expected follow-up turns:
 
 ---
 
+## (f) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Visual Hierarchy per slide, and the narrative judgment inside `Overall Impression`. Usability is near-irrelevant: a deck is presented, not used.
+
+**Where findings route.** Arc problems — a slide that does not earn its place, a claim landing before its setup — route to Layer 1 Content and Layer 1 Goal, per-slide, using the micro-prompt pattern above rather than a deck-wide re-prompt. Within-slide hierarchy routes to Layer 1 Layout and then Layer 4 Typography. Layer 5 is unusually load-bearing here: Anthropic's verbatim guidance weights design quality and originality highest for an external investor audience, so a critique that trades polish for density is describing a weighting problem, not a layout one.
+
+**Export findings are not critique findings.** The PPTX text-as-text caveat in the caveats section above is a destination constraint. It will not appear in the critique and it will not be fixed by any layer.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration

skills/claude-design-facilitator/references/presets/prototypes.md

@@ -214,6 +214,16 @@ Expected follow-up turns:
 
 ---
 
+## (g) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Usability first, Visual Hierarchy second. Consistency matters only where component reuse has drifted, which is a narrower read than in the static presets.
+
+**Where findings route.** Affordance and task-flow findings route to Layer 1 — usually Goal or Audience rather than Layout, because a prototype that fails a usability read has generally been briefed for the wrong user or the wrong job. Re-check the Audience line before touching the layout. Hierarchy findings route to Layer 1 Layout, then Layer 4.
+
+**Expect findings that exceed prompt scope.** This is the preset where 9c's exceeds-prompt-scope case fires most often: a critique will name an interaction that needs real state, a validation rule that needs real data, or a transition that needs a live backend. No layer fixes those. Say so plainly instead of routing them somewhere — a re-prompt aimed at an unfixable finding burns a turn and tends to degrade what already worked.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration

skills/claude-design-facilitator/references/presets/slides.md

@@ -225,6 +225,16 @@ Expected follow-up turns:
 
 ---
 
+## (g) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Visual Hierarchy, read per slide as eye flow, and Consistency, read deck-wide as drift between slides. Usability is near-irrelevant — there is no task flow in a deck to test.
+
+**Where findings route.** Per-slide hierarchy findings route to Layer 1 Layout, naming the region order for that slide. Deck-wide drift is the more valuable finding and routes elsewhere: to Layer 2a when the house-style spec was never concrete enough to hold across slides, and to Layer 4 for the type scale and semantic color roles that keep a deck coherent. Fixing drift one slide at a time is the common mistake; it is a spec problem, not a slide problem.
+
+**Screenshot input is usually the right choice here.** A deck's truth is the rendered slide, so the 9a screenshot path — one image per slide — grounds the critique better than an HTML export for this preset.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration

skills/claude-design-facilitator/references/presets/wireframes-mockups.md

@@ -152,6 +152,16 @@ Expected follow-up turns:
 
 ---
 
+## (f) Critique-iterate hint
+
+Phase 9 in `references/05-critique-iterate.md` carries the shared loop: export the artifact, run `design:critique`, read the output by judgment, re-prompt one layer. This block records only what differs for this preset.
+
+**Dominant critique sections.** Usability and Visual Hierarchy. Consistency, and any finding about type, color, or polish, is a **category error in low-fidelity mode** — the artifact is deliberately unfinished, and a critique that grades it on craft is answering a question nobody asked.
+
+**Where findings route.** Structure and flow findings route to Layer 1 Layout, and to Layer 1 Content when a region is unlabelled or vague. Do NOT route fidelity findings to Layer 4; that turns a wireframe into a mockup by accident and destroys the reason it was low-fi. The correct response is a Layer 5 re-weighting instead: Anthropic's verbatim guidance for an early-exploration wireframe weights functionality highest and deprioritizes craft and originality. Restate that weighting in the next turn and the same critique stops firing.
+
+**In high-fidelity mode the fence moves.** Once the operator has selected the high-fidelity tier described above, Consistency and Layer 4 findings become legitimate and route as they do for `designs`. Confirm which tier the artifact is in before mapping anything.
+
 ## Sources
 
 - `https://anthropic.com/news/claude-design-anthropic-labs` — preset enumeration, one-sentence description