---
name: design-md
metadata:
  internal: true
description: Add a new design.md catalog entry to ko-design-md. Use this skill IMMEDIATELY when the user wants to onboard a new brand into THIS project's catalog — produce services/{slug}.md (Stitch v0.1 format) plus services/{slug}.tokens.json (token-card sidecar) plus public/preview/{slug}/preview.html (one file carrying both themes) plus the OG image. Trigger phrases include "add to design.md catalog", "new design.md entry for X", "onboard X to ko-design-md", "X를 ko-design-md에 추가", "X의 design.md 만들어줘", "/design-md", "X 카탈로그 항목 만들기", or any variant where the user is asking to populate this catalog with a new brand entry. Do NOT use for editing prose in an existing entry, fixing one frontmatter field, generating non-catalog design docs, or working in any other repository. The skill operates only inside the ko-design-md repo and verifies this via `package.json` name.
---

# /design-md skill — orchestration body

This skill builds a complete catalog entry through a 5-subagent pipeline with one user checkpoint every entry hits (Stage 7), plus a conditional one ahead of it when a design board is the upstream (Stage 4c). The pipeline is heavy (research, drafting, two review loops) so resumability matters: each stage's artifact lives on disk in `.claude/cache/design-md/{slug}/` and the next stage reads from there. State is encoded by file presence — no separate state.json needed for v1.

## Pipeline shape

```
[INTAKE] → research-collector → design-md-author ⇄ design-md-reviewer (loop ≤3)
                                                          ↓ score≥8 or N=3
                                                    [USER CHECKPOINT]
                                                          ↓ approve
                                                [WRITE_MD] → [TOKENS]
                                                          ↓
                                  preview-html-author ⇄ preview-html-reviewer (loop ≤3, non-blocking)
                                                          ↓
                                                   [WRITE_PREVIEW]
                                                          ↓
                                                       [BUILD_OG]
                                                          ↓
                                                       [VERIFY]
                                                          ↓
                                                         END
```

**Loop termination**: design loop is blocking — score must reach 8/10 within 3 iterations or the user decides at the checkpoint. Preview loop is non-blocking — proceed with warning if score < 8 at iteration 3.

**Key reference files** (read these before dispatching subagents that need them):
- `.claude/skills/design-md/references/stitch-format.md`
- `.claude/skills/design-md/references/design-md-template.md`
- `.claude/skills/design-md/references/rubric-design.md`
- `.claude/skills/design-md/references/rubric-preview.md`

## Stage 1 — Preflight

Verify the working environment before doing anything user-visible.

1. `Bash`: `pwd` to capture the absolute repo root. Hold this value as `${repo_root}` in your reasoning and substitute it literally into every later Bash command and dispatch prompt that touches a repo path. The shell preserves cwd across calls, but pinning the absolute path makes Stage 8/10/11 robust to any inadvertent `cd`.
2. `Bash`: `date +%Y-%m-%d` to capture today's date. Hold this value as `${today}` in your reasoning. Stage 6a passes this to the author for **both** the `last_updated` and `created_at` frontmatter fields — a brand-new entry is added and last-updated on the same day. The project's date validator at `src/lib/content-parser.ts` rejects any other format, and `missing-created-at` in `src/lib/draft-validator.ts` blocks a draft that omits `created_at`.
3. `Read` `${repo_root}/package.json`. If `"name"` is not exactly `"ko-design-md"`, abort with: "이 스킬은 ko-design-md 레포 안에서만 동작합니다. 현재 디렉터리: ${repo_root}". Do not proceed.
4. Verify `${repo_root}/src/lib/content-types.ts` is readable. If not, abort.
5. `Read` `${repo_root}/src/lib/content-types.ts` and extract the live `CATEGORIES` const. Use this as the source of truth for the intake category picker (do NOT hardcode the enum from memory — it can drift).

## Stage 2 — Conversational intake

Use a single `AskUserQuestion` form with these 3 questions (multi-select where indicated):

1. **브랜드명** (text via "Other" → custom input): e.g. "토스", "당근", "구름". Use the Korean company/brand display name as it should appear in the `name` frontmatter, not the design system product name. If research later surfaces a distinct design system name (e.g. "SEED Design", "Vapor UI"), the author stores that in optional `design_system_name`.
2. **참고 URL** (text via "Other"): comma-separated URLs. **2개 이상 권장** — 1개만 입력 시 research-collector가 INSUFFICIENT_SOURCES로 중단할 수 있고, 그 경우 스크린샷 보강 필요. Brand homepage, design system page, blog post about their UI, etc.
3. **카테고리** (single-select): all values from `CATEGORIES` const, in order. Last option is `etc`.

Do not ask for a language. An entry is one Korean design.md — `lang` is always `ko` (`docs/adr/0001-korean-design-md-only.md`), and every dispatch below passes it as a literal.

Then ask four follow-up text inputs:
- **스크린샷 경로** (optional) — comma-separated absolute paths to screenshot files. The user can type "없음" to skip.
- **로고 자산 경로** (optional) — an existing local file path for a brand logo. Accept only `.svg`, `.png`, `.webp`, or `.avif`. The user can type "없음" to skip.

  **CRITICAL — pick a small square symbol mark, NOT a wordmark.** Two square slots in the site consume this asset: the catalog grid card (~48–96 px on screen) AND the OG image's top-left brand mark (32×32 px in the 1200×630 social card, see `src/og/template.tsx`). The OG renderer (Satori) has limited `object-fit` support, so a non-square asset is stretched into the 32×32 box rather than letterboxed — the catalog card has the same constraint at its own scale. Choose accordingly:
  - ✅ Pick the brand's standalone **symbol / mark / favicon shape** with a transparent background — e.g. SOCAR's angular blue mark, Toss's curved oval lens, Gmarket's circular G, Baemin's symbol. Match the style of existing `public/logos/{toss,socar,baemin,…}.png` (square, no text, no baked-in frame).
  - ❌ Avoid the **horizontal wordmark / lockup** (the brand name written out, e.g. "Gmarket", "toss", "쏘카") — wordmarks render too small in the grid card or break its aspect.
  - ❌ Avoid **iOS-squircle / framed app icons** with a rounded gradient background baked in — that frame conflicts with the catalog card's own background. Prefer the unframed symbol form.
  - When a bundle provides multiple variants (e.g. `logo-brand.png` wordmark vs `logo-circular-g.png` symbol vs `logo-app-icon.png` framed), the **unframed symbol** is correct for the catalog grid. Filename hints for the GRID-WRONG forms: `*wordmark*`, `*logotype*`, `*-brand*`, `*-horizontal*`, `*-app-icon*` (framed). Filename hints for the GRID-RIGHT form: `*-symbol*`, `*-mark*`, `*-circular*`, `*-icon*` (when unframed), or a generic `{slug}.png` that is already a symbol.

  **Optional second asset — wordmark/logotype for the preview hero.** The catalog grid uses the symbol, but the preview HTML hero (`public/preview/{slug}/preview.html`) has room for a richer brand lockup with the brand name visible. If the source provides BOTH a symbol AND a horizontal wordmark/logotype, capture both paths. Stage 4a will place the wordmark at `public/logos/{slug}-logotype.{ext}` (matching the existing `toss-logotype.png` convention), and the preview-html-author renders the wordmark in the hero where there is space. The grid card always uses the symbol; the **wordmark has no frontmatter field** — it stays a site-internal preview-only asset (the design.md's `logo` frontmatter URL still points to the symbol so the file remains portable outside ko-design-md).
- **디자인 시스템 문서 사이트 URL** (optional) — if the brand publishes its design system as a documentation website (not only Figma), the root URL of that site (e.g. `https://socarframe.socar.kr/`). Stage 4b crawls it into a research corpus. The user can type "없음" to skip.

- **디자인 보드 / 핸드오프 번들 경로** (optional) — comma-separated absolute paths to a Claude Design board's exported frames, or a directory the handoff bundle was already extracted into. The user can type "없음" to skip. This is what makes **Stage 4c** fire; without it there is nothing to approve and the run goes straight from Stage 4b to Stage 5. Ask for it even when the brand has a docs site — the two are different upstreams and an entry can have both. **The link expires.** A Claude Design handoff URL 404s in roughly fifteen minutes, so the user must have already saved it locally; do not accept a URL here.

Capture the answers as: `brand_name`, `source_urls` (parsed array), `category`, `screenshot_paths` (parsed array, may be empty), `logo_asset_path` (string or empty), `docs_site_url` (string or empty), `design_board_paths` (parsed array, may be empty).

**Screenshot path preflight**: for each path in `screenshot_paths`, run `Bash`: `[ -f "$path" ]`. If any path is missing, surface the missing list to the user and re-prompt the screenshot question. This avoids research-collector failing silently mid-read.

**Logo path preflight**: if `logo_asset_path` is not empty/`없음`, run `Bash`: `[ -f "$logo_asset_path" ]` and verify the extension matches `svg|png|webp|avif`. If missing or unsupported, surface the problem and re-prompt the logo question. Do not download logos from the web.

## Stage 3 — Slug derivation + conflict resolution

Derive `slug` from `brand_name`:
1. NFD-normalize and strip diacritics/non-ASCII.
2. Lowercase, replace `[^a-z0-9]+` with `-`, trim leading/trailing `-`.
3. If the result is empty (Korean-only brand with no Latin form), prompt the user via `AskUserQuestion` for an explicit slug. Question wording: **"slug은 영문 소문자/숫자/하이픈만 가능합니다 (예: `toss`, `karrot-market`)."** Validate the user's input matches `^[a-z0-9-]+$`; on mismatch, re-prompt.

Check for conflicts via `Bash` (`ls services/{slug}.md 2>/dev/null`):

- No conflict → proceed.
- Conflict → `AskUserQuestion`:
  - "다른 slug 사용" → user provides a new slug, recheck.
  - "기존 항목 업데이트" → set `mode = update`. The pipeline still runs but final write overwrites.
  - "취소" → abort.

## Stage 4 — Cache setup

Create the staging directory:

```bash
mkdir -p .claude/cache/design-md/{slug}
```

This directory holds all intermediate artifacts. It's gitignored (`.claude/cache/` was added to `.gitignore` when the skill was installed) so partial work won't leak into PRs.

### Stage 4a — Logo asset resolution

**Before resolving paths — verify the logo asset is the right FORM.** The catalog grid card uses a small square logo slot, so the chosen asset MUST be a **symbol / mark / favicon shape** (transparent background, no text), NOT a horizontal wordmark and NOT an iOS-squircle app icon with a baked-in background. When auto-picking from a bundle/zip that contains multiple variants, prefer filenames matching `*-symbol*`, `*-mark*`, `*-circular*`, or unframed `*-icon*`; reject filenames matching `*wordmark*`, `*logotype*`, `*-horizontal*`, `*-brand*` (often the wordmark), or `*-app-icon*` (often the iOS-squircle framed form). If only a wordmark variant is available, prompt the user to confirm before placing it — wordmarks are a known catalog-grid mismatch (see Stage 2's logo intake rule and the existing `public/logos/{toss,socar,baemin,...}.png` reference). This check applies inside step 1 below.

Resolve **two** logo values before dispatching author agents — different downstream concerns need different forms:

- **`logo_url`** — fully-qualified URL like `https://getdesign.kr/logos/toss.png`. Goes into design.md **frontmatter**, where it must stay meaningful when the file is copied outside the ko-design-md site (PRD User Story 1 — vibe-coding flow).
- **`logo_src_path`** — site-relative path like `/logos/toss.png`. Goes into preview HTML `<img src>`, which is only ever loaded inside the catalog site's iframe. Keeping it relative avoids making dev/staging depend on the production-domain asset.

Both either co-exist (logo found) or are simultaneously empty (no logo).

The canonical site origin is **`https://getdesign.kr`**. Change this constant in one place only — this paragraph — if the origin ever moves.

1. If `logo_asset_path` was provided:
   - Verify it exists and has a supported extension (`svg`, `png`, `webp`, `avif`).
   - If it already lives under `${repo_root}/public/logos/`, set `logo_src_path = /logos/{basename}` and `logo_url = https://getdesign.kr/logos/{basename}`.
   - Otherwise copy it to `${repo_root}/public/logos/{slug}.{ext}` and set `logo_src_path = /logos/{slug}.{ext}` and `logo_url = https://getdesign.kr/logos/{slug}.{ext}`. This is allowed only for user-supplied local logo assets.
2. If no logo path was provided, auto-detect the first existing file in `public/logos/{slug}.{svg,png,webp,avif}` (in that order) and set `logo_src_path = /logos/{slug}.{ext}` and `logo_url = https://getdesign.kr/logos/{slug}.{ext}`.
3. If nothing is found, set both to an empty string and continue. The entry may ship without a logo, but Stage 13 must report the missing logo TODO.
4. **Optional wordmark / logotype for the preview hero.** If a wordmark variant was captured at Stage 2 (a horizontal lockup that contains the brand name as text — e.g. `logo-brand.png`, `*-logotype.svg`), copy it to `${repo_root}/public/logos/{slug}-logotype.{ext}` and set `logo_wordmark_src_path = /logos/{slug}-logotype.{ext}`. If no wordmark was captured at intake but a file already exists at `public/logos/{slug}-logotype.{svg,png,webp,avif}`, auto-detect it (same precedence order as the symbol). Otherwise set `logo_wordmark_src_path = ""`. There is NO frontmatter URL for the wordmark — it is a site-internal preview-only asset; the design.md `logo` field always references the symbol so the file remains portable outside ko-design-md.

The auto-detect pattern for the catalog grid logo is exactly `public/logos/{slug}.{svg,png,webp,avif}`; for the optional wordmark it is `public/logos/{slug}-logotype.{svg,png,webp,avif}`. When the symbol values are non-empty, every later stage must preserve them exactly — design-md-author writes `logo_url` verbatim into frontmatter, preview-html-author embeds `logo_src_path` as `<img src>` (or `logo_wordmark_src_path` in the hero when that is non-empty), and the Stage 10 grep checks match each file against the appropriate form.

### Stage 4b — Docs-site crawl (conditional)

If `docs_site_url` is empty or "없음", skip this stage and set `crawl_corpus_path = "none"`.

Otherwise, crawl the brand's documentation site into the cache directory so research-collector can use it as a primary source. This runs the `docs-crawler` skill's engine — a sitemap-driven crawl with a JS-render fallback that also localizes images (external and inline base64) into `crawl/images/`, so the cached corpus is self-contained:

```bash
cd "${repo_root}" && pnpm crawl:docs "${docs_site_url}" --out "${repo_root}/.claude/cache/design-md/{slug}"
```

The crawl writes `crawl-corpus.md` (the merged corpus) plus `crawl/pages/*.md`, the downloaded `crawl/images/`, and `crawl/manifest.json` into the (gitignored) cache directory. The first crawl of a JavaScript-rendered site auto-installs a headless browser (~150MB, one-time).

After it returns, verify the corpus landed:

```bash
[ -s "${repo_root}/.claude/cache/design-md/{slug}/crawl-corpus.md" ] && echo CORPUS_OK || echo CORPUS_MISSING
```

- `CORPUS_OK` → set `crawl_corpus_path = ${repo_root}/.claude/cache/design-md/{slug}/crawl-corpus.md`.
- `CORPUS_MISSING`, or the crawl exited non-zero → the crawl failed. It is best-effort: research can still proceed from `source_urls`. `AskUserQuestion`: "문서 사이트 크롤 실패 — (a) 다시 시도 / (b) 크롤 없이 진행 / (c) 취소". On "다시 시도" re-run the crawl; on "크롤 없이 진행" set `crawl_corpus_path = "none"`; on "취소" abort with the resume path.

### Stage 4c — Design board checkpoint (conditional)

Run this stage when `design_board_paths` from Stage 2 is non-empty; otherwise skip it and go to Stage 5. That variable is the trigger — the condition is not a judgment call.

**Preflight**: for each path, `Bash`: `[ -e "$path" ]`. Surface any missing path and re-prompt, the same as the screenshot preflight. Then `Read` the frames (image paths read as images; a directory is listed and its files read).

Show what the board settled and what it left open: the palette in both themes, the type scale, the components it laid out, and anything it declined to define. Then `AskUserQuestion`: "디자인 보드를 확인해 주세요 — (a) 승인하고 리서치로 / (b) 보드를 고치고 다시 / (c) 취소". On (b), the user's corrections go back to the board; nothing downstream is generated until it is approved.

**On approval, carry the board forward — the gate is worthless if the values stop here.** Append the approved **image files** to `screenshot_paths` before Stage 5 dispatches, reusing the listing the preflight already produced: a path that was a directory is expanded to the files inside it, and the directory string itself is never appended. research-collector's contract is "an array of local image paths to read" and its tools are `WebFetch, WebSearch, Read, Write` — it has no `Bash` to list a directory, and `Read` cannot open one, so a directory handed over here is a source that silently never gets read. Without this step Stage 5 receives only `source_urls` and the crawl corpus, and the run rebuilds from public research alone while the approval implies otherwise.

This is what puts the board upstream of `research.md`, and through it upstream of the draft, the preview, the sidecar and the OG image.

The asymmetry is what justifies a second gate. Approving a wrong board costs the entire run, because every later artifact is rebuilt from it — and the Stage 7 checkpoint cannot recover it, since by then the draft has already transcribed the wrong values and reads as internally consistent. Approving a right one pays off at Stage 12: on `remember` the board's twenty role colors survived the whole chain into the preview unchanged, and the one discrepancy the comparison found was not a value but **where** a value had been applied — which no gate in this pipeline looks at.

An entry researched from public sources alone has no board to approve and goes straight to Stage 5.

## Stage 5 — Research (research-collector)

Dispatch via `Agent` tool with `subagent_type: "research-collector"`. Pass this prompt:

```
Research the brand "{brand_name}" (slug: {slug}) for ko-design-md catalog onboarding.

source_urls: {comma-separated URLs}
screenshot_paths: {comma-separated paths or "none"}
crawl_corpus_path: {crawl_corpus_path from Stage 4b — absolute path to crawl-corpus.md, or "none"}
category: {category}
lang: ko
cache_dir: {absolute path to .claude/cache/design-md/{slug}/}

Follow your agent definition. If crawl_corpus_path is not "none", read that corpus first as your primary source. Write exactly one file at {cache_dir}/research.md with the cited-claims structure. Halt with INSUFFICIENT_SOURCES only if crawl_corpus_path is "none" AND fewer than 2 URLs return 2xx.
```

After the agent returns, `Read` `{cache_dir}/research.md`.
- If the first line of `## Sources` is `INSUFFICIENT_SOURCES`, surface this to the user via `AskUserQuestion` with options: "URL 추가 입력" / "스크린샷 경로 추가" / "취소". On URL/screenshot addition, re-dispatch research-collector with the augmented inputs.
- **Section sanity check**: `Bash`: `grep -c '^## ' {cache_dir}/research.md`. Expected output is `9` (one per documented H2 section). If less than 9, the agent silently produced a malformed file — re-dispatch with an instruction prefixed: "Your previous research.md was malformed (only N sections found). Produce ALL 9 H2 sections in the documented order, even if some are `(no public evidence found)`."
- Otherwise, proceed.

## Stage 6 — Draft + design.md review loop

Iteration counter `N = 1`. Loop:

### 6a. Dispatch design-md-author

Via `Agent` with `subagent_type: "design-md-author"`. Pass:

```
Author a Stitch v0.1-format design.md draft for "{brand_name}".

cache_dir: ${repo_root}/.claude/cache/design-md/{slug}/
slug: {slug}
name: {brand_name}
category: {category}
lang: ko
today: {today as YYYY-MM-DD}
logo_url: {logo_url or "none"}
research_path: ${repo_root}/.claude/cache/design-md/{slug}/research.md
prior_review_path: ${repo_root}/.claude/cache/design-md/{slug}/review-{N-1}.json or "none" on first pass
format_reference_path: ${repo_root}/.claude/skills/design-md/references/stitch-format.md
template_path: ${repo_root}/.claude/skills/design-md/references/design-md-template.md
demo_paths: (none — leave empty by default; pass an existing ${repo_root}/services/*.md only if a stylistic peer genuinely fits the new brand. The early _demo-*.md fixtures have been removed.)

Follow your agent definition. Write {cache_dir}/draft.md.
```

After return, verify `{cache_dir}/draft.md` exists and is non-empty. If missing, the author failed — log the issue, retry once with the same prompt; if still missing, abort with a diagnostic message.

### 6a2. Deterministic draft gate (machine validation)

Before spending a reviewer dispatch, run the draft validator — it covers every mechanically checkable rubric item (frontmatter round-trip, section presence/order, OKLCH-only token values, `[src:N]`/References integrity, expected logo) so the reviewer model never has to "grep mentally":

```bash
cd "${repo_root}" && pnpm validate:draft .claude/cache/design-md/{slug}/draft.md \
  --slug {slug} --expected-logo {logo_url or none} --lang ko \
  --iteration {N} --json-out "${repo_root}/.claude/cache/design-md/{slug}/review-machine-{N}.json"
```

- **Exit 0** → proceed to 6b, passing the machine report path (see the 6b prompt).
- **Exit 1** (block issues) → do NOT dispatch the reviewer. Re-dispatch 6a with `prior_review_path` = the `review-machine-{N}.json` above (its `issues[]` uses the same `severity`/`section`/`fix` shape the author already consumes). Machine retries use a sub-counter **K (max 2) and do not increment N** — machine fixes are cheap and must not consume the semantic-review budget.
- **K exhausted with blocks remaining** → dispatch 6b anyway; the reviewer receives the failing machine report and the normal loop/checkpoint rules take over (no new termination path).

### 6b. Dispatch design-md-reviewer

Via `Agent` with `subagent_type: "design-md-reviewer"`. Pass:

```
Score the draft.md at {cache_dir}/draft.md against the rubric.

cache_dir: {abs path}/.claude/cache/design-md/{slug}/
draft_path: {cache_dir}/draft.md
research_path: {cache_dir}/research.md
content_types_path: {abs path}/src/lib/content-types.ts
rubric_path: {abs path}/.claude/skills/design-md/references/rubric-design.md
expected_logo_url: {logo_url or "none"}
machine_report_path: {cache_dir}/review-machine-{N}.json
iteration_n: {N}
output_path: {cache_dir}/review-{N}.json

Follow your agent definition. Write exactly one file at output_path.

The machine report has already verified the deterministically checkable items
(frontmatter round-trip, section presence/order, hex/rgba token scan,
[src:N]/References integrity, expected logo). Do not re-verify those — spend
your review on judgment items: Brand fidelity semantics against research.md,
Voice/tone, and cross-section token contradictions.
```

After return, `Read` `{cache_dir}/review-{N}.json`.

### 6c. Loop decision

- If `review.passed && review.score >= 8` → exit loop, go to Stage 7.
- Else if `N < 3` → `N += 1`, go back to 6a (the author will read review-{N-1}.json and revise).
- Else (`N == 3` and not passed) → exit loop with a `warn` flag; go to Stage 7. The user will see the failed verdict at the checkpoint and decide.

## Stage 7 — User checkpoint

This is the gate **every** entry passes through — Stage 4c precedes it only when a design board is upstream. Show the user:

1. The current `draft.md` content (read it and display the full file inline, formatted as markdown — paste in code fences).
2. The latest `review-{final}.json` verdict — extract `score`, `passed`, `verdict`, and bullet the issues array.
3. If iteration > 1, show a brief diff highlight: `"Iter 1 score: X → Iter {final} score: Y"` plus the top 1–2 issues that improved between iterations (compare `review-1.json.issues` and `review-{final}.json.issues`).

Then `AskUserQuestion`:

| Option | Effect |
|---|---|
| "승인하고 계속" | Approve as-is. Proceed to Stage 8. |
| "수정 사항 알려주고 한 번 더" | User provides feedback in the "Other" custom input. Append the user's notes to the prior review-N.json's issues array (with `severity: block`) and re-dispatch the author for one more revision. After this extra revision, run the reviewer once more, then return to checkpoint with the new draft. |
| "취소" | Abort. Cache dir is left intact. Print: "취소되었습니다. 재개하려면 cache 디렉터리에서 작업을 이어가세요: `.claude/cache/design-md/{slug}/`" |


## Stage 8 — Write design.md to services/

After approval:

1. `Bash`: `cp ${repo_root}/.claude/cache/design-md/{slug}/draft.md ${repo_root}/services/{slug}.md`
2. `Read` the placed file to confirm content arrived intact.
3. **Generate the token sidecar** — `Bash`: `pnpm tokens:build {slug}` extracts `services/{slug}.tokens.json` from the design.md you just placed. This is the visual design-token data (colors / typography / spacing / radius / elevation) that drives the detail page's **Tokens** tab (`src/routes/services/$slug.tsx:257`); `src/lib/content-collection.ts` loads it as `doc.tokens` (runtime is a plain `JSON.parse`, no markdown parsing). Inspect the printed `Nc Nt Ns Nr` line (a trailing `Ne` appears when `## Elevation & Depth` publishes shadow values). The extractor reads the frontmatter token maps (`colors:` / `typography:` / `spacing:` / `rounded:`) and markdown tables, one token per line — `name: oklch(...)` (colors), `name: 16px` (spacing/rounded). **Typography is the exception: it nests.** A bare style name on its own line, then four-space `fontSize` / `fontWeight` / `lineHeight` / `letterSpacing`. The inline `name: { size, weight, line-height }` and `name: 16 / 24 / 700` forms are read only from markdown tables and legacy body fences — written into frontmatter they yield **zero** type tokens, and `tokens:check` then agrees with the empty sidecar it generated from them. **Semantic aliases** (`{colors.x}`, bare references like `fill-brand: blue-500`) are intentionally excluded — they stay in the prose only. If **any** of the four counts is unexpectedly `0`, that `## Colors / Typography / Spacing / Rounded` section isn't in a codegen-readable form. **`Ne` is exempt from that rule** — it is absent whenever the entry's Elevation section carries usage labels or z-indices instead of shadow values (bezier and class101 are both legitimately shadow-less), so a missing `Ne` is only a signal when you authored real `box-shadow` values there. The deterministic path is to **route back to a Stage 6 draft revision** with a blocking prior-review issue naming the unreadable section (a human operator running the skill by hand may instead fix the section directly), then re-run `pnpm tokens:build {slug}` so the entry ships with full token cards.

If the `cp` itself fails (filesystem error), surface the error and route back to the checkpoint.

## Stage 9 — Preview HTML author + review loop

Iteration counter `M = 1`. Same shape as Stage 6, dispatching `preview-html-author` and `preview-html-reviewer`.

### 9a. Dispatch preview-html-author

```
Build preview.html for "{brand_name}".

cache_dir: {abs path}/.claude/cache/design-md/{slug}/
slug: {slug}
name: {brand_name}
lang: ko
design_md_path: {abs path}/services/{slug}.md
runtime_tokens_path: {abs path}/public/preview/_runtime/tokens.css
runtime_iframe_path: {abs path}/public/preview/_runtime/iframe.js
logo_src_path: {logo_src_path or "none"}
logo_wordmark_src_path: {logo_wordmark_src_path or "none"}
demo_html_paths: (none — leave empty by default; pass an existing {abs path}/public/preview/*/preview.html only if a visual peer genuinely fits. The early demo-courier/demo-pay previews have been removed.)
prior_review_path: {cache_dir}/preview-review-{M-1}.json or "none"

Follow your agent definition. Write {cache_dir}/preview.html. If `logo_wordmark_src_path` is not "none", render that wordmark `<img>` in the hero brand lockup (the hero has room for the brand name) and reserve `logo_src_path` (the small symbol) for compact references inside the component showcase, favicons, or chip-sized contexts. If `logo_wordmark_src_path` is "none", use `logo_src_path` in the hero too. Size hero `<img>` by `height` + `width: auto` so either aspect ratio (square symbol or horizontal wordmark) renders correctly.
```

### 9a2. Deterministic preview gate (machine validation)

Same shape as 6a2 — run the preview validator before spending a reviewer dispatch:

```bash
cd "${repo_root}" && pnpm validate:previews \
  --preview .claude/cache/design-md/{slug}/preview.html \
  --design-md "${repo_root}/services/{slug}.md" \
  --expected-logo-src {logo_src_path or none} \
  --expected-wordmark-src {logo_wordmark_src_path or none} \
  --iteration {M} --json-out "${repo_root}/.claude/cache/design-md/{slug}/preview-review-machine-{M}.json"
```

It hard-checks the structural rubric items (data-theme/lang, absolute runtime paths, foreign scripts, transfer size, hero logo src, catalog disclosure strip) **plus two content rules that used to be reviewer judgment** — a swatch catalog (fill-only elements per theme, Item 2) and a type-scale showcase (design.md typography token names printed as visible text labels, Item 3). Size is weighed in **brotli** bytes, the form Vercel actually serves, with a raw cap kept only as a safety net against runaway generated markup. It also emits warn-level responsive heuristics plus an `oklch coverage` metric (`matched/total` per theme) in `metrics`.

- **Exit 0** → proceed to 9b, passing the machine report path.
- **Exit 1** → do NOT dispatch the reviewer. Re-dispatch 9a with `prior_review_path` = the `preview-review-machine-{M}.json`. Machine retries use a sub-counter **K (max 2) and do not increment M**.
- **K exhausted with blocks remaining** → dispatch 9b anyway; the normal non-blocking loop rules take over.

### 9b. Dispatch preview-html-reviewer

```
Score the preview HTML files at {cache_dir} against the rubric.

cache_dir: {abs path}/.claude/cache/design-md/{slug}/
preview_path: {cache_dir}/preview.html
design_md_path: {abs path}/services/{slug}.md
rubric_path: {abs path}/.claude/skills/design-md/references/rubric-preview.md
expected_logo_src_path: {logo_src_path or "none"}
machine_report_path: {cache_dir}/preview-review-machine-{M}.json
iteration_n: {M}
output_path: {cache_dir}/preview-review-{M}.json

Follow your agent definition. Write exactly one file at output_path.

The machine report has already verified the structural Item 1 checks
(data-theme, absolute runtime paths, foreign scripts, transfer size, hero
logo src, catalog disclosure strip). Do not re-verify those — adopt the
report's result for Item 1. It also carries two content blocks: a swatch
catalog forces Item 2 to 0 and a type-scale showcase forces Item 3 to 0,
adopted wholesale on the same rule and mirrored into `issues` as `block`.
Spend the rest of your review on judgment: Color fidelity semantics (use the
report's oklch coverage metric as the Item 2 input), Component coverage,
Typography hierarchy, and dark-mode appropriateness.
```

### 9c. Loop decision (non-blocking)

- If `passed && score >= 8` → exit loop, go to Stage 10.
- Else if `M < 3` → `M += 1`, go back to 9a.
- Else (`M == 3` and not passed) → log the warning, exit loop, go to Stage 10 anyway. Preview review is non-blocking because visual previews iterate naturally during real use; the user already approved the design.md the preview is built from.

## Stage 10 — Write previews to public/

```bash
mkdir -p ${repo_root}/public/preview/{slug}
cp ${repo_root}/.claude/cache/design-md/{slug}/preview.html ${repo_root}/public/preview/{slug}/preview.html
```

### Logo deterministic check

If the resolved logo values are non-empty, verify the placed main markdown contains the absolute URL form and the preview HTML contains the site-relative form:

```bash
# Markdown: frontmatter `logo` is the symbol's absolute URL (portable across copies of the file).
rg -q -F "logo: {logo_url}" "${repo_root}/services/{slug}.md" || echo "LOGO_MISSING_MD"

# Preview HTML hero src: when the wordmark exists, the hero uses the wordmark; otherwise the symbol.
# `{logo_wordmark_src_path}` is the literal string "none" when no wordmark was captured —
# `${var:-fallback}` would treat "none" as a non-empty value and skip the fallback, so use an
# explicit conditional that handles both "none" and the empty case.
HERO_SRC="{logo_wordmark_src_path}"
if [ "$HERO_SRC" = "none" ] || [ -z "$HERO_SRC" ]; then
  HERO_SRC="{logo_src_path}"
fi
rg -q -F "src=\"${HERO_SRC}\"" "${repo_root}/public/preview/{slug}/preview.html" || echo "LOGO_MISSING"
```

If any sentinel prints, do not proceed to Stage 11. If the markdown is missing the logo, re-run Stage 6a with a blocking prior-review issue that says `logo_url` must appear as frontmatter `logo` (the exact fully-qualified URL — not a site-relative shortcut). If the preview is missing the hero logo, re-run Stage 9a with a blocking prior-preview issue that says the exact `HERO_SRC` (site-relative form — wordmark when defined, else symbol) must render as an `<img src>` in the shared markup — not inside a theme variant.

### Catalog disclosure deterministic check

`validate:previews` already blocks on this at 9a2, so reaching here with a missing strip means the file changed after the gate. Re-check the placed file:

```bash
F="${repo_root}/public/preview/{slug}/preview.html"
rg -q -F 'class="catalog-disclaimer"' "$F" || echo "DISCLAIMER_MISSING"
rg -q -F '제휴·후원 관계가 없습니다' "$F" || echo "DISCLAIMER_NO_NONAFFILIATION"
rg -q -F '더미 데이터' "$F" || echo "DISCLAIMER_NO_DUMMYDATA"
rg -qU '<body>(\s|<!--[\s\S]*?-->)*<div class="catalog-disclaimer"' "$F" || echo "DISCLAIMER_MISPLACED"
```

`-U` (multiline) is required for the placement check — the strip sits on the line *after* `<body>`, so a line-scoped match never sees both. The comment alternation matches `DISCLAIMER_FIRST_CHILD` in `src/lib/preview-validator.ts`: a comment between `<body>` and the strip is still a strip-first document, and flagging it here would send Stage 9a back to fix markup that 9a2 already passed.

**These sentinels are deliberately stricter than the validator on one axis: quoting.** `preview-validator.ts` accepts `class='catalog-disclaimer'` because it also validates hand-edited and pre-existing files. Stage 10 re-checks *pipeline output*, where `.claude/agents/preview-html-author.md` prescribes the strip **byte for byte** with double quotes — so `-F` on the verbatim form is the point, not an oversight. A single-quoted strip reaching here means the author deviated from a verbatim instruction, which is worth a Stage 9a round. Do not "fix" this by loosening it to match the validator.

The two phrase sentinels are literal (`-F`) for the same reason: the non-affiliation sentence is shared verbatim with `src/components/site/footer.tsx` and pinned by `src/lib/license-notice-consistency.test.ts`.

If any `DISCLAIMER_*` sentinel prints, do not proceed to Stage 11. Re-run Stage 9a with a blocking prior-preview issue quoting the verbatim strip from `.claude/agents/preview-html-author.md` and stating it must be the first child of `<body>` — in the shared markup, not inside a theme variant.

### Preview token alias registration

The moment the previews land in `public/`, the OKLCH drift gate starts expecting this slug to be accounted for. Run it:

```bash
cd "${repo_root}" && pnpm test src/lib/oklch-drift-corpus.test.ts
```

That gate compares each preview's `--custom-property: oklch(…)` declarations against the `name: oklch(…)` definitions in `services/{slug}.md`, by **exact name**. Previews almost always namespace their variables (`--tds-blue-500` for md `blue-500`), so each slug declares a rewrite rule in `PREVIEW_TOKEN_ALIASES` (`src/lib/oklch-drift.ts`). Without one, every declaration in this preview is unreachable and the gate silently checks nothing for the new entry — which is what the corpus test refuses to let happen.

**Stage 9a2's `oklch coverage` metric does not cover this.** It searches the HTML for the design.md's OKLCH *values* as substrings; it never looks at custom-property *names*, and `src/lib/preview-validator.ts` does not consult the drift gate at all. A fully namespaced preview can score 100% coverage at 9a2 and still match zero declarations here.

**And no gate here looks at WHERE a value is painted.** The drift gate compares a preview's
`--custom-property: oklch(…)` *declaration* against the md's definition of the same name.
`pnpm audit:oklch` compares an OKLCH literal against the hex annotated beside it. Both answer
*"is this value right?"*; neither answers *"is it on the right element?"* — `var(--x)` usage sites
are not scanned by either. remember declared its surface tokens correctly (light 10 and dark 10
matched the design boards 20/20) and painted one of them on six cards where the research had
observed a single 550px column, at `radius-md` where the observation said 4px. Every gate was
unanimous: `audit:oklch` 0 mismatched, the drift gate matched, `validate:previews --slug remember`
0 blocking 0 warning. Checking the application site means opening the research cache or the brand
publication and comparing element by element — the Stage 12 board cross-check's work and a
human's, not a gate's. **Do not read a clean `audit:oklch` as "the preview is faithful".**

Three rule shapes are in use, all measured against real entries:

| md name | preview name | rule |
|---|---|---|
| `blue-500` | `--tds-blue-500` | `["", "tds-"]` — prepend |
| `ldsg-color-linegreen` | `--ldsg-linegreen` | `["ldsg-color-", "ldsg-"]` — replace |
| `gray0` | `--g-gray-0` | `[["gray", "g-gray-"], ["", "g-"]]` — one family differs from the rest |

Rules are tried in order, first match wins, and an empty `from` matches anything so it belongs last.

If the test fails with `these slugs have no entry in MATCH_FLOOR`, add the rule, then record the count the failure message prints into `MATCH_FLOOR` (`src/lib/oklch-drift-corpus.test.ts`) — that table is a per-slug floor, so it also has to be raised deliberately rather than guessed. Recording a bare `0` is refused: only `bezier` is entitled to it, because its preview is hex rather than OKLCH and no naming rule can reach it.

Both files are outside this skill's write scope, so this does not route back to Stage 9a — a human operator running the skill by hand makes these two edits directly. Skipping them does not corrupt the entry; it leaves the drift gate blind to it, and CI fails on the pull request rather than here.

### Token coverage row

The same moment creates a row this entry owes to `src/lib/token-coverage.test.ts`. Run it:

```bash
cd "${repo_root}" && pnpm test src/lib/token-coverage.test.ts
```

That file pins, per entry, how many `name: oklch(…)` definitions each token gate can see — exact in both directions, because a count that rises can mean a reader widened, not that tokens were added. A new entry fails it with `these entries have no row in TOKEN_COVERAGE`, and the message prints the row itself: paste that line into `TOKEN_COVERAGE` at its sorted position, then read it. `drift: 0` is refused (the drift gate would have no md-side name to compare for the whole entry — fix the frontmatter token map instead), while `annotated: 0` can be right (an entry that comments its colours in prose with no hex, as baemin and toss do). Nothing else in the repo prints these numbers, so do not guess them. A row per entry is what lets two catalogue pull requests be open at once without the second one failing on the first one's merge (#324).

This file is outside the skill's write scope too: the operator makes the edit by hand, next to the `MATCH_FLOOR` row above.

### The rest of the per-slug rows

Four more tables owe this entry a row, and none is reachable from this stage — each fails in CI on
someone who never saw it. `CLAUDE.md` 「카탈로그 정책」 carries the full list; the ones not already
covered above are:

- **`BASELINE_TABLE`** (`src/lib/contrast-baseline.ts`) — four rows per slug, mirrored byte for byte
  into `docs/preview-contrast-baseline.md`. `pnpm gate:contrast` prints the rows on failure, and it
  drives a browser, so CI is the authority on the numbers.
- **The `NOTICE` asset inventory** — any file Stage 4a placed under `public/logos/` owes a row.
  `license-notice-consistency.test.ts` compares both directions.
- **The missing-primary list** (`src/lib/google-designmd-corpus.test.ts`) — only when the entry has
  no token literally named `primary`. Do not invent one to avoid the row.
- **`KNOWN_SPEC_LIMITATIONS`** (same file) — only when the entry publishes a `%` radius or a
  multi-stop gradient, the two places the catalog is more expressive than the published spec. It is
  a **two-way ratchet** on the slug's error count, so a later silent fix fails it too. Record the
  count; do not flatten the value to satisfy the linter.

All are outside this skill's write scope: the operator edits them by hand, the same as the two above.

## Stage 11 — Build OG image

```bash
cd "${repo_root}" && pnpm build:og
```

After the command:

**If exit non-zero**: capture stderr. Likely cause is frontmatter that `buildDoc` in `src/lib/content-parser.ts` rejects after slipping past the 6a2 gate (e.g. a hand edit at the Stage 7 checkpoint): a `last_updated` / `created_at` that is not a real `YYYY-MM-DD` date, or an `estimated_tokens` that is not a number. An off-enum category does not fail `build:og` (`buildDoc` falls back to `etc`); once the draft is past 6a2, only `pnpm validate:catalog` catches it, so run it before finishing. Surface stderr via text. Offer via `AskUserQuestion`: "frontmatter 직접 수정 후 재시도" (open `${repo_root}/services/{slug}.md` for editing; on user confirmation that they've edited, re-run `pnpm build:og` and re-validate — loop up to 3 retries), "취소 (파일 유지)" (partial state is acceptable since the index works without an OG image — the route falls back per `build-og.ts`). Do NOT auto-rollback the placed .md. After 3 failed retries, fall through to "취소" with a diagnostic message.

**If exit zero**: validate the OG output (catches the corrupt-PNG silent failure mode that happens on satori panic):

```bash
[ -s "${repo_root}/public/og/{slug}.png" ] || echo "OG_EMPTY"
file "${repo_root}/public/og/{slug}.png" | grep -q PNG || echo "OG_NOT_PNG"
```

If either check prints its sentinel, treat as the same error path as a non-zero exit (surface, ask the user, do not auto-rollback).

## Stage 12 — Verification (preview MCP)

Start the dev server and confirm the new entry renders correctly. This is the strongest end-to-end check.

1. **Port preflight**: `Bash`: `lsof -i :3000 -t 2>/dev/null`. If the output is non-empty, port 3000 is already in use (the user has a dev server running). `AskUserQuestion`: "포트 3000이 사용 중입니다 — (a) 기존 서버 종료 후 재시작 / (b) 검증 단계 건너뛰기 / (c) 취소". On "건너뛰기", skip to Stage 13 with a `verification_skipped: port_collision` flag in the report.
2. `Bash` (run_in_background): `cd "${repo_root}" && pnpm dev` — runs on port 3000.
3. **Server readiness poll**: `Bash`: `for i in $(seq 1 30); do curl -sf http://localhost:3000 -o /dev/null && echo READY && break; sleep 0.5; done`. The dev server takes a few seconds to bind; without this poll, `preview_start` may hit a connection refused before Vite is up. If the loop completes without printing `READY`, fall through to the `curl` fallback at the end of this stage.
4. `mcp__Claude_Preview__preview_start` with URL `http://localhost:3000/services/{slug}`.
5. `mcp__Claude_Preview__preview_eval`: `document.title` — should contain `{brand_name}` and `ko/design.md`. Then confirm the **token-card section** loaded from the Stage 8 sidecar: `preview_eval`: `document.querySelector('[aria-label="Design tokens"]')?.querySelector('p')?.textContent ?? 'MISSING'` — should return the count badge (`{N} Colors · {N} Type · …`). `MISSING` means `services/{slug}.tokens.json` is absent or failed `coerceServiceTokens`; verify it exists and is valid JSON before continuing.
6. `preview_eval` against the iframe: confirm `document.querySelector('iframe')?.src` contains `/preview/{slug}/preview.html`, and that the iframe document's `data-theme` matches the route default (`src/routes/services/$slug.tsx:97`) — one file serves both themes now.
7. `preview_screenshot` once on the default tab.
8. `preview_eval`: navigate to `?tab=md` and confirm DESIGN.md tab renders the syntax-highlighted markdown.
9. `preview_screenshot` once on the `?tab=md` view.
10. **Agent endpoint check**: `Bash`: `curl -sf -o /dev/null -w "%{http_code} %{content_type}\n" http://localhost:3000/services/{slug}/llms.txt` — expect `200 text/plain; charset=utf-8`. This raw-markdown sibling route reads from `services/{slug}.md` directly, so a failure here means either the file wasn't placed correctly or the project's `/services/$slug/llms.txt` route regressed. Surface non-200 output to the user before stopping the server.
11. **Responsive sweep (mobile / tablet / desktop)** — confirm the preview demo doesn't break at narrow widths (the regression class hotfixed in PR #77). Load each demo **top-level**, not through the width-constrained detail-page iframe. Sweep **both themes** of the one file: load it, then run the probe once with `data-theme="light"` and once with `"dark"`. They share layout, but PR #77's lesson is that a fix can miss one theme, and the two scopes can still size text differently. `preview_eval`: `window.location.href = "http://localhost:3000/preview/{slug}/preview.html"`, and set the theme with `document.documentElement.setAttribute('data-theme', '{theme}')` before each probe, then at **375 (mobile) / 768 (tablet) / 976 (detail-page embed width — the historical blind spot where multi-column cells are tightest, see PR #150) / 1440 (desktop)** × 900 run `mcp__Claude_Preview__preview_resize` to `{width} × 900` followed by `preview_eval` of the overflow probe:

    ```js
    (() => {
      const d = document.documentElement;
      const vw = d.clientWidth;
      const overflowPx = d.scrollWidth - vw;
      const broken = overflowPx > 1;
      // Collect culprits only when the document actually overflows, AND skip any element
      // inside an overflow-x: hidden/auto/scroll ancestor: an intentional horizontally-
      // scrollable row (chip row, carousel) reports right > vw without extending the
      // document, so it is not the break even when another element broke the page.
      const culprits = !broken ? [] : Array.from(document.querySelectorAll('body *'))
        .filter(el => {
          const r = el.getBoundingClientRect();
          if (r.right <= vw + 1 && r.left >= -1) return false;
          for (let p = el.parentElement; p && p !== document.body; p = p.parentElement) {
            const ox = getComputedStyle(p).overflowX;
            if (ox === 'hidden' || ox === 'auto' || ox === 'scroll') return false;
          }
          return true;
        })
        .slice(0, 6)
        .map(el => {
          // getAttribute('class') works for SVG too (el.className is an SVGAnimatedString there).
          const cls = (el.getAttribute('class') || '').trim();
          return el.tagName.toLowerCase() + (cls ? '.' + cls.split(/\s+/).slice(0, 2).join('.') : '');
        });
      return { viewport: vw, scrollWidth: d.scrollWidth, overflowPx, broken, culprits };
    })()
    ```

    `broken = overflowPx > 1` (1px tolerance) means a horizontal scrollbar — a broken responsive layout. The check keys on the **document** `scrollWidth`, so an element inside an intentional horizontally-scrollable row (a chip row, a carousel) does not trip it. `culprits` (collected only when `broken`, and excluding any element nested in an `overflow-x` scroll/clip ancestor) lists the genuinely page-extending elements (e.g. `.comp-card`, `.ftile`) so the fix can be targeted. Collect every `broken` result as `breaks[] = {file, width, overflowPx, culprits}`.

    **Auto-fix loop** (≤ 2 attempts) when `breaks` is non-empty — reuses the Stage 9a dispatch and the Stage 10 copy, so there is no new mechanism:
    1. Write a synthetic review at `{cache_dir}/preview-review-resp-{attempt}.json` whose `issues[]` carries one `severity: "block"` entry per break: `{"severity":"block","section":"responsive — {theme} @{width}px","fix":"Horizontal overflow {overflowPx}px at {width}px. Offending: {culprits}. Repair per the author's Responsive & mobile-overflow guard — the usual root cause is a bare 1fr grid track flooring at its content min-content, so switch content tracks to minmax(0, 1fr), add a mobile grid-collapse @media rule, and put min-width: 0 on items wrapping fixed-width children. A layout fix belongs in the shared rules, not duplicated per theme scope."}`.
    2. Dispatch `preview-html-author` exactly as in **Stage 9a**, with `prior_review_path` = that JSON. The author rewrites `{cache_dir}/preview.html`.
    3. Re-copy staging → public with the **Stage 10** `cp` commands (the Stage 10 logo deterministic check still applies).
    4. `preview_eval`: `window.location.reload()` (the `/preview/*` `no-cache` header serves the fresh file), then re-run the sweep.
    Stop when `breaks` is empty or after 2 attempts.

    **Result**: if `breaks` is empty → `responsive_result = ok` (record the attempt count). If still non-empty after 2 attempts → `preview_screenshot` at the narrowest failing width for evidence and set `responsive_result = warn` with the residual `breaks`. Non-blocking either way (consistent with the non-blocking preview loop). The OG image is derived from design.md, so re-fixed previews do **not** trigger an OG rebuild. (The port-collision path never reaches this step — it returns to Stage 13 at step 1 — so handling for that case lives in the Stage 13 report, not here.)
12. **Design-board cross-check (conditional)** — run when `design_board_paths` from Stage 2 is non-empty; otherwise set `board_result = skipped (no board)` and go to step 13. Stage 4c approved the board *before* anything was generated; this is the other half of that gate — the finished preview measured back against it. The question is **not whether the values are right**. `pnpm audit:oklch` and the drift gate already answered that, and on `remember` they answered it correctly: the board's twenty role colors reached the preview 20/20 unchanged. The question is **where each value landed**, which no gate in this pipeline asks — see **Preview token alias registration** in Stage 10, where that blind spot is stated against `audit:oklch` and the drift gate.

    `Read` the board frames from `design_board_paths` again. The preview is still loaded top-level from step 11; `preview_resize` back to `1440 × 900` and run this probe once per theme, setting `data-theme` the same way step 11 does:

    ```js
    (() => {
      const seen = new Map();
      for (const el of document.querySelectorAll('body *')) {
        const r = el.getBoundingClientRect();
        if (r.width < 4 || r.height < 4) continue;
        const cs = getComputedStyle(el);
        for (const prop of ['backgroundColor', 'color', 'borderTopColor']) {
          const v = cs[prop];
          if (!v || v === 'transparent' || v === 'rgba(0, 0, 0, 0)') continue;
          const key = prop + ' ' + v;
          const bucket = seen.get(key) ?? [];
          const cls = (el.getAttribute('class') || '').trim();
          bucket.push({
            el: el.tagName.toLowerCase() + (cls ? '.' + cls.split(/\s+/).slice(0, 2).join('.') : ''),
            w: Math.round(r.width),
            h: Math.round(r.height),
            radius: cs.borderRadius,
          });
          seen.set(key, bucket);
        }
      }
      return [...seen]
        .map(([k, v]) => ({ k, count: v.length, sample: v.slice(0, 3) }))
        .sort((a, b) => b.count - a.count);
    })()
    ```

    Buckets are keyed on the **serialized computed string, whatever the browser emits for it** — Chromium keeps `oklch()` colors in their own space rather than converting to `rgb()`, and that format is not stable across versions. You are matching buckets to board tokens by reading them, not by string-comparing against the md, so the format does not matter.

    For each token the board defines, check three things against the board frame and `{cache_dir}/research.md`: **which element carries it**, **how many of them**, and **that element's radius and box size**. A discrepancy is a token whose bucket disagrees on any of the three. That is exactly the shape of the only thing this comparison has ever caught — on `remember` one surface color was painted on **six** cards where the research had observed a single **550px** column, at `radius-md` where the observation said **4px**, while every gate was green.

    **Record, do not auto-fix.** Set `board_result = ok` when no bucket disagrees, or `board_result = discrepancies` carrying one line per finding (`{token} — 보드/관측: {expected}, 프리뷰: {observed}`). Do not route back into the Stage 9a loop the way the responsive sweep does: that loop's input is a layout rule the author can apply blind, whereas this finding is a judgment about a brand publication the author cannot see, and a wrong auto-fix repaints a correct value onto a different wrong element. Stage 13 reports it and the person decides.

13. **Stop the dev server**: `Bash`: `kill $(lsof -t -i:3000) 2>/dev/null || true`. Killing by port is portable across macOS/Linux and avoids accidentally killing other `pnpm` processes the user might be running. The `|| true` keeps the skill from aborting if the process already exited.

If preview MCP tools are unavailable, fall back to `Bash`: `curl -sf http://localhost:3000/services/{slug} | grep -q '<iframe'` — non-zero exit means the page failed to render. The responsive sweep (step 11) requires the preview MCP tools; without them, note `responsive_result = skipped (no preview MCP)` in the report, and the board cross-check (step 12) the same way as `board_result = skipped (no preview MCP)`.

## Stage 13 — Final report and cleanup

Print a summary message containing:

- Files written (with absolute paths):
  - `services/{slug}.md`
  - `services/{slug}.tokens.json` (visual design-token sidecar → detail-page card view)
  - `public/preview/{slug}/preview.html`
  - `public/og/{slug}.png` (from `pnpm build:og`)
- Surfaced URLs (paths only — host depends on env):
  - `/services/{slug}` — HTML detail page (Live Preview · Tokens · DESIGN.md tabs; the Tokens tab appears only when the sidecar carries tokens).
  - `/services/{slug}/llms.txt` — raw `text/plain` design.md (frontmatter + body) for LLMs / agents to fetch directly. Discoverable via `<link rel="alternate" type="text/plain">` on the HTML page.
- Final review scores: design `{score}/10`, preview `{score}/10`.
- Screenshots taken during verification (paths or inline).
- Responsive verification (Stage 12 sweep) — pick the line by state:
  - `responsive_result = ok` → `반응형: ✅ 375/768/976/1440 가로 오버플로 없음 (자동수정 {attempts}회)`
  - `responsive_result = warn` → `반응형: ⚠️ 잔여 오버플로 — {file} @{width}px {overflowPx}px, 요소 {culprits} (스크린샷 {path}, 자동수정 2회 후 잔존)`
  - skipped — set when `verification_skipped: port_collision` (step 1 returned early, so `responsive_result` was never assigned) **or** `responsive_result = skipped` (preview MCP unavailable) → `반응형: ⏭ 검증 건너뜀 (포트 충돌 / preview MCP 없음)`
- Design-board cross-check (Stage 12, after the responsive sweep) — pick the line by state:
  - `board_result = ok` → `보드 대조: ✅ 보드 토큰의 적용 위치·개수·형상이 관측과 일치`
  - `board_result = discrepancies` → `보드 대조: ⚠️ 적용 위치 불일치 {N}건 — {finding 한 줄씩}`
  - `board_result = skipped (no board)` → `보드 대조: ⏭ 보드 없음 — 공개 자료만으로 만든 항목이라 대조할 상류가 없습니다`
  - `board_result = skipped (no preview MCP)`, or step 1 returned early on `verification_skipped: port_collision` so `board_result` was never assigned → `보드 대조: ⏭ 검증 건너뜀 (포트 충돌 / preview MCP 없음)`

  **No two of the four may print the same line** — that is what the contract test pins. Three of them are where it actually happens: `discrepancies` carries a ⚠️ and is never mistaken for silence, while the other three all look like nothing-to-see. "보드가 없었다" · "대조했고 어긋난 것이 없었다" · "대조가 아예 안 돌았다" 는 서로 다른 사실이고, 이 저장소에서 반복적으로 같은 침묵으로 보고돼 왔다. 특히 `skipped` 를 침묵으로 처리하면 사람은 초록으로 읽는다.
- Leftover TODOs:
  - If the logo values are empty: "Logo asset: `public/logos/{slug}.svg|png|webp|avif` 가 아직 없습니다. 직접 추가한 뒤 frontmatter `logo: https://getdesign.kr/logos/{slug}.{ext}` (절대 URL, 외부 복사 대비) 를 채우고 preview HTML에는 `<img src=\"/logos/{slug}.{ext}\">` (site-relative, iframe 전용) 형식으로 렌더링하세요."
  - **Every `warn` in the final preview review, whatever the score.** The rubric's three advisory sections — `Mobile overflow`, `Dummy-data labelling`, `Explanatory prose` — add no points by design, so a preview can carry all of them and still pass 9c's `score >= 8` on the first iteration and exit without the author ever seeing the review. Reporting them only when iteration 3 fell short drops them in exactly the case they exist for: `remember` scored 10/10 with 61% of its rendered text restating the design.md. List each one's `section` and `fix` verbatim. If the list is empty, say so — an absent line reads as "none found" whether or not the check ran.
- **What is left for the person to look at.** Close the report by saying the loops are already done — the draft gate and review (6a2/6b), the preview gate and review (9a2/9b) and the Stage 12 sweep have all run — and then name what they do not cover, so the user spends their pass on the residue instead of re-checking what a machine just checked. On `remember` every gate was green when the user found four things: the preview was more than half explanat

[
  {
    "query": "토스를 ko-design-md 카탈로그에 추가하고 싶어. design.md랑 preview HTML 만들어줘. https://toss.im 참고로",
    "should_trigger": true
  },
  {
    "query": "Stripe의 design system을 catalog에 등록해줘. 참고 URL은 stripe.com/customers",
    "should_trigger": true
  },
  {
    "query": "당근의 디자인 시스템 정리해서 catalog에 새 항목으로 만들어줄 수 있어? screenshot 4장 있어 — ~/Desktop/karrot-1.png부터 4까지",
    "should_trigger": true
  },
  {
    "query": "ko-design-md에 Linear 추가하자. linear.app, lang ko, category content 정도?",
    "should_trigger": true
  },
  {
    "query": "쿠팡으로 새 design.md 만들어야 해. 자료조사부터 preview까지 한 번에 가자. category는 commerce",
    "should_trigger": true
  },
  {
    "query": "/design-md",
    "should_trigger": true
  },
  {
    "query": "this brand isn't in our catalog yet — can you onboard them? brand: notion, urls: notion.so, notion.so/blog",
    "should_trigger": true
  },
  {
    "query": "넷플릭스 카탈로그 등록 진행. services/{slug}.md 자동으로 만들어주는 그거",
    "should_trigger": true
  },
  {
    "query": "Spotify를 추가하려는데 design.md 자동 생성하는 워크플로우 있다고 했지? 그거로 해줘",
    "should_trigger": true
  },
  {
    "query": "services/baemin.md의 typography 섹션 한 줄만 고쳐줘 — 'Pretendard'를 'Pretendard Variable'로",
    "should_trigger": false
  },
  {
    "query": "design.md 파일 형식이 뭔지 설명해줘. Google Stitch에서 만든 거 맞아?",
    "should_trigger": false
  },
  {
    "query": "services/toss.md의 last_updated를 오늘 날짜로 갱신만 해줘",
    "should_trigger": false
  },
  {
    "query": "preview HTML의 dark mode에서 contrast가 부족해 보이는데 토큰 값 좀 봐줘 — public/preview/demo-courier/preview.html",
    "should_trigger": false
  },
  {
    "query": "src/routes/index.tsx에 카테고리 필터 사이드바 추가해줘. 기존 스타일 따라서",
    "should_trigger": false
  },
  {
    "query": "build:og 스크립트가 NaN 에러 내면서 실패해. 디버깅해줘. scripts/build-og.ts 봐주면 됨",
    "should_trigger": false
  },
  {
    "query": "내 다른 사이드프로젝트(설계 시스템 카탈로그 비슷한 거)에서도 design.md 같은 거 쓰고 싶은데 어떻게 시작해야 해?",
    "should_trigger": false
  },
  {
    "query": "design.md 잘 쓰는 법 가이드 같은 거 있어? 책이나 블로그 추천해줘",
    "should_trigger": false
  },
  {
    "query": "Stripe design.md 파일을 다운로드해서 우리 프로젝트 docs/ 폴더에 참고 자료로 가져다 놔줘",
    "should_trigger": false
  },
  {
    "query": "services/toss.md를 services/toss-copy.md로 이름 바꿔서 복제해줘. 내용은 그대로",
    "should_trigger": false
  },
  {
    "query": "ko-design-md 프로젝트 README에 카탈로그 항목 추가하는 방법 한 단락 적어줘",
    "should_trigger": false
  }
]