Przejdź do treści
Biblioteka skilli
Projektowanie i UX · Research

reference-intelligence

/reference-intelligence

Pozyskuje prawdziwe referencje projektowe z Awwwards, Mobbin i MotionSites, mierzy ich DNA projektowe i składa Reference Board w .sumi/refs/ do budowy i oceny kolejnych prac.

Repozytorium
sumi ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
24.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
7
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
2
Przestarzałość

Brak sygnałów. Repozytorium zmienione 24.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Pozyskuje prawdziwe referencje projektowe z Awwwards, Mobbin i MotionSites, mierzy ich DNA projektowe i składa Reference Board w .sumi/refs/ do budowy i oceny kolejnych prac.

Wyzwalacze z opisu

make it look likesites likeaward-winningbest in class
Oryginalny opis (EN)

Sources REAL design references instead of recalling them — award-winning live sites from Awwwards, app screens and flows from Mobbin (MCP), motion recipes from MotionSites (MCP) — captures them, measures their design DNA (type, color, spacing, grid, radius, motion stack), and synthesizes a Reference Board in .sumi/refs/ that every MAKE and REVIEW command builds and grades against. Use when the user mentions: inspiration, inspo, references, reference sites, moodboard, Awwwards, SOTD, site of the day, Mobbin, MotionSites, 'make it look like', 'sites like', 'award-winning', 'best in class', examp

Jak działa

  1. Source routing
  2. Non-negotiables
  3. Running the scripts
  4. Output: .sumi/refs/
  5. Related skills
Sekcje z nagłówków SKILL.md, w oryginale · 93 linii, 726 słów
Podgląd SKILL.md
---
name: reference-intelligence
description: "Sources REAL design references instead of recalling them — award-winning live sites from Awwwards, app screens and flows from Mobbin (MCP), motion recipes from MotionSites (MCP) — captures them, measures their design DNA (type, color, spacing, grid, radius, motion stack), and synthesizes a Reference Board in .sumi/refs/ that every MAKE and REVIEW command builds and grades against. Use when the user mentions: inspiration, inspo, references, reference sites, moodboard, Awwwards, SOTD, site of the day, Mobbin, MotionSites, 'make it look like', 'sites like', 'award-winning', 'best in class', examples of, what are the best sites for, reference board, steal like an artist, benchmark against real sites."
---

# Reference Intelligence — look before you design

Every other Sumi skill encodes taste from memory. This one goes and **looks**. A
senior studio doesn't design a fintech landing page from recollection; it pulls
ten current winners onto a wall, pulls them apart, agrees what to steal, builds,
then pins the build next to the wall and asks whether it belongs there.

That loop has four steps and Sumi owns all of them:

| Step | What happens | Where it lives |
|------|--------------|----------------|
| **Scout** | Find 8-12 candidates from real sources | `scripts/awwwards.mjs`, Mobbin MCP, MotionSites MCP |
| **Capture** | Screenshot the LIVE sites and measure their DNA | `scripts/capture.mjs` → `.sumi/refs/<slug>/` |
| **Board** | Synthesize what to steal / avoid into one direction | `.sumi/refs/board.md` + `board.json` |
| **Compare** | Grade a build side by side with the board | `critic` agent, `/grade`, `/roast` |

## Source routing

| The ask is… | Primary source | Secondary |
|-------------|----------------|-----------|
| Marketing site, landing page, portfolio, brand, campaign | **Awwwards** | MotionSites for motion recipes |
| App screen, dashboard, settings, product UI | **Mobbin** | Awwwards `app-style` / `ui-design` tags |
| A flow (onboarding, checkout, signup, paywall, search) | **Mobbin** (flows) | — |
| Motion, scroll storytelling, WebGL, transitions | **Awwwards** (`gsap`, `three-js`, `webgl`, `transitions`, `scrolling`) | **MotionSites** |
| "Make it look like <url>" | That URL, straight into `capture.mjs` | Awwwards category of that site |

Adapters, one per source:
- `references/awwwards-adapter.md` — listings, the 192 category tags, sector → tag map, etiquette
- `references/mobbin-adapter.md` — MCP auth, query shapes, what may be stored
- `references/motionsites-adapter.md` — prompt library, free-tier limit, upgrade message rule
- `references/dna-schema.md` — what `capture.mjs` measures and how to read it
- `references/board-synthesis.md` — combining references without cloning one; `board.json` schema
- `references/comparison-protocol.md` — how the critic grades a build against the board

## Non-negotiables

1. **Real, not recalled.** A reference must be a URL that was fetched this session (or a cached
   fetch under `.sumi/refs/`), a Mobbin result from the MCP, or a MotionSites prompt. Never
   present a site as an Awwwards winner from memory.
2. **Capture the live site, not the thumbnail.** Awwwards and Mobbin are indexes. The DNA comes
   from the site itself.
3. **One script call, not click-by-click browsing.** Capture runs as ONE `node scripts/capture.mjs`
   invocation over all picks. Never drive puppeteer/Chrome MCP step by step to study a site.
4. **Small and on-demand.** 8-12 candidates per run, 3-5 kept. No bulk crawling of Awwwards;
   reuse a cached listing under `.sumi/refs/` if it is under 7 days old.
5. **Steal traits, never layouts.** The board takes at most ONE signature trait from each
   reference (see `board-synthesis.md`). A build that is recognisably one reference is a fail.
6. **Screenshots stay local.** Third-party captures are study material. Suggest adding
   `.sumi/refs/**/*.jpg` to `.gitignore`; never publish or deploy them.
7. **The user curates.** Present the shortlist and let them keep 3-5. Art direction is a choice,
   not a computation.

## Running the scripts

Scripts live in the plugin, not the project. Resolve the plugin root once:

```bash
SUMI="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(find ~/.claude/plugins -path '*sumi*/scripts/capture.mjs' -print -quit)")")}"
node "$SUMI/scripts/awwwards.mjs" technology --awarded --limit 10 --out .sumi/refs/awwwards-technology.json
node "$SUMI/scripts/capture.mjs" --from .sumi/refs/awwwards-technology.json --pick slug-a,slug-b,slug-c
node "$SUMI/scripts/capture.mjs" https://linear.app https://stripe.com   # direct URLs
```

`capture.mjs` needs `puppeteer-core` (resolved from the project, `$SUMI_PUPPETEER_DIR`, or known
sibling projects) and a local Chrome. It takes ~40-60s per site (desktop + phone, scroll steps).
Run it in the background for more than 3 sites.

## Output: `.sumi/refs/`

```
.sumi/refs/
├── awwwards-<listing>.json   # scout results (cache)
├── mobbin.json               # Mobbin picks: app, screen/flow, url, why
├── motion.json               # MotionSites prompts used
├── <slug>/dna.json           # measured DNA, desktop + phone
├── <slug>/desktop-0..3.jpg   # scroll-step captures
├── <slug>/phone-0..2.jpg
├── board.md                  # human-readable Reference Board
└── board.json                # machine-readable direction every command consumes
```

`board.json` is the contract. `/style` turns its `direction` into tokens and its references
into the `references` array of `.sumi/style.json` (per `design-memory`, only `/style` writes
that file). `/page`, `/screen` and `/component` build against it; `/grade` and `/roast`
compare against it.

## Related skills
- `visual-design-mastery` — the 10-dimension scoring the comparison uses
- `screen-flow-patterns` — the screen/flow taxonomy used to phrase Mobbin queries
- `sector-style-intelligence` — sector norms; its "Inspiration Links" seed Mobbin queries
- `interaction-motion-design`, `animation-recipe-library` — translating captured motion stacks into code
Pliki w paczce (7)
  • SKILL.md 6 KB
  • references/awwwards-adapter.md 4 KB
  • references/board-synthesis.md 5 KB
  • references/comparison-protocol.md 3 KB
  • references/dna-schema.md 4 KB
  • references/mobbin-adapter.md 3 KB
  • references/motionsites-adapter.md 1 KB

Wersje

W bazie nie ma innych skilli o nazwie reference-intelligence.

Migawka bazy z 13.11.2026 · wersja paczki cafef0f0148d (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 90mobbin-research
    Prowadzi badania inspiracji designem z biblioteki ekranów Mobbin przez MCP: referencje, audyt brakujących ekranów i przepływów.
  • 100awwwards-inspiration
    Szuka referencji designu i inspiracji w nagrodzonych stronach, np. e-commerce czy brutalizm, i obsługuje lokalny indeks.
  • 100mobbin-design-research
    Prowadzi badania projektowe w Mobbin, analizując przepływy i komponenty innych aplikacji, by poprawić ekran.
  • 100design-dna
    Wyciąga abstrakcyjny plan wizualny i ruchowy (design DNA) ze stron referencyjnych lub szuka nagradzanych referencji po opisie nastroju, wyłącznie obserwując i abstrahując.
  • 100design-inspiration
    Szuka referencji wizualnych w galeriach i buduje samodzielny moodboard HTML z obrazów lub krótkich filmów, np. z Pinteresta czy Behance.
  • 100studio-research
    Przygotowuje brief strony, audytuje konkurencję i zbiera referencje z galerii projektów, z uzasadnieniem każdej pozycji.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.