Ss Dial

Dial an axis

Registry-first artifact boundary

When .styleseed/project.json and .styleseed/artifacts/index.json exist, resolve the requested artifact ID first, then read only .styleseed/bundles/<artifact-id>.md and .styleseed/manifests/<artifact-id>.json. Never fall back to the global legacy bundle for a registry project. Legacy projects may use .styleseed/effective-rules.md only when no registry exists.

"Make it more minimal" is something you can just say — the model already reads plain language. A skill only earns its place where one word must move many tokens at once, in a coordinated way, without breaking a rule — and where doing it by hand gives an inconsistent result (some tokens changed, the grid broken, a second accent introduced). That's what /ss-dial is: not interpretation, but a deterministic ramp + guardrails + re-gate.

If the request is a mood word ("more premium", "more editorial", "more playful"), that's not one axis — it's a combination of positions across several axes. Use `/ss-restyle <preset>` for those. /ss-dial moves exactly one axis.

When NOT to use

• A vague vibe the model can just apply from words ("cleaner", "nicer") → don't wrap it in a skill; say it.
• A named aesthetic (Swiss / editorial / brutalist) → /ss-restyle (a preset of dial positions).
• Changing the accent hue itself (rebrand) → edit the lock's Key color directly, then re-derive.
• No STYLESEED.md lock yet → run /ss-build or /ss-setup first; there's nothing to dial from.

The mechanic (every axis)

1. Read `STYLESEED.md` — find the axis's current position (Mood/Density/Radius/Elevation/ Type scale/Font weight/Motion fields). If the lock doesn't record it, infer it from the code.
2. Move ONE position in the requested direction on that axis's ramp (below). "more X" = one step; an explicit target ("density: dense") jumps straight there. Clamp at the ends — you cannot dial past dense or below airy. If already at the end, say so and stop (this is why "each use makes it more" is bounded, not runaway).
3. Apply the whole coordinated token set for the new position across every file that uses those tokens — not just the one component in view. This is the point: system-wide, consistent.
4. Respect the guardrails (each axis lists its own). Never break a Golden Rule to satisfy a dial — if "denser" would push a touch control below 44px, stop at the floor and note it.
5. Update `STYLESEED.md` with the new position (so it persists and the next prompt obeys it).
6. Re-run the Quality Gate (/ss-score, loop to ≥ 80). A dial that drops the score below 80 is reverted or fixed, not shipped. Report: axis, old → new position, score.

The axes

1. Density — spacing rhythm + internal padding + type/line-height, together

Ramp: airy → comfortable → compact → dense. The page gutter stays px-6/mx-6 always (fixed rule); density moves the vertical rhythm, card interior, and reading scale.

Guardrails: stay on the 8px grid (only p-2/4/6/8, gap-* on grid or the 4px half-step — never invent p-5/gap-2.5); touch controls stay ≥ 44px even at `dense` (shrink padding, not tap targets); body never drops below the surface floor (desktop 16px). Dense is for data-heavy surfaces; don't dense-ify a marketing landing.

2. Hierarchy contrast — the size/weight gap between levels

Ramp: subtle → balanced → strong → dramatic. Moves the ratio between the hero and the body, plus display tracking.

Guardrails: pick sizes from the Font Size table only (don't invent); body stays at the surface floor regardless; keep the number-to-unit 2:1 pairing intact; one focal element still dominates (dialing contrast up must not create two competing heroes).

3. Radius — the corner personality (categorical swap, not a slider)

Ramp: sharp ↔ soft ↔ pill. Swaps the whole mapping table as one set, never one component.

Guardrails: one personality everywhere (sharp cards + pill buttons is the exact mixed-personality tell we ban); nested elements still follow inner = outer − padding.

4. Elevation / depth — how surfaces separate

Ramp: flat → subtle → layered → lifted. Light and dark speak different languages — apply the one that matches the theme.

Guardrails: never exceed ~8% shadow opacity in light; never a drop shadow in dark (use the tonal surface ramp + hairline borders); one shadow language / one light direction across the whole UI.

5. Color — saturation and temperature (two sub-dials, accent stays single)

saturation: muted ↔ balanced ↔ vivid · temperature: cooler ↔ neutral ↔ warmer. Shifts the one accent in HSL and re-derives its tints; may nudge the neutral greys' chroma. Does NOT add a hue.

Guardrails: still one accent — this shifts the existing hue, never introduces a second; tints follow the 10–14%-alpha-over-card formula (light + dark); accent keeps ≥4.5:1 where it carries text; a warm/cool grey shift must stay near-neutral (chroma ≤ ~6%), not become a tint.

6. Font weight — the weight ramp

Ramp: light → regular → bold. Shifts the whole weight scale up/down by one notch, keeping the spread (so hierarchy survives).

Guardrails: keep contrast between levels (don't make everything one weight — that flattens hierarchy); body ≤ 500 for readability at length; CJK weight does the work tracking can't.

7. Motion energy — seed + durations

Ramp: still → calm → lively → energetic. Swaps the motion seed and scales durations globally.

Guardrails: numbers, balances, and money never animate at any level; always honor