@genex-ai/cli-demo 0.84.0-dev.215 → 0.85.0-dev.216

package/templates/skills/genex-threejs-game-ui/SKILL.md

@@ -71,66 +71,62 @@ and how the space reads (route, scale) — plus the brief's palette,
 materials, and light. A beautiful empty vista with nothing to fight and
 nowhere to go is a FAILED concept; so is one that invents mechanics the
 game doesn't have (a lap counter in a game without laps). Generate it
-`--size 2560x1440 --quality high --candidates 2 --no-wait`, enqueued FIRST
-of all art; the picked candidate's URL goes into the style-brief comment.
-
-**Describe the concept, show it, then get a YES before the style-dependent
-work fans out.** First lay the concept out in WORDS — the playable moment
-(the verb), what threatens the player, what they chase, how the space reads,
-and the brief's palette / materials / light / references — so the user is
-weighing a stated direction, not guessing at a picture. Generate the mockup
-FIRST of all art (`--candidates 2`) and get it in front of the user AS FAST
-AS POSSIBLE: pick the stronger candidate yourself, pick it up with
-`genex wait <id> --open` (or generate it with `--open`) so it opens in the
-user's browser AND prints the links, and paste BOTH candidates' URLs as
-clickable links saying which one you picked and why — a URL is invisible in a
-terminal, and "do you like it?" with no picture in front of the user is the
-#1 way this checkpoint fails (they end up digging logs for the file path).
-
-**Then ask for the yes with your question tool** — the one that shows the
-user clickable options; a short numbered list in chat only where there is
-none. ONE question — "this is roughly
-how the game and its HUD will look — keep this direction, or change
-something?" — with concrete keep / change options. This confirmation is
-REQUIRED for every game: the concept sets the STYLE every later asset
-inherits, so the user gets a real say before that style is committed. This
-reverses the old "advisory, never gate" rule — the concept now gates, but
-ONLY the style-dependent work (below), never the whole build.
-
-**The yes gates the STYLE-DEPENDENT work — nothing else.** Until the user
-approves a frame, do NOT fan out the art or subagents that build ON the
-chosen look: the HUD Stage-2 deconstruct (from the picked candidate), the
-menu still + video (`--edit`-anchored to the mockup), and the logotype. (The core asset set — hero model, ground texture, skybox,
-sfx — is prompted from the game IDEA, not the picked image, and mostly
-survives a style change, so it does NOT wait: launch it up front with
-placeholders, re-rolling only the few that don't survive if the look shifts.)
-Everything else that does NOT depend on the look
-keeps moving at full speed IN PARALLEL — the scaffold and boot wiring, the
-core gameplay / network loop, the controller, and the gameplay-LOGIC subagent
-modules (world, quests, enemies, items — their structure comes from the
-contract, not the picture). The wait is therefore never idle: a slow-to-answer
-user still gets a walkable first version, and the instant they say yes the
-style pipeline launches against the frame they approved. (A user who vanishes
-entirely leaves the LOOK pending, not the game — the deliberate trade for
-never committing a style behind their back.)
+`--size 2560x1440 --quality high --no-wait`, enqueued FIRST of all art —
+ONE image, no candidate variants unless the user asks; its URL goes into
+the style-brief comment.
+
+**Describe the concept in words while it renders.** Lay it out in chat —
+the playable moment (the verb), what threatens the player, what they chase,
+how the space reads, and the brief's palette / materials / light /
+references — so the user is weighing a stated direction, not guessing at a
+picture.
+
+**The moment the mockup lands, the style chain fires — then the user sees
+the frame.** In this order, no waiting between the steps: decide the HUD
+lane as art director and record the `HUD lane:` line in DESIGN.md
+(`$genex-game-director` §5 owns the criteria), enqueue the style-dependent
+chain `--no-wait` — the HUD Stage-2 deconstruct (from the mockup), the menu
+still (`--edit`-anchored to it), and the logotype — and THEN show the frame:
+pick it up with `genex wait <id> --open` (or generate with `--open`) so it
+opens in the user's browser AND prints the link, and paste the URL as a
+clickable link — a URL is invisible in a terminal, and "do you like it?"
+with no picture in front of the user is the #1 way this checkpoint fails.
+
+**Ask keep-or-change with your question tool — as INFORMATION, never a
+gate.** The one that shows clickable options; a short numbered list in chat
+only where there is none. ONE question — "this is roughly how the game and
+its HUD will look — keep this direction, or change something?" — with
+concrete keep / change options. The chain is already running while they
+read it: silence means the concept stands; nothing except the menu VIDEO
+ever waits for the answer. The user still gets a real say — a "change" at
+any time loops the concept with their notes at image prices (below). The
+menu video (the one expensive item) fires at the FIRST of: the user's yes ·
+the next `genex preview` after the menu still landed · style work being the
+only work left — and never while a user objection is open
+(`$genex-ai-menu` owns the trigger). (The core asset set — hero model,
+ground texture, skybox, sfx — is prompted from the game IDEA, not the
+image, and mostly survives a style change: launch it up front with
+placeholders. Everything style-independent — scaffold, boot wiring, the
+core loop, the gameplay-LOGIC subagent modules — keeps moving at full speed
+in parallel throughout.)
 
 **Change reopens the loop, same shape.** If the user picks "change" — or
 comes back with notes immediately or an hour later — re-run Stage 1 (the
-concept mockup itself) with their exact notes (`--candidates 2–3` gives them
-options to choose from), open + link the new frame, and ask again the same
-structured way. Carry every note forward so each round compounds; if two
-rounds don't converge, offer 2–3 distinct directions instead of re-rolling
-blind. Each frame the user approves becomes the working style, and the
-style-dependent pipeline stays gated on the latest yes (strictly CHEAPER than
-it used to be: one image carries scene + HUD, there is no separate concept to
-redo). When the style actually changes after downstream art already ran,
-re-anchor it: the menu still is re-edited (`--edit`) against the new mockup
-and its video re-run once from the new still (`$genex-ai-menu` — a
-user-driven style change re-opens its one-video rule), and the HUD deconstruct
-(Stage 2 onward, `$genex-ai-hud`) restarts from the new mockup. Style-neutral
-assets (most textures, sfx, models) usually survive — judge each in one line.
-The same "open it + paste the link" rule covers every image the user weighs
-in on — the menu still, the HUD mockup candidates.
+concept mockup itself) with their exact notes, open + link the new frame,
+ask again the same structured way, and re-run the cheap chain from the new
+frame (image-priced — that is the design: the correction lane is cheap
+because the expensive item waited). Carry every note forward so each round
+compounds; if two rounds don't converge, offer 2–3 distinct directions
+(that's the one moment `--candidates` earns its place) instead of
+re-rolling blind. Each standing frame is the working style. When the style
+changes after downstream art already ran, re-anchor it: the menu still is
+re-edited (`--edit`) against the new mockup and its video re-run once from
+the new still (`$genex-ai-menu` — a user-driven style change re-opens its
+one-video rule), and the HUD deconstruct (Stage 2 onward, `$genex-ai-hud`)
+restarts from the new mockup. Style-neutral assets (most textures, sfx,
+models) usually survive — judge each in one line. The same "open it + paste
+the link" rule covers every image the user weighs in on — the menu still,
+the HUD mockup.
 
 **The concept anchors STYLE, not truth.** Palette, materials, light, and
 register come from the frame; CONTENT comes from the game contract. This
@@ -165,13 +161,16 @@ rule explicitly does not apply to this one message):
 ```
 UI plan
 • Screens: <list with tiers — loader / menu / pause (Esc) / win/lose / …>
-• Style: <4–5 named hues> · fonts <display> / <body>
+• Style: <4–5 named hues> · fonts <display> / <body> (from $genex-ai-menu's
+  genre table, or a one-line reason)
 • References: <2–3 AAA games — one line on what's borrowed>
 • Menu: <archetype + button treatment, one-line reason from the brief>
-• Concept (HUD mockup): <generation id — 2 candidates> — awaiting your keep / change
-• Queued ON YOUR YES (style-dependent): HUD sheet (Stage 2, from the picked
-  mockup) · menu still → video <or "no menu: reason"> · logotype <or
-  "skipped: reason">
+• HUD lane: <sprites (…) | CSS (…, one-line justification)> — recorded in DESIGN.md
+• Concept (HUD mockup): <generation id> — shown for keep / change
+  (informational — the chain below is already queued; silence = it stands)
+• Queued on concept landing: HUD sheet (Stage 2) · menu still · logotype
+  <or "skipped: reason">; menu VIDEO waits for: your yes / the next preview
+  after the still lands / style work being all that's left <or "no menu: reason">
 • Building now (style-independent): <core loop · logic modules already moving>
 • Deferred from mockup: <widgets the image invented but the game lacks — or "none">
 ```
@@ -190,8 +189,9 @@ A message missing any line means the gate did not run — go back and run it.
   every game), and the generated **logotype** — one `--transparent` wordmark
   in the brief's display register (`$genex-ai-menu`'s logotype step), default
   YES for every game with a menu; skipping it needs a one-line stated reason.
-  Enqueue this chain the instant the user approves the concept
-  (`--no-wait`) — it is style-dependent, so it waits on the yes — then
+  Enqueue this chain the instant the concept mockup LANDS (`--no-wait`) —
+  the keep/change answer never gates it; only the menu VIDEO waits, for its
+  event triple (`$genex-ai-menu`) — then
   keep building, pick results up with `npx genex wait <id>`, swap them in as
   they land. **Tier 2 must never block a playable v0 — but the game is NOT
   DONE until its Tier-2 assets have landed and been wired in** (the only
@@ -200,7 +200,9 @@ A message missing any line means the gate did not run — go back and run it.
   Run `npx genex wait` on every enqueued ID before any publish and before
   the final handoff of a session — never park landed assets for "later".
   Shipping the placeholder CSS HUD as the final HUD is a failure, not a
-  tier choice.
+  tier choice — the ONE exception is a DESIGN.md-recorded `HUD lane: CSS`
+  decision (`$genex-game-director` §5), where the CSS build, finished to
+  its brief, IS the production HUD.
 - **Tier 3 — offer, don't build.** Video layers over the HUD, 9-slice panel
   sprites, animated menu sprites. Offer in one line
   after the player has seen Tier 1+2 working; build on request.
@@ -522,11 +524,13 @@ architecture and consume the shared style brief.
 - Hard-cut phase swaps, a menu whose elements just appear, numbers that
   teleport.
 - A silent menu; a bare "Loading…" over black.
-- Style-dependent art fanned out before the user approved the concept — the
-  concept confirmation is REQUIRED and gates the look-dependent work (HUD
-  Stage 2, menu still/video, logotype, style-matched assets); OR the whole
-  build stalled waiting on that yes, when concept-INDEPENDENT work (scaffold,
-  core loop, logic subagents) must keep moving in parallel while it is pending.
+- The style chain parked behind the keep/change question — the HUD Stage-2
+  sheet, menu still, and logotype enqueue the moment the mockup LANDS, and
+  silence means the concept stands; OR the menu VIDEO fired while a user
+  objection was still open (its event triple is the only wait in the lane);
+  OR the whole build stalled on the concept at all, when concept-INDEPENDENT
+  work (scaffold, core loop, logic subagents) must keep moving in parallel
+  throughout.
 - A CSS-cut corner (`clip-path`/`mask`) that shears its own content — clipped
   text or padding, a lost focus ring or glow, a jagged aliased edge, or a
   border/frame that stops at the cut instead of following it — the

package/templates/skills/genex-threejs-visual-validation/SKILL.md

@@ -56,9 +56,9 @@ translation may be normalized for Rapier.
 
 For plain game tasks — nothing from the procedural/visual-system pack loaded —
 this is the whole acceptance gate, and it is also the *ceiling*: a smoke check,
-not a certification. Run it ONCE per milestone, and only AFTER that milestone's
-`genex preview` is pushed — ship the rough draft first, then check it; the
-player may already be walking around your build while you do. Catch obvious
+not a certification. Run it ONCE per milestone, against that milestone's
+`genex preview` build — the player may already be walking around it while
+you check. Catch obvious
 breakage, fix what's clearly broken, and hand the feel/polish judgment to the
 player — don't loop re-testing the same build, don't re-test after cosmetic
 tweaks (sounds, colors, tuning values), and don't try to exercise every button
@@ -106,7 +106,12 @@ everything twice.
 4. In that screenshot, check oriented models: the hero faces its travel
    direction, and NPCs driven by chase/aim code face their target. A model
    rotated 90° reads as broken — `$genex-ai-model` has the one-time facing
-   fix.
+   fix. **In any two-character or enemy-encounter capture, the characters
+   face their TARGET, not the camera** — Meshy/Mixamo/VRM rigs rest facing
+   +Z (straight at a side camera), so an unset yaw ships duelists staring
+   at the lens; and a rig "turned" with `scale.x = -1` is a defect even
+   when it looks right from one angle (negative scale flips a SkinnedMesh's
+   winding and normals — the character-controller skill has the rules).
 5. Vehicles get one extra pass: drive forward once and confirm the NOSE
    leads (a 180° body is this bug's favorite disguise), and check the body
    stands ON the road with its wheels inside the silhouette — a body