@autoaiai/aicut 0.1.11 → 0.1.13

package/skills/image-smixs/references/patterns/character-design.md

@@ -1,150 +0,0 @@
-# Character Design Patterns
-
-Reusable prompt templates for character turnarounds, expression sheets, outfit variants, and collectible/card formats. Each pattern uses `{variables}` for customization. Default model: GPT Image 2.5 (5-slot format) unless noted.
-
----
-
-## Character Turnaround Sheet (3-View)
-
-Use for game or animation pre-production — front, side, and back views of a character on a single white canvas with color callouts and height reference lines.
-
-<!-- Source concept: character model sheet / turnaround sheet for 3D modelers and animators -->
-
-```
-Scene: clean white background, flat even lighting with no cast shadows, thin horizontal height reference lines in #CCCCCC spanning the full width at head, shoulder, waist, knee, and foot level
-Subject: {character_name} — {character_description} — shown in three views arranged left to right: front view (facing camera), three-quarter side view (turned 75 degrees right), back view (facing away)
-Important Details: all three views share identical proportions and vertical alignment along the height lines, feet on the same baseline, arms relaxed at sides for clear silhouette reading, color callout annotations — small circles of each key color ({color_1} {hex_1}, {color_2} {hex_2}, {color_3} {hex_3}) connected by thin #999999 leader lines to the corresponding material on the front view, fine line weight for height markers, clothing folds and seam lines consistent across all three angles
-Use Case: game character pre-production, animation model sheet, 3D reference handoff
-Constraints: no background elements, no props in hands, no dramatic poses — neutral standing pose only, all three views must depict the exact same character with identical outfit and proportions, no drop shadows, no gradient backgrounds
-```
-
-**Key levers:** `{character_name}`, `{character_description}` (age, build, hairstyle, outfit — be specific), `{color_1}`/`{hex_1}` through `{color_3}`/`{hex_3}` (key palette colors for callouts, e.g. jacket navy #1B2A4A, skin warm beige #D4A574, hair auburn #8B3A2F)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — height reference lines and color callout text require precise rendering
-
----
-
-## Expression Sheet
-
-Use to produce a grid of 6–9 facial expressions for the same character — consistent head angle and art style, with emotion labels under each face.
-
-<!-- Source concept: character expression/emotion reference sheet for animation or visual novel production -->
-
-```
-Scene: white background, 3x3 grid (or 3x2 for 6 expressions) with thin #DDDDDD divider lines, each cell contains one head-and-shoulders portrait
-Subject: {character_name} — {character_description} — same head angle (three-quarter left), same hairstyle, same lighting across all cells
-Important Details:
-  Cell 1: neutral — relaxed brow, closed mouth, calm eyes. Label: "NEUTRAL"
-  Cell 2: happy — genuine smile reaching the eyes, raised cheeks. Label: "HAPPY"
-  Cell 3: angry — furrowed brow, clenched jaw, narrowed eyes. Label: "ANGRY"
-  Cell 4: sad — downturned mouth, glistening eyes, slightly lowered head. Label: "SAD"
-  Cell 5: surprised — wide eyes, raised eyebrows, open mouth. Label: "SURPRISED"
-  Cell 6: disgusted — wrinkled nose, upper lip raised, squinted eyes. Label: "DISGUSTED"
-  {extra_expressions}
-  Labels in small {label_font} beneath each cell, #555555 text
-  Consistent {art_style} rendering across all cells — skin tone, line weight, shading approach identical
-Use Case: animation expression reference, visual novel sprite guide, game character documentation
-Constraints: same character identity in every cell — no variation in hair, accessories, skin tone, or clothing between expressions, head angle stays fixed, no hand gestures, labels must be legible
-```
-
-**Key levers:** `{character_name}`, `{character_description}` (face shape, skin tone, hair, distinguishing marks), `{art_style}` (clean cel-shaded anime, painterly semi-realism, flat vector illustration), `{label_font}` (condensed sans-serif, monospace, rounded sans), `{extra_expressions}` (add cells 7-9: e.g. "Cell 7: smirk — one corner of mouth raised, knowing look. Label: 'SMIRK'")
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — text labels and consistent facial identity across 9 cells need precise control
-
----
-
-## Outfit Variant Grid
-
-Use to show one character in multiple outfits or costumes — for fashion exploration, game skin concepts, or wardrobe design.
-
-<!-- Source concept: character costume/skin variant sheet for fashion or game design -->
-
-```
-Scene: light neutral background ({bg_color}), {grid_layout} grid, thin white gaps between cells, soft even front lighting in every cell
-Subject: {character_name} — {character_description} — same pose ({pose_description}) in every cell, only the outfit changes
-Important Details:
-  Cell 1: {outfit_1_name} — {outfit_1_description}
-  Cell 2: {outfit_2_name} — {outfit_2_description}
-  Cell 3: {outfit_3_name} — {outfit_3_description}
-  Cell 4: {outfit_4_name} — {outfit_4_description}
-  Cell 5: {outfit_5_name} — {outfit_5_description}
-  Cell 6: {outfit_6_name} — {outfit_6_description}
-  Outfit name in small bold sans-serif centered below each cell, #333333 text
-  Character body proportions, face, hairstyle, and skin tone identical across all cells — only clothing and accessories differ
-Use Case: game skin lineup, fashion mood board, costume design exploration
-Constraints: same character identity and pose in every cell, no background scenery — character only, outfit labels must be readable, no overlapping garments between cells, {grid_layout} layout must be uniform
-```
-
-**Key levers:** `{character_name}`, `{character_description}` (build, face, hair — anchor identity), `{bg_color}` (#F0F0F0 light gray, #FFF8F0 warm cream, #E8EDF2 cool blue-gray), `{grid_layout}` (2x3 or 3x3), `{pose_description}` (hands on hips, relaxed standing, one hand raised), `{outfit_N_name}` / `{outfit_N_description}` (e.g. "Street Casual" — oversized denim jacket, white tee, black cargo pants, chunky sneakers)
-
-**Recommended model:** GPT Image 2.5 (`quality: medium`) — character consistency is the priority; `high` only if outfit labels need fine legibility
-
----
-
-## Chibi / Mini-Me Collectible
-
-Use to transform a realistic character into a cute 3D collectible figurine — oversized head, compact body, multiple poses performing different activities.
-
-<!-- Source concept: chibi/super-deformed vinyl collectible figurine with consistent identity across poses -->
-
-```
-Scene: soft gradient background ({bg_gradient}), studio product lighting with rim light from behind and soft fill from front, subtle ground shadow beneath each figurine
-Subject: chibi-style 3D collectible figurine of {character_name} — {character_description_simplified} — large head (roughly 1:2 head-to-body ratio), rounded limbs, smooth matte vinyl surface, {num_poses} poses arranged in a row
-Important Details:
-  Pose 1: {pose_1_description}
-  Pose 2: {pose_2_description}
-  Pose 3: {pose_3_description}
-  {extra_poses}
-  Face retains recognizable features from the original character — {face_markers} — simplified into the chibi style with large round eyes and small nose/mouth
-  Outfit matches the original: {outfit_simplified} — colors preserved ({color_palette}), details reduced to clean shapes
-  Each figurine sits on a small circular base ({base_color} matte finish)
-  Vinyl toy aesthetic — visible seam line at sides, slight glossy highlight on forehead and cheeks
-Use Case: merchandise concept, social media avatar set, fan collectible design
-Constraints: consistent face and outfit across all poses, chibi proportions must stay uniform (no realistic proportions creeping in), no text on bases, smooth render — not cel-shaded, matte vinyl material throughout
-```
-
-**Key levers:** `{character_name}`, `{character_description_simplified}` (key outfit and hair only), `{face_markers}` (e.g. round glasses, scar on left cheek, green eyes), `{color_palette}` (hex values for 2-3 dominant colors), `{bg_gradient}` (#F5F0EB to #FFFFFF warm, #E0E8F0 to #FFFFFF cool), `{num_poses}` (3-5), `{pose_N_description}` (e.g. sitting cross-legged reading a book, waving with both hands, holding a coffee cup), `{base_color}` (white, black, matching character's main color)
-
-**Recommended model:** GPT Image 2.5 (`quality: medium`) — smooth 3D vinyl surfaces render well at medium; `high` for marketing-ready close-ups
-
-### Nano Banana version:
-
-```
-A row of {num_poses} chibi-style 3D vinyl collectible figurines of {character_name}, each in a different pose. Large head (1:2 head-to-body ratio), rounded limbs, smooth matte vinyl surface with visible seam lines and subtle glossy highlights on the forehead. Face retains {face_markers} simplified into chibi proportions with large round eyes. Outfit: {outfit_simplified} in {color_palette}. Poses left to right: {pose_1_description}, {pose_2_description}, {pose_3_description}. Each figurine on a small circular {base_color} matte base. Soft gradient background ({bg_gradient}), studio product lighting with rim light from behind and soft fill from front, subtle ground shadow. Format: 16:9.
-```
-
----
-
-## Anime-Style Character Card
-
-Use for a full character reference card with portrait, full body, key items, and color palette — organized on a white background in a professional concept art layout.
-
-<!-- Source concept: anime/game character reference sheet with stats, items, and palette swatches -->
-
-```
-Scene: white background, organized reference card layout divided into clear sections with thin #CCCCCC separator lines
-Subject: {character_name} — {character_description} — anime-style rendering with clean line art and flat cel shading
-Important Details:
-  Left section (40% width): full-body standing pose, front-facing, arms slightly away from body to show full outfit, feet visible, confident neutral expression
-  Upper-right section: portrait bust — head and shoulders, three-quarter angle, detailed face rendering showing {face_details}
-  Mid-right section: {num_items} key items arranged in a row — {item_1}, {item_2}, {item_3} — each drawn at consistent scale with thin outline, labeled in small text below
-  Lower-right section: color palette — {num_swatches} rectangular swatches in a horizontal strip showing the character's key colors ({swatch_colors}), hex code below each swatch
-  Bottom strip: brief stat block or bio text in clean sans-serif — "Name: {character_name} | Class: {class} | Height: {height} | Affiliation: {affiliation}"
-  Consistent line weight and shading style across all sections
-Use Case: game character documentation, light novel illustration guide, animation production reference
-Constraints: unified anime art style across all sections — portrait and full body must be the same character with identical design, items must match what the character wears/carries in the full body view, no decorative borders or ornamental frames, text must be legible at screen resolution
-```
-
-**Key levers:** `{character_name}`, `{character_description}` (detailed: hair color/style, eye color, outfit layers, accessories), `{face_details}` (distinctive facial features — e.g. heterochromia, facial tattoo, sharp jawline), `{item_1}`/`{item_2}`/`{item_3}` (signature weapon, accessory, artifact), `{swatch_colors}` (e.g. midnight blue #191970, cherry red #C41E3A, silver #C0C0C0, warm skin #E8B89D), `{num_swatches}` (4-6), `{class}` / `{height}` / `{affiliation}` (stat block fields)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — text-heavy layout with hex codes, labels, and stat block requires precise rendering
-
-### Nano Banana version:
-
-```
-An anime-style character reference card for {character_name} on a white background. Left side: full-body standing pose, front-facing, clean cel-shaded anime rendering — {character_description}. Upper right: portrait bust at three-quarter angle showing {face_details}. Mid-right: key items laid out in a row — {item_1}, {item_2}, {item_3} — each drawn consistently and labeled. Lower right: horizontal color palette strip with {num_swatches} rectangular swatches ({swatch_colors}). Clean layout with thin gray separator lines between sections. Professional concept art quality, consistent line weight throughout. Format: 3:4.
-```
-
----
-
-*Author: Serge Shima ([t.me/aimastersme](https://t.me/aimastersme) · [sergeshima.com](https://sergeshima.com) · [aimasters.me](https://aimasters.me)) · License: CC BY 4.0 — attribution required · Source: [smixs/visual-skills](https://github.com/smixs/visual-skills)*

package/skills/image-smixs/references/patterns/ecommerce.md

@@ -1,124 +0,0 @@
-# E-Commerce Product Photography Patterns
-
-Reusable prompt templates for product ads, packaging, and commercial visuals. Each pattern uses `{variables}` for customization. Default model: GPT Image 2.5 (5-slot format) unless noted.
-
----
-
-## Miniature Diorama Product Ad
-
-Use when you need a playful, attention-grabbing product visual where tiny workers interact with an oversized product — ideal for social media ads and launch campaigns.
-
-<!-- Source concept: miniature/tilt-shift product advertising with construction-worker scale play -->
-
-```
-Scene: clean {surface_color} tabletop studio, soft overhead diffused light, shallow depth of field with tilt-shift blur at edges
-Subject: oversized {product_name} centered in frame, surrounded by miniature construction workers (1/87 scale figurines) — some climbing the packaging with tiny ladders, others operating a miniature crane to lift the cap/lid, a crew painting the label
-Important Details: {product_material} surface catches key light from upper left, visible condensation/texture on product, figurines cast tiny hard shadows, warm {accent_color} hard hats on workers, fine detail on miniature tools, slightly desaturated background, eye-level camera angle
-Use Case: social media product ad, Instagram carousel hero
-Constraints: no text, no logos other than product label, no floating elements, product must remain recognizable and unaltered, no more than 8 figurines
-```
-
-**Key levers:** `{product_name}`, `{product_material}` (frosted glass, matte aluminum, glossy plastic), `{surface_color}` (white marble, raw concrete, light birch wood), `{accent_color}` (safety orange #FF6600, yellow #FFD600)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — precise figurine detail and product label legibility
-
----
-
-## Luxury Cosmetics Studio Shot
-
-Use for premium beauty or fragrance product photography — dark, moody, tactile surfaces with atmospheric effects.
-
-<!-- Source concept: luxury perfume/cosmetics dark-marble studio photography with condensation and smoke -->
-
-```
-Scene: dark studio, {background_surface} surface with subtle reflections, thin layer of low-hanging smoke drifting left to right, {time_mood} ambient
-Subject: {product_name} bottle/tube centered, three-quarter angle, {product_finish} catching a single key light from upper right
-Important Details: fine water droplets on product surface (condensation, not spray), {accent_material} accent elements flanking the product (raw stone, dried botanicals, metal shavings), volumetric haze behind product, reflection on surface below is soft and dark, color palette restricted to {palette}, contact shadow sharp near base fading to soft
-Use Case: luxury brand campaign hero, print ad, website banner
-Constraints: no text overlays, no human hands, background stays dark (#0a0a0a to #1a1a1a gradient), no color spill outside the defined palette, no lens flare
-```
-
-**Key levers:** `{background_surface}` (nero marquina marble, wet obsidian slab, brushed gunmetal), `{product_finish}` (frosted glass, lacquered black, brushed gold), `{accent_material}` (raw quartz crystals, dried lavender stems, black river stones), `{palette}` (golds #C9A84C and blacks, rose #B76E79 and creams, emerald #2D6A4F and silvers), `{time_mood}` (cold blue, warm amber)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — surface materials and condensation detail
-
----
-
-## 9-Panel TVC Storyboard Grid
-
-> For a dark-themed variant with timestamps, see [multi-panel.md](../multi-panel.md#1-9-cell-grid-storyboard).
-
-Use to present a product commercial shot breakdown in a single image — pitch decks, creative presentations, client approvals.
-
-<!-- Source concept: 9-panel television commercial storyboard grid with numbered frames -->
-
-```
-Scene: white canvas background, clean 3x3 grid with thin #CCCCCC divider lines (2px), each cell represents one shot in a {duration}-second commercial
-Subject: {product_name} commercial storyboard — each panel is a distinct camera setup
-Important Details:
-  Panel 1 (wide): establishing shot of {setting}, warm natural light, product not yet visible
-  Panel 2 (medium): {protagonist} notices/discovers the product on {surface}
-  Panel 3 (close-up): hand reaching for {product_name}, shallow depth of field
-  Panel 4 (ECU): product detail — texture of {product_material}, label readable
-  Panel 5 (medium): {protagonist} using/opening the product, genuine expression
-  Panel 6 (reaction): close-up face, {emotion} expression, soft key light
-  Panel 7 (wide): product in context of {lifestyle_scene}
-  Panel 8 (beauty shot): product hero on {beauty_surface}, studio lighting
-  Panel 9 (pack shot): product centered on white with "{tagline}" below in thin sans-serif, #333333
-Use Case: creative pitch deck, storyboard for TVC production
-Constraints: consistent character identity across all panels, no panel numbering text, uniform lighting temperature within the narrative (panels 1-7), distinct studio lighting for panels 8-9
-```
-
-**Key levers:** `{product_name}`, `{protagonist}` (woman in her 30s, young couple, family), `{setting}` (bright kitchen, outdoor terrace, urban cafe), `{emotion}` (satisfied, surprised, relaxed), `{beauty_surface}` (white marble, gradient gray), `{tagline}`, `{duration}` (15, 30)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — grid precision and text in panel 9
-
----
-
-## Floating Ingredient Freeze-Frame
-
-Use for food, beverage, or supplement products where suspended ingredients communicate freshness, flavor, or composition.
-
-<!-- Source concept: frozen-motion ingredient explosion around product, high-speed photography aesthetic -->
-
-```
-Scene: {background_gradient} gradient backdrop, high-speed flash freeze-frame moment, clean studio environment
-Subject: {product_name} container in center, tilted {tilt_angle} degrees, with {liquid_type} mid-pour arcing from the opening
-Important Details: individual {ingredient_list} frozen in mid-air around the product — each element sharply focused with visible texture ({texture_details}), micro water droplets suspended alongside ingredients, single hard flash from behind (rim light on ingredients), secondary soft fill from front, liquid splash forms a clean arc with visible viscosity, product label faces camera and remains fully legible, ingredients distributed in a loose orbital pattern
-Use Case: beverage packaging, food product poster, social media ad
-Constraints: no ingredients overlapping the product label, no motion blur (everything frozen sharp), background must remain clean — no stray splashes hitting edges, no more than {max_ingredients} floating elements, no artificial glow effects
-```
-
-**Key levers:** `{product_name}`, `{background_gradient}` (#F5F0EB to #FFFFFF for light, #1A0A2E to #0D0D0D for dark), `{liquid_type}` (amber juice, white milk, green smoothie), `{ingredient_list}` (sliced strawberries + mint leaves + ice cubes, cocoa nibs + hazelnuts + vanilla pod), `{texture_details}` (visible seeds on strawberry cross-section, frost crystals on ice), `{tilt_angle}` (15, 25), `{max_ingredients}` (6-8)
-
-**Recommended model:** GPT Image 2.5 (`quality: high`) — frozen detail precision and label legibility
-
----
-
-## Inflatable Surrealism Product Poster
-
-Use for disruptive, scroll-stopping social ads where the product packaging appears squeezed, inflated, or physically distorted as if made of soft rubber or vinyl.
-
-<!-- Source concept: inflatable surrealism — product packaging rendered as squeezed/puffy/distorted soft objects -->
-
-```
-Scene: solid {background_color} background, soft even studio lighting with no hard shadows, slightly elevated camera angle (15 degrees above eye level)
-Subject: {product_name} packaging reimagined as a puffy inflatable vinyl object — the shape is recognizable but squeezed at the middle as if gripped by an invisible hand, seams visible where vinyl panels meet, surface slightly reflective like a pool float
-Important Details: {product_color_scheme} preserved on the inflated surface but stretched and slightly warped around curves, visible air valve at the bottom edge (small brass circle), subtle wrinkles where the vinyl compresses, the brand name/logo distorted by the inflation but still readable, two or three {companion_objects} nearby also inflated (matching aesthetic), environment reflection on glossy vinyl surface, cast shadow soft and diffused below
-Use Case: disruptive social media ad, brand campaign poster, billboard
-Constraints: product must remain identifiable despite distortion, no liquid, no particles, no humans, no text outside what exists on the packaging, vinyl texture must read as physical (not digital 3D render), background is flat color only
-```
-
-**Key levers:** `{product_name}`, `{background_color}` (bubblegum pink #FFB6C1, electric blue #007BFF, acid yellow #E8FF00), `{product_color_scheme}`, `{companion_objects}` (matching accessories, ingredient items, brand mascot elements)
-
-**Recommended model:** NBP — complex spatial reasoning for believable physical distortion
-
-### Nano Banana version:
-
-```
-A product poster showing {product_name} packaging transformed into a puffy inflatable vinyl object, squeezed at the middle as if gripped by an invisible hand. The surface is slightly glossy like a pool float, with visible seams where vinyl panels meet and a small brass air valve at the base. The original {product_color_scheme} is preserved but stretched and warped around the inflated curves. Brand text is distorted by the shape but still legible. Two small {companion_objects} sit nearby, also inflated in the same vinyl style. Solid {background_color} background, soft even studio light, slightly elevated camera angle. Soft diffused shadow below. Format: 4:5.
-```
-
----
-
-*Author: Serge Shima ([t.me/aimastersme](https://t.me/aimastersme) · [sergeshima.com](https://sergeshima.com) · [aimasters.me](https://aimasters.me)) · License: CC BY 4.0 — attribution required · Source: [smixs/visual-skills](https://github.com/smixs/visual-skills)*

package/skills/image-story-video-wizard/SKILL.md

@@ -1,148 +0,0 @@
----
-name: image-story-video-wizard
-description: "Use when a user wants step-by-step help making an audio-first image-story, AI narration, slideshow, illustrated story, AI 讲书, 图片联播, 有声故事, or 静态图叙事视频 with Codex or WorkBuddy; not for a standalone script, single image, or ordinary video editing. Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
-license: MIT
-source: "aaronyi97/image-story-video-wizard"
----
-
-# Image Story Video Wizard
-
-## Running it in AICUT
-
-AICUT's film is `film.html`: it cuts pages, footage, pictures and sound together on tracks. A page is a web page that
-sets `window.film = { frame(t) }` and draws that moment — no framework, no build step, no composition object, no
-`registerRoot`. Five shots are five pages cut together, not one page that changes scene, so each shot stays trimmable
-and replaceable in Studio.
-
-```sh
-npx -y @autoaiai/aicut@latest          # the manual: the format and the commands, always current
-npx -y @autoaiai/aicut@latest open .   # make this folder a film and print Studio's address
-npx -y @autoaiai/aicut@latest look     # a contact sheet of the whole film, its sound, and a determinism check
-npx -y @autoaiai/aicut@latest look 4.5 # one frame, full size — look at the PNG, not at the code
-npx -y @autoaiai/aicut@latest render   # the MP4, beside film.html
-```
-
-Run the manual before the first film: it is authoritative for the format, and this skill is about the method above it.
-
-Where the words below name another program's part, it becomes this:
-
-| elsewhere | in AICUT |
-|---|---|
-| composition, timeline, project file | `film.html`; tracks and clips inside it |
-| a scene, a sequence, a slide | a page (`pages/<name>.html`) cut onto a track |
-| `useCurrentFrame()`, `interpolate()` | `frame(t)` — the picture depends only on `t`, never on state or `Date.now()` |
-| a still, a screengrab | `aicut look <t>` |
-| `render` / `build` / `export` | `aicut render` (the person can also export from Studio) |
-| a dev server, a preview window | `aicut open` and the Studio address it prints |
-
-Hard rules that hold whatever the method says: the picture depends only on `t`; every value in the person's prompt is
-binding; look at the frames `look` writes before saying a film is done.
-
-
-Own the process. The user supplies the current decision or material; the Skill decides what must happen next, explains it, performs everything it can, and stops at the next confirmation gate.
-
-## Guided interaction contract
-
-Never dump the whole workflow and ask the user to drive it. At every turn, say:
-
-1. `现在进行到：` current stage and purpose.
-2. `我现在会做：` the action the Skill will take.
-3. `你现在只需要：` one to three current inputs or decisions.
-4. `完成后我会交付：` the concrete artifact or preview.
-5. `确认后下一步：` the next stage, without starting it early.
-
-Ask only what blocks the current stage. Do not ask the user to choose the next workflow step. Avoid generic questions such as “接下来想做什么？” Instead state the next step and request its minimum input.
-
-Use these stage statuses exactly: `未开始`, `进行中`, `待确认`, `已确认`, `需要返工`, `已跳过`. A reply such as “继续” or “可以” approves only the current gate, not all later gates.
-
-## Start or resume
-
-On first use, detect whether this is a new project or a resumed one. Look for `PROJECT_STATE.json` in the supplied project folder. If none exists, initialize one with `scripts/project_state.py init`. If a state file exists, validate it, summarize the latest confirmed artifact, and resume at `pending_request`; do not restart from the beginning.
-
-At stage 0, identify the actual host and capabilities. Read [references/host-routing.md](references/host-routing.md) when choosing between Codex, WorkBuddy, or a handoff. Never claim a host can access local files, call a model, use a logged-in browser, synthesize audio, or render unless that capability is available now.
-
-Read [references/workflow.md](references/workflow.md) before starting a project and whenever entering a new stage. Read [references/state-schema.md](references/state-schema.md) before creating or changing project state.
-
-## Stage order and hard gates
-
-Follow this state machine:
-
-`START → BRIEF → BENCHMARKS → WRITING_PACK → SCRIPT → VOICE → STORYBOARD → VISUAL_STYLE → CHARACTER_ANCHORS → IMAGE_PROMPTS → IMAGE_GENERATION → ASSET_QC → MUSIC → PREVIEW → FINAL_RENDER → FEEDBACK`
-
-Hard gates:
-
-- Do not generate a writing pack before product direction and benchmark roles are confirmed.
-- Do not synthesize full narration before the final script is confirmed.
-- Do not write the complete image-prompt manifest before image cadence and visual style are confirmed.
-- Do not batch-generate images before a three-to-five-image pilot and any required character anchors are confirmed.
-- Do not render a final video before the user accepts the preview.
-- Do not publish, upload, post, or change a live channel unless the user separately authorizes that action.
-
-If a gate fails, mark `需要返工`, return only to the earliest affected stage, and preserve later artifacts as untrusted rather than deleting them.
-
-## Production invariants
-
-### Script
-
-- Learn a benchmark's topic logic, structure, pace, hooks, transitions, and audience need; never copy its original wording or finished assets.
-- At WRITING_PACK and SCRIPT, read [writing and review](references/writing-and-review.md). Keep reusable writer rules, the current channel/language with selected examples, and episode materials separate inside one self-contained package.
-- Require one complete first draft; do not pad for length. A complete but slightly short draft can be reviewed as-is. A hollow draft or missing necessary material calls for repairing the package, not decorative expansion.
-- The original guiding conversation gives a focused edit list; the chosen writer performs local repairs. Compare the returned text against the list, then stop for user acceptance. Large rewrites require a clear reason and user confirmation.
-
-### Voice
-
-- Ask whether TTS credentials are locally configured; never ask the user to paste a secret into chat. If absent, guide local secret storage and verify only availability.
-- Compare five to ten voices with the same approximately twenty-second sample. Confirm voice first, then test speaking rate.
-- Prefer narration output with sentence- or word-level timestamps when available.
-
-### Storyboard and images
-
-- Calculate image count from narration duration. A dynamic 6–8 second cadence means about 75–100 images per ten minutes; an economical 10–12 second cadence means about 50–60.
-- Lock image style and text treatment with a three-to-five-image pilot before producing the full prompt manifest.
-- Detect recurring characters. When identity continuity matters, confirm face and full-body anchors before batch generation.
-- In manual mode, guide a pilot first, then batches. Do not dump dozens of prompts in the first image turn.
-- Keep prompt IDs, storyboard IDs, generated filenames, and narration ranges aligned.
-
-### Assembly and review
-
-- Prefer HyperFrames for programmable assembly when available, but follow the confirmed project format and host capability.
-- When actual assembly or rendering begins in an environment that provides the HyperFrames skills, load the `hyperframes` mandatory entry point and follow the routed core, media, animation, audio, and CLI instructions that apply to the confirmed project.
-- Align images, subtitles, text cards, and optional music to narration timing.
-- Produce a reviewable preview before final render. Machine checks do not replace visual inspection and one full human watch.
-- Keep delivery status `已做待验` until the user accepts the final master.
-
-## Secrets and external actions
-
-Do not store API keys, session URLs, redemption codes, cookies, or tokens in prompts, project files, logs, screenshots, or repositories. Ask whether access is configured, not for the plaintext secret.
-
-Model calls that spend money, browser actions using logged-in sessions, final rendering, uploads, and publishing must stay within the user's current authorization. Explain cost or account impact before the action when material.
-
-## Project artifacts
-
-Use stable filenames so the project can resume across hosts:
-
-- `PROJECT_STATE.json`
-- `BRIEF.md`
-- `BENCHMARKS.md`
-- `writing-pack/`
-- `SCRIPT.md`
-- `audio/`
-- `STORYBOARD.csv`
-- `VISUAL_STYLE.md`
-- `characters/`
-- `IMAGE_PROMPTS.md`
-- `images/`
-- `review/`
-- `renders/`
-- `HANDOFF.md` when another host must continue
-
-Use the templates in `assets/` when creating these artifacts. Validate `PROJECT_STATE.json` before claiming a stage is complete.
-
-## Completion
-
-Completion means the confirmed master and its resumable project files exist and pass the proportional checks in the workflow. Report the current state as `未做`, `已做待验`, or `已验收`. Do not call a workflow “automated” merely because one sample rendered; record manual intervention and real production time after several episodes.
-
-## Source
-
-Rewritten for AICUT from [`aaronyi97/image-story-video-wizard`](https://github.com/aaronyi97/image-story-video-wizard)
-(MIT), SKILL.md. The method is that skill's own; the way it runs is AICUT's.

package/skills/image-story-video-wizard/docs/ARTICLE_ALIGNMENT.md

@@ -1,29 +0,0 @@
-# 教程与 Skill 对齐记录
-
-| 教程要求 | Skill 落点 | 结果 |
-| --- | --- | --- |
-| Skill 主动引导，用户不需要自己记整套流程 | `SKILL.md` 的五段式交互合同 | 已对齐 |
-| 只问当前必需的材料或决定 | 每个阶段都有 `Ask now`，限定在当前阶段 | 已对齐 |
-| 关键节点等用户确认后再继续 | 写作包、文案、声音、样图、人物母版、预览和成片都有独立 gate | 已对齐 |
-| 学对标的选题、结构、节奏和钩子，不照搬原句 | `BENCHMARKS` 和 `WRITING_PACK` | 已对齐 |
-| Kimi 一次成稿，不在坏稿上二次填充 | `SCRIPT` 的返工规则 | 已对齐 |
-| WorkBuddy 里使用 Kimi K3、Max、最高思考强度和 1M 上下文 | `references/host-routing.md` | 已对齐，但必须以当前页面实际可用选项为准 |
-| 豆包 Seed-TTS 2.0，同文本试听 5–10 个音色，先选音色再调语速 | `VOICE` | 已对齐 |
-| 没有豆包权限时，由 Skill 继续带着申请和配置 | `VOICE` 的 `Skill acts` | 已对齐 |
-| 按实际音频时长拆分镜，经济节奏每 10 分钟 50–60 张 | `STORYBOARD` 和生产不变式 | 已对齐 |
-| 先做 3–5 张样图，再锁画风、人物和文字样式 | `VISUAL_STYLE`、`CHARACTER_ANCHORS`、`IMAGE_PROMPTS` | 已对齐 |
-| 手动生图时一个新对话只跑一张；API 先估算数量和成本再小批跑 | `IMAGE_GENERATION` | 已对齐 |
-| 生图后检查数量、编号、画风和人物一致性 | `ASSET_QC` | 已对齐 |
-| BGM 可选，不应阻塞成片 | `MUSIC` 允许显式跳过 | 已对齐 |
-| HyperFrames 先组装预览，人工确认后再渲染 | `PREVIEW` 和 `FINAL_RENDER` | 已对齐 |
-| 7–15 天流量弱时先复盘选题和文案；三到五篇稳定稿以后再提炼自己的文案 Skill | `FEEDBACK` | 已对齐 |
-
-## 特意不写死的内容
-
-- 生图和配音的单价会变，Skill 会在实际选择 API 时重新估算，不把某一天的价格写成永久规则。
-- 「稳定日更」和「人工介入低于一小时」是目标，必须在多期真实运行后记录，不会因为一期成片就声称已经实现。
-
-## 当前验收边界
-
-- Skill 结构、全部 16 个阶段、五段式交互、关键确认门、状态文件初始化和校验已通过自动测试。
-- WorkBuddy/Kimi 和各个外部 API 的实际调用需要当前账号、模型和权限，不在本地结构测试里冒充验收。

package/skills/image-story-video-wizard/references/host-routing.md

@@ -1,44 +0,0 @@
-# Codex and WorkBuddy host routing
-
-Do not route by product name alone. Route by verified capability in the current session.
-
-## Capability check
-
-At START, determine whether the host can currently:
-
-- read and write the chosen local project folder;
-- package and open attachments;
-- route to the requested writing model;
-- use a logged-in browser within the authorized boundary;
-- call the configured TTS service without exposing secrets;
-- generate or inspect images;
-- run HyperFrames or another confirmed assembly tool;
-- render a local video.
-
-Record the result in `PROJECT_STATE.json`. `Logged in` is not proof of the correct account, and an installed tool is not proof it is authorized for this project.
-
-## Codex route
-
-Use Codex as the continuous host when local files, required tools, and render capability are available. It may own the state file, produce project artifacts, coordinate writing-model handoffs, inspect images, build the HyperFrames project, and render after the preview gate.
-
-If a required external model or service is unavailable, do not substitute silently. Create a bounded user action or handoff package.
-
-For writing, keep the original guiding conversation as the reviewer and the user's chosen model as the author. Follow [writing and review](writing-and-review.md): the guiding conversation sends specific local edit instructions, the writer returns the full revision, and the guiding conversation checks the actual changes before user acceptance. A file handoff does not authorize the reviewer to replace the author's voice or expand into a rewrite.
-
-## WorkBuddy route
-
-WorkBuddy may own early stages when it can analyze benchmarks, build or consume a writing pack, and use Kimi K3. For the tutorial route, select Kimi K3, turn on Max mode, choose the strongest available thinking setting such as `超高`, and use the 1M context window when those controls are actually visible. Confirm the selected model, mode, thinking strength, and context window before claiming Kimi K3 participated; if the product labels or available options have changed, state the nearest verified substitute instead of pretending the original setting is still available.
-
-If WorkBuddy has verified local file and render capabilities, it may continue. Otherwise stop after the last supported stage and create `HANDOFF.md` plus all referenced artifacts for Codex. Tell the user exactly:
-
-- what WorkBuddy completed;
-- what remains unconfirmed;
-- which folder or archive to give Codex;
-- what Codex should do first;
-- which gate must be presented to the user next.
-
-## Handoff rules
-
-Use `assets/handoff-template.md`. A handoff is valid only when artifact paths resolve or files are included, current stage/status are explicit, and the pending user request is preserved.
-
-Do not call a handoff complete merely because a summary was written. Validate the state and package contents.

package/skills/image-story-video-wizard/references/state-schema.md

@@ -1,79 +0,0 @@
-# Project state contract
-
-`PROJECT_STATE.json` is the single source for workflow position. It is not a log of secrets or a substitute for the actual artifacts.
-
-## Required top-level fields
-
-```json
-{
-  "schema_version": 1,
-  "project_id": "slug-or-uuid",
-  "title": "Human-readable title",
-  "project_root": "/absolute/project/path",
-  "host": {
-    "name": "codex|workbuddy|other",
-    "capabilities": {
-      "local_files": true,
-      "model_routing": false,
-      "logged_in_browser": false,
-      "tts": false,
-      "image_generation": false,
-      "hyperframes": false,
-      "render": false
-    }
-  },
-  "current_stage": "START",
-  "stage_status": "进行中",
-  "pending_request": "Confirm project root and whether this is new or resumed work.",
-  "next_stage": "BRIEF",
-  "decisions": {},
-  "artifacts": {},
-  "stage_history": [],
-  "created_at": "ISO-8601 timestamp",
-  "updated_at": "ISO-8601 timestamp"
-}
-```
-
-## Allowed stages
-
-`START`, `BRIEF`, `BENCHMARKS`, `WRITING_PACK`, `SCRIPT`, `VOICE`, `STORYBOARD`, `VISUAL_STYLE`, `CHARACTER_ANCHORS`, `IMAGE_PROMPTS`, `IMAGE_GENERATION`, `ASSET_QC`, `MUSIC`, `PREVIEW`, `FINAL_RENDER`, `FEEDBACK`.
-
-## Allowed statuses
-
-`未开始`, `进行中`, `待确认`, `已确认`, `需要返工`, `已跳过`.
-
-## Update rules
-
-1. Update state after creating a material artifact, reaching a gate, receiving a gate decision, or changing hosts.
-2. Before entering a stage, append the prior stage result to `stage_history` with timestamp and artifact paths.
-3. `pending_request` must name the one current user action. It must not contain the full future checklist.
-4. Store decisions as facts with source and status, for example:
-
-```json
-"decisions": {
-  "aspect_ratio": {
-    "value": "16:9",
-    "source": "user",
-    "status": "已确认"
-  }
-}
-```
-
-5. Artifact paths must be absolute inside `PROJECT_STATE.json`. Public deliverables must not expose private paths.
-6. Never store plaintext API keys, cookies, login URLs, redemption codes, or tokens.
-7. When returning to an earlier stage, do not delete downstream artifacts. Mark them in `artifacts` as `stale: true` until regenerated or re-confirmed.
-
-## Resume behavior
-
-On resume:
-
-1. Validate the state file with `scripts/project_state.py validate`.
-2. Confirm that the latest required artifact still exists.
-3. Tell the user the latest confirmed gate and the single pending request.
-4. Continue from `current_stage`; do not repeat already confirmed questions.
-
-## Delivery status mapping
-
-- No material artifact: `未做`.
-- Artifact exists but user has not accepted the relevant gate: `已做待验`.
-- User accepted the final master: `已验收`.