@hienlh/ppm 0.9.81 → 0.9.83

package/.opencode/skills/ai-artist/data/domains.csv

@@ -1,16 +0,0 @@
-STT,Domain,Description,Key Considerations,Prompt Structure,Common Mistakes,Best Platforms
-1,Marketing,Advertisements, campaigns, promotional materials,"Brand consistency, clear CTA, target audience, emotional appeal, legal compliance","[Product/Service] + [Value Proposition] + [Target Emotion] + [Style matching brand] + [Professional quality]","Generic stock photo look, off-brand colors, unclear product, busy composition, text issues","DALL-E (text), MJ (aesthetics), Flux (brand control)"
-2,Social Media,Platform-specific content (Instagram, TikTok, LinkedIn),"Platform dimensions, scroll-stopping visuals, engagement-first, trend awareness, quick comprehension","[Hook visual] + [Platform aesthetic] + [Trending style] + [Optimized aspect ratio] + [Vibrant/bold]","Wrong aspect ratio, too subtle for scroll, text too small, not platform-native feel","MJ (aesthetic), DALL-E (text overlays), Flux (versatile)"
-3,E-commerce,Product photography, lifestyle shots, detail images,"Clean backgrounds, accurate representation, multiple angles, lifestyle context, zoom-ready detail","[Product] + [Angle: front/45deg/detail] + [Background: white/lifestyle] + [Professional lighting] + [Sharp focus]","Unrealistic product appearance, wrong scale, poor shadows, cluttered background, text on product","MJ --style raw, SD (product LoRAs), DALL-E (describe product)"
-4,Brand Identity,Logos, icons, brand assets, visual identity elements,"Scalability, simplicity, memorability, versatility, vector-ready output","[Symbol/Mark] + [Brand values] + [Simple geometric] + [Limited colors] + [Clean vector style]","Too complex, won't scale, not recognizable small, too trendy, difficult to reproduce","Claude (SVG), MJ (concept), Midjourney then vectorize"
-5,Editorial,Magazine covers, article illustrations, news imagery,"Story support, emotional resonance, publication style, ethical representation","[Subject] + [Narrative context] + [Publication style] + [Dramatic/editorial lighting] + [Thoughtful composition]","Misleading imagery, inappropriate for context, too literal, lacking depth","MJ (editorial style), DALL-E (specific scenes)"
-6,Web/UI Design,Hero images, backgrounds, UI illustrations, interface elements,"Web-safe, fast loading, responsive-friendly, consistent with UI, accessibility","[Purpose: hero/background/icon] + [Style matching UI] + [Web-optimized] + [Ample negative space] + [Scalable]","Too heavy/detailed, clashes with UI, poor contrast for text overlay, not responsive-friendly","MJ (backgrounds), Claude (SVG icons), Flux (illustrations)"
-7,Gaming,Game assets, character art, environments, concept art,"Stylistic consistency, asset pipeline ready, game engine compatible, clear silhouettes","[Asset type] + [Game genre] + [Art style] + [Technical specs] + [Concept art quality]","Inconsistent style, poor silhouette, wrong scale for use, too realistic for stylized games","SD (LoRAs), MJ (concept), Flux (style control)"
-8,Film/Video,Storyboards, concept art, VFX reference, production design,"Continuity, director's vision, practical feasibility, cinematic language","[Shot type] + [Cinematic reference] + [Mood/tone] + [Production value] + [Story moment]","Wrong aspect ratio, unrealistic for production, poor continuity, generic cinematography","MJ (cinematic), Runway/Veo (motion), DALL-E (specific scenes)"
-9,Publishing,Book covers, illustrations, chapter headers, print materials,"Print resolution (300dpi), spine/bleed awareness, genre conventions, thumbnail test","[Genre signals] + [Key imagery] + [Typography space] + [Print quality] + [Thumbnail readable]","Won't work as thumbnail, wrong genre signals, no space for title, too low res","MJ (covers), DALL-E (illustrations), SD (specific styles)"
-10,Education,Diagrams, illustrations, infographics, learning materials,"Clarity over beauty, accessible, appropriate complexity, culturally neutral","[Concept to illustrate] + [Educational clarity] + [Appropriate complexity] + [Clean lines] + [Accessible colors]","Too complex, culturally specific, distracting style, unclear concept visualization","DALL-E (clear concepts), Claude (diagrams), MJ (engaging style)"
-11,Healthcare,Medical illustrations, wellness imagery, health communications,"Accuracy, sensitivity, compliance, reassuring tone, diverse representation","[Medical context] + [Accurate representation] + [Reassuring tone] + [Diverse subjects] + [Professional clean]","Inaccurate anatomy, insensitive imagery, scary instead of reassuring, compliance issues","DALL-E (accurate), MJ with care (aesthetic), SD (medical LoRAs)"
-12,Architecture,Renderings, visualizations, concept designs, interior design,"Scale accuracy, material realism, lighting accuracy, context appropriate","[Building/space type] + [Architectural style] + [Material specification] + [Time of day] + [Render quality]","Wrong scale, unrealistic materials, poor perspective, lighting doesn't match location","MJ (visualizations), SD (architectural), Flux (control)"
-13,Fashion,Lookbooks, campaign imagery, product shots, editorial fashion,"Trend awareness, garment accuracy, model diversity, brand aesthetic","[Garment] + [Styling context] + [Model type] + [Fashion photography style] + [Brand aesthetic]","Wrong fit/drape, outdated styling, limited diversity, too editorial for commercial","MJ (fashion), DALL-E (specific garments), SD (fashion LoRAs)"
-14,Food & Beverage,Food photography, packaging, restaurant menus, recipes,"Appetizing appeal, accurate representation, proper styling, food safety","[Dish] + [Styling: overhead/45deg] + [Props and context] + [Food photography] + [Appetizing colors]","Unappetizing colors, wrong texture, artificial look, poor composition","MJ (food style), DALL-E (specific dishes), SD (food LoRAs)"
-15,Technology,Tech products, futuristic concepts, interface mockups, innovation,"Clean modern aesthetic, accurate representation, futuristic credibility","[Tech product/concept] + [Clean modern style] + [Accurate details] + [Futuristic credibility] + [Professional render]","Unrealistic tech, dated futurism, poor UX representation, too sci-fi for realistic","MJ (tech aesthetic), DALL-E (concepts), Flux (control)"

package/.opencode/skills/ai-artist/data/image-styles.csv

@@ -1,21 +0,0 @@
-STT,Style,Category,Prompt Keywords,Lighting,Composition,Quality Modifiers,Negative Prompt,Best For,Platform Tips
-1,Photorealistic,Photography,"photorealistic, hyperrealistic, ultra detailed, 8k uhd, realistic skin texture, natural proportions","golden hour, natural lighting, soft shadows, studio lighting, rim light","rule of thirds, shallow depth of field, centered subject, eye-level angle","8k, highly detailed, professional photography, sharp focus, RAW photo","cartoon, illustration, painting, anime, distorted, blurry, low quality","Product shots, portraits, architectural, stock photos","MJ: --style raw --v 6.1; SD: CFG 7-9; DALL-E: describe naturally"
-2,Cinematic,Photography,"cinematic shot, movie still, film grain, anamorphic lens, dramatic composition, blockbuster aesthetic","Rembrandt lighting, volumetric light rays, atmospheric haze, neon glow, backlit","widescreen 2.39:1, dutch angle, low angle hero shot, silhouette, framing with foreground","35mm film, IMAX quality, Hollywood production, professional cinematography","flat lighting, amateur, snapshot, overexposed, underexposed","Movie posters, hero sections, dramatic storytelling, trailers","MJ: --ar 21:9 --style raw; Flux: cinematic + film grain keywords"
-3,Editorial Fashion,Photography,"high fashion editorial, vogue cover, luxury magazine, runway model, haute couture","butterfly lighting, fashion studio, ring light, dramatic shadows, clean white background","full body pose, three-quarter view, dynamic pose, negative space, minimalist background","high-end fashion photography, professional retouching, crisp details","casual wear, amateur, candid, street style, wrinkles, messy","Fashion campaigns, luxury brands, magazine covers, lookbooks","MJ: --stylize 250; DALL-E: mention specific designers/magazines"
-4,Product Showcase,Photography,"product photography, commercial shot, packshot, clean background, floating product","soft box lighting, even illumination, subtle reflections, gradient background","centered, floating, 45-degree angle, hero shot, detail macro","advertising quality, pristine, professional retouching, sharp edges","dirty, scratched, damaged, fingerprints, dust, uneven lighting","E-commerce, ads, packaging, marketing materials","MJ: --style raw; SD: product_photography LoRA"
-5,Portrait Artistic,Portrait,"artistic portrait, fine art photography, emotional expression, soulful eyes, painterly quality","Rembrandt, split lighting, chiaroscuro, natural window light, golden hour","tight crop, eye contact, off-center, rule of thirds, negative space","masterpiece portrait, award-winning, museum quality, emotional depth","snapshot, ID photo, passport, unflattering angle, harsh flash","Personal branding, artist profiles, book covers, bio photos","MJ: --stylize 500+; Flux: mention specific portrait photographers"
-6,Minimalist,Style,"minimalist design, clean composition, white space, simple geometry, single subject, negative space","flat even lighting, soft shadows, no harsh contrasts","centered subject, lots of white space, geometric shapes, clean lines","pristine, clean, uncluttered, zen-like, simple elegance","busy, cluttered, complex, ornate, maximalist, chaotic","Brand identity, app icons, modern marketing, clean UI mockups","DALL-E: emphasize simplicity; MJ: --stylize 0-100"
-7,Cyberpunk,Sci-Fi,"cyberpunk aesthetic, neon lights, rain-soaked streets, holographic displays, dystopian city, tech noir","neon glow, volumetric fog, rain reflections, pink/cyan/purple neon, city lights","low angle, reflections in puddles, silhouette, busy background, layered depth","blade runner style, high detail, atmospheric, moody, cinematic","bright daylight, clean, futuristic utopia, sunny, cheerful","Gaming, sci-fi projects, tech products, album covers, posters","MJ: --chaos 20; SD: cyberpunk_2077 LoRA + neon + rain"
-8,Fantasy Epic,Fantasy,"epic fantasy scene, magical landscape, mystical creatures, enchanted forest, castle in clouds","ethereal glow, magical particles, volumetric god rays, bioluminescence, aurora","wide establishing shot, dramatic perspective, sense of scale, layered depth","highly detailed, concept art, digital painting, award-winning, 8k","modern, urban, technology, cars, phones, realistic mundane","Book covers, game assets, worldbuilding, D&D campaigns","MJ: --stylize 750; Flux: add artist references like Greg Rutkowski"
-9,Anime,Illustration,"anime style, manga illustration, Japanese animation, cel shaded, large expressive eyes","anime lighting, dramatic shadows, bloom effects, lens flare, sakura petals","dynamic pose, speed lines, impact frame, close-up reaction shot","Studio Ghibli quality, Makoto Shinkai style, beautiful anime, masterpiece","western cartoon, 3D render, realistic, photographic","Character design, fan art, web novels, visual novels, merch","MJ: --niji 6; SD: anime LoRA + danbooru tags"
-10,Watercolor,Art,"watercolor painting, soft washes, paper texture, wet-on-wet technique, delicate brushstrokes","soft natural light, diffused, gentle shadows, pastel tones","loose composition, bleeding edges, white paper showing, organic flow","artistic, hand-painted feel, traditional media, gallery quality","digital, sharp edges, photorealistic, crisp lines, harsh colors","Wedding invitations, children books, botanical art, cards","DALL-E: watercolor + soft + hand-painted; MJ: --stylize 750"
-11,Oil Painting,Art,"oil painting, visible brushstrokes, rich colors, impasto technique, classical composition","dramatic lighting, Baroque chiaroscuro, warm palette, museum lighting","classical composition, portrait orientation, golden ratio, layered depth","masterpiece, museum quality, old master technique, rich texture","flat, digital, smooth, photographic, clean lines","Portraits, landscapes, classical themes, luxury branding","MJ: --stylize 1000; SD: oil_painting LoRA + artist name"
-12,3D Render,Digital,"3D render, octane render, cinema 4D, blender, photorealistic CGI, subsurface scattering","HDRI lighting, global illumination, soft shadows, studio setup","isometric, hero angle, product shot, architectural visualization","8k, ray tracing, physically based rendering, professional CGI","2D, flat, hand-drawn, pixelated, low poly","Product visualization, tech, architecture, abstract art","SD: 3d_render LoRA; MJ: --style raw for realism"
-13,Isometric,Digital,"isometric view, 3D illustration, orthographic projection, clean geometry, tiny world, diorama","soft even lighting, no harsh shadows, subtle ambient occlusion","30-degree angle, grid-aligned, miniature scene, top-down tilted","clean vector look, professional illustration, game asset quality","perspective distortion, fisheye, realistic depth, photographic","Infographics, game assets, explainer graphics, app illustrations","MJ: isometric exact angle; Flux: isometric + clean + geometric"
-14,Retro Vintage,Style,"vintage aesthetic, retro 70s/80s, nostalgic, grain, faded colors, analog photography","warm color cast, sunset tones, lens flare, light leaks, vignette","polaroid crop, centered subject, domestic scene, casual composition","film grain, faded, sun-bleached, authentic vintage, analog feel","modern, crisp, digital, clean, contemporary","Throwback campaigns, nostalgia marketing, music albums, indie brands","MJ: vintage film + specific decade; SD: analog film LoRA"
-15,Pop Art,Art,"pop art style, Andy Warhol, Roy Lichtenstein, Ben-Day dots, bold colors, comic style","flat even lighting, no shadows, high contrast, primary colors","centered portrait, grid layout, repeated elements, bold outline","vibrant, graphic, iconic, screen print aesthetic, 1960s art","subtle, natural colors, photorealistic, soft, muted","Bold marketing, youth brands, social media, merchandise","DALL-E: pop art + Warhol; MJ: pop art --stylize 500"
-16,Vaporwave,Style,"vaporwave aesthetic, 90s internet, glitch art, marble statues, tropical sunset, retro tech","neon pink/cyan/purple, sunset gradient, glowing, soft bloom","centered composition, geometric shapes, grid floor, palm trees","synthwave, retrowave, outrun, aesthetic, lo-fi, dreamy","realistic, modern, clean, corporate, serious","Music covers, aesthetic content, nostalgic tech, social posts","MJ: vaporwave + specific elements; SD: vaporwave_aesthetic LoRA"
-17,Dark Academia,Style,"dark academia aesthetic, classical literature, oxford, vintage library, candlelit, scholarly","warm candlelight, moody, low key, autumn colors, window light","books and papers, classical architecture, warm browns and greens","atmospheric, cozy, intellectual, autumn vibes, mysterious","modern, bright, minimal, colorful, tech, summer","Education, book marketing, fashion, lifestyle, writing","MJ: dark academia + specific setting; DALL-E: describe mood in detail"
-18,Cottagecore,Style,"cottagecore aesthetic, pastoral, countryside, wildflowers, rustic charm, homemade, cozy","soft morning light, dappled sunlight through trees, golden hour, overcast","rule of thirds, natural framing with foliage, intimate scale, pastoral scene","dreamy, soft focus, whimsical, peaceful, handcrafted feel","urban, modern, technology, harsh, industrial, artificial","Lifestyle brands, organic products, homeware, wellness","DALL-E: cottagecore + specific activities; MJ: --stylize 500+"
-19,Brutalist,Architecture,"brutalist architecture, raw concrete, geometric forms, massive scale, exposed structure","harsh shadows, dramatic contrast, overcast sky, stark","low angle looking up, symmetrical, geometric framing, urban context","architectural photography, dramatic, imposing, monumental","soft, decorative, ornate, colorful, natural","Architecture, urban projects, bold branding, editorial","MJ: --style raw; Flux: brutalist + specific building elements"
-20,Surrealist,Art,"surrealism, dreamlike, impossible geometry, melting objects, floating elements, Dali inspired","dramatic spotlight, impossible shadows, ethereal glow, otherworldly","impossible perspective, juxtaposition, dream logic, layered reality","artistic, thought-provoking, museum quality, fantastical","realistic, logical, ordinary, mundane, predictable","Art projects, creative campaigns, album covers, editorial","MJ: --chaos 50 --weird 500; Flux: surrealist + Dali/Magritte"

package/.opencode/skills/ai-artist/data/lighting.csv

@@ -1,19 +0,0 @@
-STT,Lighting Type,Category,Keywords,Description,Mood,Best For,Prompt Keywords,Technical Notes
-1,Golden Hour,Natural,"golden, sunset, warm, soft, magic hour, golden light","Warm directional sunlight during first/last hour of day","Romantic, warm, dreamy, nostalgic","Portraits, landscapes, lifestyle","golden hour lighting, warm sunset light, magic hour, soft directional sunlight","Sun 15-20° above horizon; warm color temp ~3000K; long shadows"
-2,Blue Hour,Natural,"blue, twilight, dusk, dawn, cool, moody, serene","Cool ambient light just after sunset or before sunrise","Calm, mysterious, ethereal, melancholic","Cityscapes, moody portraits, atmospheric scenes","blue hour, twilight lighting, cool ambient light, pre-dawn atmosphere","No direct sun; sky as diffused light source; ~4000-6000K; city lights mix well"
-3,Overcast,Natural,"overcast, cloudy, diffused, soft, even, flat","Evenly diffused light from cloud cover","Neutral, natural, intimate, documentary","Portraits, products, nature close-ups","overcast lighting, soft diffused daylight, cloudy day light","Giant softbox effect; minimal shadows; color temp ~6500K; flattering for skin"
-4,Harsh Midday,Natural,"harsh, midday, direct, high contrast, hard shadows","Direct overhead sunlight with strong shadows","Dramatic, bold, stark, energetic","Fashion, architectural, dramatic scenes","harsh midday sun, direct overhead lighting, high contrast sunlight","Sun directly overhead; hard shadows under features; challenging for portraits"
-5,Rembrandt,Portrait,"rembrandt, dramatic, chiaroscuro, triangle, classic","Single light source creating triangle on cheek","Dramatic, artistic, classic, serious","Dramatic portraits, fine art, character studies","Rembrandt lighting, triangle light on cheek, chiaroscuro, single source dramatic","45° angle, slightly above; small triangle under eye on shadow side"
-6,Butterfly,Portrait,"butterfly, paramount, glamour, beauty, hollywood, classic","Light directly in front and above subject","Glamorous, elegant, flattering, hollywood","Beauty shots, fashion, headshots","butterfly lighting, paramount lighting, beauty light, overhead frontal","Creates shadow under nose; symmetrical; very flattering; fill from below optional"
-7,Split,Portrait,"split, half lit, dramatic, mysterious, moody","Light illuminating exactly half the face","Mysterious, dramatic, intense, artistic","Dramatic portraits, conceptual, film noir","split lighting, half-face illumination, dramatic side lighting","Light at 90° to face; maximum drama; villain lighting; strong emotion"
-8,Loop,Portrait,"loop, natural, versatile, slight shadow, classic","Slight shadow from nose toward cheek","Natural, approachable, versatile, professional","Professional headshots, corporate, general portraits","loop lighting, natural portrait light, slight nose shadow","Between butterfly and Rembrandt; 30-45° from camera; most versatile"
-9,Rim Light,Accent,"rim, back, edge, separation, halo, outline","Light from behind creating edge highlight","Dramatic, separated, defined, ethereal","Silhouettes, product separation, dramatic portraits","rim lighting, backlight, edge light, hair light, subject separation","Behind subject; creates outline; great for hair; adds depth"
-10,Volumetric,Atmospheric,"volumetric, god rays, light rays, foggy, atmospheric","Visible light rays in atmosphere","Mystical, spiritual, dramatic, cinematic","Forests, churches, dramatic scenes, fantasy","volumetric lighting, god rays, light beams, atmospheric fog lighting","Requires particles/fog; directional light source; dramatic effect"
-11,Neon,Artificial,"neon, cyberpunk, colorful, glow, synthetic, urban","Colored artificial light sources creating glow","Futuristic, edgy, urban, energetic","Cyberpunk, night scenes, portraits, gaming","neon lighting, cyberpunk glow, colored light sources, neon signs","Multiple color sources; pink/cyan common; creates color mixing on skin"
-12,Studio Softbox,Studio,"softbox, studio, professional, even, controlled","Large diffused artificial light source","Professional, clean, commercial, polished","Product shots, headshots, e-commerce","studio softbox lighting, professional studio light, soft even illumination","Large source = soft light; multiple setups possible; controllable"
-13,Ring Light,Studio,"ring light, even, beauty, catchlight, influencer","Circular light source around camera lens","Modern, clean, beauty, social media","Beauty content, vlogs, product reviews, selfies","ring light, circular catchlight, even facial illumination","Creates distinctive circular catchlight in eyes; very even; popular for influencers"
-14,Natural Window,Indoor,"window, natural indoor, side light, soft ambient","Daylight coming through windows","Intimate, natural, homey, authentic","Lifestyle, portraits, indoor scenes","natural window light, side lighting from window, soft indoor daylight","Direction and quality vary with time; curtains diffuse; very flattering"
-15,Low Key,Mood,"low key, dark, moody, shadows, dramatic, noir","Mostly shadow with selective illumination","Mysterious, dramatic, artistic, moody","Film noir, dramatic portraits, conceptual","low key lighting, dramatic shadows, selective illumination, dark mood","High contrast; dark background; minimal fill; emphasis on shadows"
-16,High Key,Mood,"high key, bright, clean, minimal shadows, airy","Bright even illumination with minimal shadows","Clean, optimistic, fresh, commercial","Commercial, beauty, product, children","high key lighting, bright even illumination, minimal shadows, clean white","Multiple light sources; white/light backgrounds; reduced contrast"
-17,Practical,Scene,"practical, motivated, realistic, in-scene, diegetic","Light sources visible within the scene","Realistic, cinematic, grounded, authentic","Interior scenes, realistic settings, film","practical lighting, motivated light sources, in-scene illumination","Lamps, candles, screens as light sources; adds realism; matches setting"
-18,Color Gel,Creative,"gel, colored, creative, mood, theatrical","Artificially colored light for creative effect","Creative, emotional, theatrical, stylized","Creative portraits, music, events, artistic","colored gel lighting, theatrical colored light, mood lighting","Colors convey emotion; complementary or contrasting; theatrical effect"

package/.opencode/skills/ai-artist/data/llm-patterns.csv

@@ -1,17 +0,0 @@
-STT,Pattern Name,Category,Template,When to Use,Example,Tips
-1,Role Definition,System,"You are a [ROLE] with expertise in [DOMAIN]. Your responsibilities include [TASKS]. You communicate in a [TONE] manner.","Starting any prompt that requires consistent persona or expertise","You are a senior marketing strategist with 15 years of experience in B2B SaaS. Your responsibilities include campaign planning and content strategy. You communicate in a professional but approachable manner.","Be specific about experience level; include domain constraints; define communication style; avoid conflicting roles"
-2,Context Setting,System,"## Context\n[Background information]\n[Current situation]\n[Relevant constraints]\n[User's goal]","When task requires understanding of specific situation, domain, or constraints","## Context\nYou're helping a startup prepare for Series A funding. The company has 50 employees and $2M ARR. They need investor-ready materials. Budget is limited.","Front-load critical context; be specific about constraints; include what the user ultimately wants to achieve"
-3,Task Decomposition,Instruction,"Break this into steps:\n1. [First action - output X]\n2. [Second action - using X, produce Y]\n3. [Final action - using Y, deliver Z]","Complex multi-step tasks, ensuring nothing is missed, transparent process","Break this into steps:\n1. Analyze the competitor's homepage - list key messages\n2. Using those messages, identify gaps in our positioning\n3. Using gaps, draft 3 new value propositions","Number steps clearly; specify outputs for each step; show dependencies between steps"
-4,Output Format JSON,Format,"Respond in valid JSON only:\n```json\n{schema}\n```\nNo markdown outside JSON. No explanations.","When you need structured, parseable output for code integration","Respond in valid JSON only:\n```json\n{""headline"": ""string"", ""subheadline"": ""string"", ""cta"": ""string"", ""confidence"": ""high|medium|low""}\n```\nNo markdown outside JSON. No explanations.","Provide exact schema; specify all required fields; use enums for constrained values; mention no extra text"
-5,Output Format Markdown,Format,"Format your response as:\n## [Section 1]\n[content]\n\n## [Section 2]\n[content]\n\n### Subsections as needed","Reports, documentation, structured long-form content","Format your response as:\n## Summary\n[2-3 sentences]\n\n## Key Findings\n[bullet list]\n\n## Recommendations\n[numbered list]\n\n## Next Steps\n[action items]","Define heading hierarchy; specify content type for each section (bullets, prose, tables); be consistent"
-6,Few-Shot Learning,Technique,"Example 1:\nInput: [input_1]\nOutput: [output_1]\n\nExample 2:\nInput: [input_2]\nOutput: [output_2]\n\nNow apply to:\nInput: [actual_input]","When output format or reasoning pattern needs demonstration, edge cases, specific style","Example 1:\nInput: 'Increase sales'\nOutput: 'Boost revenue by 25% through targeted upselling campaigns'\n\nExample 2:\nInput: 'Get more customers'\nOutput: 'Acquire 500 new qualified leads via LinkedIn outreach'\n\nNow apply to:\nInput: 'Improve retention'","Use 2-5 diverse examples; include edge cases; match complexity to target; examples should demonstrate exact output format"
-7,Chain of Thought,Technique,"Think through this step by step:\n1. First, consider [aspect 1]\n2. Then, analyze [aspect 2]\n3. Finally, conclude [outcome]\n\nShow your reasoning before the final answer.","Complex reasoning, math problems, logic puzzles, multi-factor decisions","Think through this step by step:\n1. First, identify the user's primary pain point\n2. Then, analyze which features address that pain\n3. Finally, determine the most compelling value proposition\n\nShow your reasoning before the final answer.","Explicitly request reasoning; specify aspects to consider; ask for reasoning BEFORE answer"
-8,Tree of Thoughts,Technique,"Explore 3 different approaches:\n\nApproach 1: [method]\n- Pros:\n- Cons:\n- Success probability:\n\nApproach 2: [method]\n...\n\nEvaluate and select best path.","Strategic decisions, when multiple valid solutions exist, need to compare tradeoffs","Explore 3 different approaches to increase conversion rate:\n\nApproach 1: Landing page redesign\n- Pros:\n- Cons:\n- Success probability:\n\nApproach 2: Email nurture sequence\n...\n\nEvaluate and select best path.","Request multiple approaches; define evaluation criteria; ask for explicit comparison"
-9,Self-Consistency,Technique,"Generate 3 independent solutions to this problem. Then compare them and provide the answer that appears most frequently or has strongest reasoning.","Math, factual questions, logic problems where verification matters","Generate 3 independent solutions to this pricing strategy problem. Then compare them and provide the answer that appears most frequently or has strongest reasoning.","Use with temperature >0; request explicit comparison; works best for verifiable answers"
-10,ReAct Pattern,Technique,"Follow this pattern:\nThought: [current reasoning]\nAction: [tool or step to take]\nObservation: [result of action]\n...repeat...\nFinal Answer: [conclusion]","Agent-like tasks, research, when tools/steps need to be dynamic","Thought: I need to understand the competitor landscape first\nAction: Research top 3 competitors' pricing pages\nObservation: Found competitor A uses freemium, B uses trials...\nThought: Now I should compare to our current model\n...","Define available actions; show observation format; iterate until conclusion"
-11,Self-Refine,Technique,"Step 1: Generate initial response\nStep 2: Critique your response - what's wrong or could be better?\nStep 3: Refine based on critique\nStep 4: Repeat until satisfactory or limit reached","Creative content, writing tasks, iterative improvement needed","Generate a headline for our product launch.\n\nThen critique it:\n- Is it specific enough?\n- Does it convey value?\n- Is it memorable?\n\nRefine based on your critique.","Specify critique criteria; set iteration limit; can request 2-3 rounds explicitly"
-12,Constraint Definition,Control,"Constraints:\n- DO: [allowed actions]\n- DO NOT: [prohibited actions]\n- ALWAYS: [required behaviors]\n- NEVER: [forbidden behaviors]","Safety, brand voice, legal compliance, consistent behavior boundaries","Constraints:\n- DO: Use professional language, cite sources\n- DO NOT: Make claims without evidence, use superlatives\n- ALWAYS: Include disclaimers for estimates\n- NEVER: Promise specific ROI numbers","Group by type (DO/DON'T); be specific; explain why for critical constraints"
-13,Persona Constraint,Control,"You only respond as [persona]. You never break character. Your responses always reflect [traits]. If asked something outside your expertise, respond as [persona] would.","Chatbots, roleplay, character-consistent interactions","You only respond as a helpful customer support agent for TechCorp. You never break character. Your responses always reflect patience and empathy. If asked something outside your expertise, politely redirect to appropriate resources.","Define persona completely; specify what to do when pushed off-script; include tone traits"
-14,Confidence Scoring,Control,"For each point, indicate your confidence:\n- HIGH: Strong evidence, well-established\n- MEDIUM: Reasonable inference, some uncertainty\n- LOW: Speculative, limited information\n\nIf LOW, explain what would increase confidence.","Factual queries, research, when reliability matters","For each recommendation, indicate your confidence:\n- HIGH: Proven tactic with clear data\n- MEDIUM: Common practice, results vary\n- LOW: Experimental, limited evidence\n\nIf LOW, explain what would increase confidence.","Define confidence levels clearly; require explanation for low confidence; calibrates expectations"
-15,Hallucination Reduction,Control,"Only use information from the provided context. If the answer isn't in the context, say 'I don't have information about this in the provided documents.' Do not infer or make assumptions beyond what's explicitly stated.","RAG systems, document Q&A, when accuracy is critical","Answer based ONLY on the provided customer data. If the answer isn't in the data, say 'This information is not available in the customer records.' Do not make assumptions about customer behavior.","Explicitly forbid inference; provide exact phrase for 'don't know'; repeat instruction"
-16,XML Tagging Claude,Format,"<context>\n[background]\n</context>\n\n<task>\n[specific action]\n</task>\n\n<format>\n[output structure]\n</format>\n\n<constraints>\n[limits]\n</constraints>","Claude specifically, clear section delineation, complex prompts","<context>\nYou're reviewing a marketing campaign for a B2B software company targeting enterprise clients.\n</context>\n\n<task>\nIdentify the top 3 weaknesses in the attached campaign brief.\n</task>\n\n<format>\nBullet list with specific examples.\n</format>","Claude-specific feature; use consistent tag names; can nest tags; good for separating concerns"

package/.opencode/skills/ai-artist/data/nano-banana-templates.csv

@@ -1,17 +0,0 @@
-Category,Template Name,Keywords,Prompt Template,Aspect Ratio,Tips
-Quote Card,Wide Quote Card Portrait,"quote,inspiration,motivational,portrait,typography","A wide quote card featuring a famous person, with a {background_color} background and a {font_color} serif font for the quote: ""{quote}"" and smaller text: ""—{author}."" There is a large, subtle quotation mark before the text. The portrait of the person is on the left, the text on the right. The text occupies two-thirds of the image and the portrait one-third, with a slight gradient transition effect on the portrait.",16:9,Use brown/earthy backgrounds with light-gold text for elegance
-Infographic,Bento Grid Product Infographic,"infographic,product,bento,glass,premium,educational","Premium liquid glass Bento grid product infographic with 8 modules. Product: {product}. Language: {language}. 1) Hero card (28-30%): Product photo/3D glass rendering. 2) Core Benefits: 4 key benefits with icons. 3) How to Use: 4 usage methods with icons. 4) Key Metrics: 5 data points. 5) Who It's For: 4 recommended + 3 caution groups. 6) Important Notes: 4 precautions. 7) Quick Reference: Specs/certifications. 8) Did You Know: 3 interesting facts. Background: Apple liquid glass cards (85-90% transparent). Ethereal macro/pattern/context background.",16:9,Use consistent icon style; ensure text legibility at mobile size
-Header Banner,Hand-drawn Blog Header,"header,banner,blog,hand-drawn,gradient,tech","A header image for a blog article where a person introduces ""{topic}"". Aspect ratio: horizontal 16:9. Style: simple, hand-drawn style, italic lines. Colors: {color1} and {color2} gradient. Title text: ""{title}"" in clean typography.",16:9,Keep space for text overlay; use complementary gradient colors
-Map,Watercolor Map with Labels,"map,watercolor,educational,geography,artistic","Generate a map of {country} in watercolor style, on which all {regions} are labeled in ballpoint pen handwriting. Soft color gradients for each region. Paper texture visible.",1:1,Use muted watercolor palette; ensure label readability
-Portrait,2x2 Grid Photo Studio,"portrait,grid,fashion,studio,magazine","High-end photo studio 2x2 grid photo. Top-left panel ({color1} background): Subject wears {outfit1}, holds prop with ""{text1}"". Top-right panel ({color2} background): Same person in {outfit2}, holds prop with ""{text2}"". Bottom-left panel ({color3} background): Same person in {outfit3}, holds prop with ""{text3}"". Bottom-right panel ({color4} background): Same person in {outfit4}, completing the composition. Clear makeup, bright ring light, 85mm lens, f/1.8 aperture, fashion magazine style. MUST maintain consistent facial features across all panels.",1:1,Maintain identity lock across panels; use complementary color scheme
-Patent,Vintage Patent Document,"patent,vintage,technical,document,invention","A vintage patent document for {invention}, styled after late 1800s United States Patent Office filings. Precise technical drawings with numbered callouts (Fig. 1, Fig. 2, Fig. 3) showing front, side, and exploded views. Handwritten annotations in fountain-pen ink describe mechanisms. Aged ivory paper with foxing stains and soft fold creases. Official embossed seal and red wax stamp in corner. Hand-signed inventor's name and date at bottom. Authoritative, historic, slightly mysterious feel.",3:4,Include multiple figure views; add authentic aging effects
-Chalkboard,Chalkboard News Summary,"educational,chalkboard,news,diagram,hand-written","Using the following content, summarize the information in a chalkboard-style, hand-written look. Break it down with diagrams and easy-to-understand expressions as if a teacher had written it. Topic: {topic}. Key points to cover: {points}. Include arrows, boxes, and visual connections between concepts.",16:9,Use chalk texture; include visual hierarchy with boxes and arrows
-Mirror Selfie,Otaku Room Mirror Selfie,"selfie,mirror,room,lifestyle,casual","Scene: Mirror selfie in an otaku-style room corner, {color} tone. Subject: {gender}, around {age}, {ethnicity}, {body_type}. Outfit: {clothing}. Room elements: {room_details}. Smartphone held for selfie via mirror. Natural lighting from window. Authentic lifestyle photography feel.",9:16,Include room context; ensure natural pose
-Style Transform,Ukiyo-e Modern Reimagining,"ukiyo-e,Japanese,woodblock,artistic,transformation","A Japanese Edo-period Ukiyo-e woodblock print reimagining {modern_scene}. Collaboration between masters like Hokusai and Hiroshige, reimagining modern technology through an ancient lens. Characters wear Edo-era kimono but perform modern actions. Tech transformation: {modern_item} becomes {traditional_item}. Composition: Flattened perspective, bold ink outlines. Texture: Wood grain, paper fibers, pigment bleeding. Colors: Prussian blue, vermilion red, muted ochre. Include vertical Japanese calligraphy and red artist seal.",3:4,Transform modern elements into period equivalents
-Social Banner,Tech Conference Announcement,"conference,tech,announcement,professional,corporate","A professional tech conference promotional image. Scene: Futuristic {venue_type} where humans and AI work together harmoniously. Holographic display shows ""{date}"". Color palette: deep {primary_color} as primary, electric {accent_color} as accent, pure white text elements. {style} aesthetic. Clean minimal design with subtle gradient lighting. Professional photography style, soft ambient lighting. Text overlay area at bottom for event details. NEVER include unwanted text. DO NOT add watermarks.",16:9,Reserve bottom 20% for text overlay; use corporate color scheme
-Product Hero,Premium Product on Surface,"product,commercial,studio,luxury,hero","A premium {product} positioned on {surface}. Materials: {material_finish} finish catching light. Lighting: {lighting_setup} creating {mood} mood. Camera: {angle} angle, 85mm lens, f/2.8. Background: {background_type}, slightly out of focus. Style: {style} commercial photography. Highlights on edges, subtle reflections. NEVER add text or watermarks.",1:1,Use 3-point lighting; include subtle reflections
-Character,Cyberpunk Character Portrait,"character,cyberpunk,neon,portrait,sci-fi","A {style} character portrait in cyberpunk setting. Subject: {description} with {distinctive_features}. Outfit: {outfit} with neon accents. Background: Rain-slicked street with holographic ads, neon signs in {colors}. Lighting: Neon rim light from behind, soft key light on face. Atmosphere: Moody, atmospheric fog. Camera: 85mm portrait lens, shallow DOF. STRICT identity lock if reference provided.",2:3,Use complementary neon colors; include atmospheric effects
-Food,Overhead Food Photography,"food,overhead,culinary,lifestyle,restaurant","Overhead shot of {dish} on {surface}. Plating: {plating_style} presentation. Props: {props} arranged around main dish. Lighting: {lighting} creating appetizing shadows. Include human element: {human_element}. Steam/freshness visible. Color palette: {colors}. Style: {magazine} magazine quality. NEVER add text.",1:1,Include human hand or utensil for scale; show steam/freshness
-Architecture,Interior Visualization,"interior,architecture,modern,visualization,lifestyle","A {style} interior photograph of {room_type}. View: {view_angle} angle capturing full space. Materials: {materials} creating {atmosphere} feel. Lighting: {time_of_day} light through {window_type}. Furniture: {furniture_style} pieces. Decorative elements: {decor}. Camera: Wide angle architectural lens, everything in focus. NEVER include people unless specified.",16:9,Use natural lighting; show material textures
-Speaker,Conference Speaker Spotlight,"speaker,conference,professional,portrait,tech","Professional conference speaker promotional image. Subject: {demographics} presenting on stage or in modern setting. Background: Abstract flowing data visualizations, {topic}-related holographic elements. Color scheme: {primary}, {secondary}, {accent}. Lighting: Cinematic with soft key light on face, dramatic rim lighting. Modern corporate photography style. Clean space at bottom for speaker name/title overlay. NEVER include text in image.",1:1,Leave space for text overlay; use brand colors
-Event CTA,Event Registration Urgency,"event,registration,urgency,countdown,promotional","Dynamic call-to-action promotional image for {event_type}. Scene: Excited people entering modern {venue} with {brand} elements. Countdown visualization floating in air. Golden VIP pass/ticket element representing {benefit}. Limited seats visual metaphor. Color palette: urgent {color1}, premium {color2}, trust {color3}. Energy and excitement atmosphere with motion blur on crowd. Clean bottom area for registration CTA. NEVER include specific text.",1:1,Use motion blur for energy; include urgency elements

package/.opencode/skills/ai-artist/data/platforms.csv

@@ -1,11 +0,0 @@
-STT,Platform,Type,Prompt Style,Key Parameters,Syntax Examples,Strengths,Limitations,Best Practices
-1,Midjourney v6.1,Image,"Descriptive phrases, comma-separated concepts, style references","--ar (aspect ratio), --style (raw/default), --stylize 0-1000, --chaos 0-100, --weird 0-3000, --quality, --seed, --no, --tile","portrait of woman, golden hour, 85mm lens --ar 2:3 --style raw --v 6.1","Artistic interpretation, coherent compositions, beautiful aesthetics, excellent at photography styles","Limited text rendering, no negative prompt param (use --no), Discord-only interface","Place important concepts first; use :: for multi-prompting (cat::2 dog::1); --style raw for photorealism; /describe for reverse prompting"
-2,DALL-E 3,Image,"Natural language descriptions, paragraph form, conversational","HD quality (mention in prompt), vivid style (mention in prompt), size: 1024x1024/1792x1024/1024x1792","Create an HD image of a serene mountain lake at sunrise, with mist rising from the water and pine trees reflected in the still surface. The style should be vivid and photorealistic.","Excellent text rendering, follows complex instructions, natural language understanding, API access","No parameters, no negative prompts, content filtering, less artistic control","Be descriptive but natural; mention 'HD quality' for higher detail; specify text content, font, and placement explicitly; avoid keyword lists"
-3,Stable Diffusion XL,Image,"Weighted keywords, positive/negative prompts, technical terms, LoRA references","CFG scale 5-15, steps 20-50, sampler (DPM++ 2M Karras), seed, LoRA weights, embeddings","(masterpiece:1.4), (best quality:1.3), portrait of woman, soft lighting, (sharp focus:1.2), Negative: ugly, blurry, deformed","Open source, highly customizable, LoRAs, local control, no content filter, precise control","Requires technical knowledge, hardware requirements, can produce inconsistent results","Use (word:weight) for emphasis; pair positive/negative prompts; test samplers; use quality tags; CFG 7-9 for balance"
-4,Flux 1.1,Image,"Natural language, style mixing, descriptive sentences","--guidance 2-5, aspect ratio in prompt, style keywords","A stunning photograph of an alpine meadow in summer, captured with a professional camera, natural soft lighting, mountains in background, wildflowers in foreground, 16:9 aspect ratio","Excellent prompt following, natural language, good at mixing styles, fast generation","Newer platform, smaller LoRA ecosystem, fewer community resources","Use natural sentences; mention aspect ratio in text; lower guidance for creativity; be specific about camera/lens for photos"
-5,Imagen 3,Image,"Descriptive natural language, detailed scene descriptions","Aspect ratio via text, style via description","A photorealistic image of a modern home office, 16:9 landscape format, soft natural lighting from large windows, minimalist Scandinavian design, warm wood tones","Strong prompt following, excellent at text, Google integration, high quality","Limited availability, API access required, content policies","Describe scenes fully; mention format in text; use photography terms for realism"
-6,Veo 2,Video,"Cinematography terms, scene descriptions, motion keywords","Duration, aspect ratio, camera movements in prompt","Cinematic slow-motion shot of coffee being poured into a cup, steam rising, golden morning light, shallow depth of field, camera slowly pushes in, 16:9","Native video generation, camera movement understanding, temporal consistency","Short clips only, limited control over timing, high compute","Use cinematography terms (pan, tilt, dolly); describe motion explicitly; specify duration; mention camera movements"
-7,Runway Gen-3,Video,"Scene description with motion, temporal keywords, style references","Duration 4-18s, aspect ratio, motion amount","Aerial drone shot flying over a misty forest at dawn, slowly revealing a hidden lake, cinematic color grading, smooth continuous motion","Good motion quality, style transfer, image-to-video, extend clips","Processing time, credits-based, limited duration","Describe movement direction and speed; use 'slowly', 'smoothly' etc.; start with strong first frame"
-8,Gemini Imagen,Image,"Narrative paragraphs, conversational descriptions, multi-image context","32K context, aspect ratios via text, thinking mode for complex","Please create an image of a cozy reading nook in a bay window. The scene should have warm afternoon light streaming in, comfortable cushions in earth tones, a stack of leather-bound books, and a steaming cup of tea. The style should feel like a watercolor illustration with soft edges.","Large context window (32K), multi-image input (up to 14), search grounding, thinking mode","Google ecosystem required, content policies, less artistic styles","Use narrative descriptions; ALL CAPS for critical requirements; Markdown lists for rules; photography terms improve quality"
-9,Claude Artifacts,Code/SVG,"Technical specifications, component requirements, design system references","Artifacts for code, SVG, React components","Create an SVG icon for a settings gear with 8 teeth, 24x24 viewBox, stroke-width 2, using currentColor for flexibility. Include proper accessibility attributes.","Perfect for code, diagrams, SVGs, technical accuracy, reasoning about design","Not image generation, limited to code/SVG/diagrams","Specify exact dimensions; mention accessibility; provide design system context; request semantic markup"
-10,Nano Banana,Image,"Narrative style, photography terms, hex colors for precision, multi-image reference","32K context, aspect ratios, thinking mode, up to 14 reference images","Captured with 85mm lens, soft bokeh background, natural lighting, subject: professional woman in business casual, color accent #9F2B68 magenta","Gemini-based, massive context, hex color precision, complex prompts, multi-image input","Google API required, content moderation","ALL CAPS for critical elements; hex codes for exact colors; mention lens/camera specs; can reference multiple input images"

package/.opencode/skills/ai-artist/data/quality-modifiers.csv

@@ -1,26 +0,0 @@
-STT,Modifier,Category,Effect,Platform Compatibility,Example Usage,When to Use
-1,8k uhd,Resolution,"Ultra high resolution, extremely detailed","MJ: yes, SD: quality tag, DALL-E: HD in text, Flux: yes","portrait of woman, 8k uhd, highly detailed","Final outputs needing maximum detail"
-2,4k,Resolution,"High resolution, detailed","All platforms","landscape photography, 4k resolution","Standard high-quality outputs"
-3,highly detailed,Detail,"Increases overall detail level","All platforms","highly detailed mechanical watch, intricate gears","When fine details matter (products, architecture)"
-4,intricate details,Detail,"Focus on fine, complex elements","MJ: strong, SD: strong, DALL-E: moderate, Flux: yes","intricate details, ornate frame, delicate patterns","Decorative items, jewelry, architecture"
-5,photorealistic,Style,"Maximum realism, like a photograph","MJ: --style raw, SD: photorealistic tag, DALL-E: natural, Flux: yes","photorealistic portrait, natural skin texture","Product shots, portraits, stock photos"
-6,hyperrealistic,Style,"Beyond realistic, almost uncanny detail","MJ: strong, SD: strong, DALL-E: less effective, Flux: yes","hyperrealistic water droplet, micro details visible","Macro shots, extreme close-ups"
-7,professional photography,Quality,"Studio quality, commercial grade","All platforms","professional photography, studio lighting, clean background","E-commerce, headshots, marketing materials"
-8,masterpiece,Quality,"Highest artistic quality","SD: very strong, MJ: moderate, DALL-E: weak, Flux: moderate","masterpiece, best quality, award-winning","SD priority tag for quality boost"
-9,best quality,Quality,"Top-tier output quality","SD: strong quality tag, others: moderate","best quality, masterpiece, detailed","SD primary quality boosting tag"
-10,award-winning,Quality,"Prestigious, exceptional quality","All platforms","award-winning photography, National Geographic style","Editorial, competitions, high-end marketing"
-11,trending on artstation,Quality,"Popular digital art style","SD: strong, MJ: moderate, others: weak","concept art, trending on artstation","Digital art, concept art, fantasy"
-12,sharp focus,Technical,"Crisp, clear details, no blur","All platforms","sharp focus, detailed eyes, crisp edges","Products, portraits, text, technical subjects"
-13,soft focus,Technical,"Dreamy, romantic blur effect","All platforms","soft focus, romantic portrait, ethereal","Beauty shots, dream sequences, nostalgia"
-14,shallow depth of field,Technical,"Blurred background, subject isolation","All platforms","shallow depth of field, bokeh, 85mm lens","Portraits, product isolation, artistic"
-15,motion blur,Technical,"Sense of movement and speed","All platforms","motion blur, speed lines, dynamic action","Action shots, sports, cars, movement"
-16,volumetric lighting,Lighting,"Light rays visible in atmosphere","MJ: strong, SD: strong, Flux: yes, DALL-E: describe","volumetric lighting, god rays, atmospheric haze","Dramatic scenes, forests, interiors"
-17,cinematic lighting,Lighting,"Movie-quality dramatic lighting","All platforms","cinematic lighting, dramatic shadows, film quality","Hero shots, posters, dramatic content"
-18,studio lighting,Lighting,"Professional controlled lighting","All platforms","studio lighting, soft box, even illumination","Products, portraits, commercial"
-19,golden hour,Lighting,"Warm sunset/sunrise light","All platforms","golden hour, warm tones, long shadows","Landscapes, portraits, lifestyle"
-20,rim lighting,Lighting,"Edge-lit subject, dramatic separation","All platforms","rim lighting, backlit, edge glow, halo effect","Dramatic portraits, silhouettes"
-21,octane render,Technical,"Photorealistic 3D rendering","SD: strong, MJ: yes, Flux: yes","octane render, ray tracing, CGI quality","3D scenes, products, architecture"
-22,unreal engine,Technical,"Game engine quality rendering","SD: strong, MJ: yes, Flux: yes","unreal engine 5, real-time rendering, next-gen graphics","Game assets, cinematic scenes"
-23,concept art,Style,"Professional pre-production art","All platforms","concept art, character design sheet, game art","Character design, worldbuilding, pitches"
-24,matte painting,Style,"Digital painting for film backgrounds","All platforms","matte painting, epic landscape, film background","Fantasy landscapes, sci-fi backgrounds"
-25,RAW photo,Technical,"Unprocessed, maximum data capture","MJ: --style raw, SD: yes, DALL-E: describe, Flux: yes","RAW photo, unprocessed, maximum detail","Photorealistic, needs post-processing look"

package/.opencode/skills/ai-artist/data/styles.csv

@@ -1,26 +0,0 @@
-STT,Style Name,Category,Keywords,Description,Key Characteristics,Color Palette,Best For,Platforms,Prompt Keywords
-1,Photorealistic,Photography,"photo, realistic, camera, natural, authentic, real, photography","Ultra-realistic images that mimic professional photography","Natural lighting, authentic textures, camera-specific artifacts, realistic proportions","Natural colors, realistic skin tones, environmental colors","Portraits, product shots, scenes","Nano Banana, Midjourney, SD","photorealistic, ultra realistic, 8K, RAW photo, natural lighting, professional photography"
-2,Cinematic,Photography,"film, movie, cinematic, dramatic, theatrical, hollywood, widescreen","Film-like imagery with dramatic lighting and composition","Anamorphic lens effects, color grading, shallow DOF, dramatic lighting, widescreen","Teal-orange, desaturated, film stock colors","Movie scenes, dramatic portraits, storytelling","Midjourney, Nano Banana","cinematic, film still, anamorphic, color graded, shallow depth of field, dramatic lighting"
-3,Anime Manga,Illustration,"anime, manga, Japanese, otaku, animated, cel-shaded","Japanese animation and comic style artwork","Large expressive eyes, stylized proportions, cel shading, dynamic poses, speed lines","Vibrant, saturated, anime-typical palettes","Characters, fan art, storytelling, avatars","Midjourney, SD, Nano Banana","anime style, manga, cel shaded, Japanese animation, vibrant colors, expressive eyes"
-4,3D Render,Digital,"3D, render, CGI, Blender, Cinema4D, octane, dimensional","Computer-generated 3D imagery with realistic or stylized rendering","Material reflections, global illumination, subsurface scattering, hard/soft shadows","Scene-dependent, PBR materials","Products, characters, architecture, abstract","Midjourney, SD, Nano Banana","3D render, octane render, Cinema4D, Blender, CGI, ray tracing, PBR materials"
-5,Illustration,Art,"illustrated, drawn, digital art, vector, graphic, artistic","Digital or traditional illustration styles","Clean lines, stylized forms, artistic interpretation, consistent style","Style-dependent, often bold or pastel","Editorial, children's books, branding","Midjourney, DALL-E, SD","illustration, digital art, illustrated, artistic, stylized, graphic design"
-6,Pixel Art,Retro,"pixel, 8-bit, 16-bit, retro, game, sprite, nostalgic","Retro video game aesthetic with visible pixels","Grid-based, limited color palette, dithering, nostalgic feel, sprite-like","Limited palette, 8-bit/16-bit colors","Games, avatars, nostalgic content","Midjourney, SD","pixel art, 8-bit, 16-bit, retro gaming, sprite, pixelated"
-7,Watercolor,Traditional,"watercolor, paint, artistic, soft, flowing, traditional, aquarelle","Traditional watercolor painting aesthetic","Soft edges, color bleeds, paper texture, transparent layers, organic flow","Soft, flowing, often pastel or earthy","Portraits, landscapes, artistic content","Midjourney, SD, DALL-E","watercolor painting, aquarelle, soft edges, color bleed, paper texture, artistic"
-8,Oil Painting,Traditional,"oil, painting, classical, fine art, canvas, masterpiece, textured","Classical oil painting technique","Visible brushstrokes, rich textures, layered colors, impasto, chiaroscuro","Rich, deep, Old Master palette","Portraits, landscapes, fine art","Midjourney, SD, DALL-E","oil painting, impasto, brushstrokes, classical art, canvas texture, fine art"
-9,Sketch Line Art,Drawing,"sketch, line art, drawing, pencil, ink, minimal, outlined","Hand-drawn sketch or line art style","Clean or rough lines, minimal shading, crosshatching, pen/pencil textures","Monochrome, limited color","Concepts, technical, artistic","Midjourney, SD, DALL-E","sketch, line art, pencil drawing, ink drawing, hand-drawn, crosshatching"
-10,Ink Chinese Style,Traditional,"ink wash, Chinese, Japanese, sumi-e, brush, traditional, Eastern","East Asian ink wash painting technique","Brush strokes, ink gradients, negative space, calligraphic elements, minimalism","Black ink, subtle grays, minimal color accents","Nature, calligraphy, cultural art","Midjourney, SD","ink wash, sumi-e, Chinese painting, brush strokes, traditional Asian art"
-11,Chibi Q-Style,Illustration,"chibi, kawaii, cute, SD, super deformed, adorable, tiny","Super-deformed cute character style","Oversized head, small body, simple features, kawaii expressions, round shapes","Bright, pastel, candy colors","Mascots, stickers, merchandise","Midjourney, SD","chibi, kawaii, super deformed, cute, big head, small body, adorable"
-12,Isometric,Technical,"isometric, flat, geometric, technical, diagram, 30-degree","Isometric projection technical illustration","30-degree angles, no vanishing point, geometric precision, clean lines","Often bold, flat colors","Infographics, games, technical","Midjourney, SD, DALL-E","isometric, isometric view, 30 degree angle, flat design, geometric, technical illustration"
-13,Cyberpunk Sci-Fi,Genre,"cyberpunk, neon, future, sci-fi, dystopian, tech noir, blade runner","Futuristic dystopian aesthetic","Neon lights, rain-slicked streets, high-tech low-life, holographics, chrome","Neon pink, cyan, purple on dark","Sci-fi, gaming, urban","Midjourney, SD, Nano Banana","cyberpunk, neon lights, dystopian future, sci-fi, blade runner, tech noir"
-14,Retro Vintage,Nostalgic,"retro, vintage, old school, nostalgia, classic, throwback, period","Nostalgic imagery from past eras","Era-specific aesthetics, grain/texture, period-accurate colors, vintage wear","Muted, sepia, era-specific palettes","Period pieces, nostalgia marketing","Midjourney, DALL-E, SD","vintage, retro, 1950s/60s/70s/80s, nostalgic, old school, period accurate"
-15,Minimalism,Modern,"minimal, clean, simple, modern, white space, essential, less","Clean, essential design with maximum white space","Simple forms, limited elements, high contrast, essential details only","Monochrome, limited accent colors","Modern branding, UI/UX, editorial","Midjourney, DALL-E","minimalist, minimal, clean design, simple, white space, essential"
-16,Vaporwave,Aesthetic,"vaporwave, aesthetic, 90s, glitch, synthwave, retro-futuristic, nostalgic","90s-inspired surreal aesthetic","Glitch effects, Roman statues, gradient skies, grid patterns, Japanese text","Pink, purple, cyan, sunset gradients","Music, artistic, aesthetic content","Midjourney, SD","vaporwave, aesthetic, synthwave, 90s, glitch, roman statue, sunset gradient"
-17,Glassmorphism,UI,"glass, frosted, transparent, blur, modern, UI, Apple","Frosted glass UI aesthetic","Transparency, backdrop blur, subtle borders, layered depth, vibrant backgrounds","Translucent white on vibrant BG","UI mockups, modern design","Nano Banana, Midjourney","glassmorphism, frosted glass, backdrop blur, translucent, modern UI"
-18,Claymorphism,UI,"clay, soft, 3D, playful, rounded, bubbly, toy-like","Soft 3D clay-like UI aesthetic","Rounded forms, soft shadows, pastel colors, toy-like appearance, friendly","Soft pastels, warm tones","Friendly apps, children's content","Midjourney, SD","claymorphism, clay 3D, soft shadows, rounded, pastel, playful"
-19,Portrait Photography,Photography,"portrait, headshot, face, professional, fashion, editorial, beauty","Professional portrait photography","Lighting setups (Rembrandt, butterfly), skin detail, eye focus, composition","Natural skin tones, background depends on style","Portraits, headshots, fashion","Nano Banana, Midjourney","portrait photography, professional headshot, studio lighting, 85mm lens, bokeh"
-20,Fashion Editorial,Photography,"fashion, editorial, vogue, model, haute couture, magazine, runway","High fashion magazine photography","Dramatic poses, designer clothing, artistic lighting, editorial composition","High fashion palettes, often bold or muted","Fashion, luxury, editorial","Midjourney, Nano Banana","fashion editorial, vogue, haute couture, model photography, dramatic lighting"
-21,Product Commercial,Photography,"product, commercial, advertising, studio, hero shot, professional","Professional product photography","Clean isolation, material accuracy, controlled lighting, hero angles","Product-accurate, often neutral BG","E-commerce, advertising","Nano Banana, Midjourney, SD","product photography, commercial, studio lighting, white background, hero shot"
-22,Landscape Nature,Photography,"landscape, nature, outdoor, scenic, wilderness, vista, environment","Natural landscape photography","Wide vistas, natural lighting, composition rules, atmospheric effects","Natural greens, blues, earth tones","Travel, nature, wallpapers","Midjourney, SD, Nano Banana","landscape photography, nature, scenic, golden hour, wide angle, vista"
-23,Street Documentary,Photography,"street, documentary, candid, urban, lifestyle, real, authentic","Candid street and documentary photography","Authentic moments, urban settings, available light, spontaneous composition","Natural, urban colors","Lifestyle, journalism, authentic","Midjourney, Nano Banana","street photography, documentary, candid, urban, authentic, lifestyle"
-24,Macro Close-up,Photography,"macro, close-up, detail, micro, extreme detail, texture","Extreme close-up detail photography","Shallow DOF, extreme detail, texture visibility, scale distortion","Subject-dependent","Products, nature, textures","Midjourney, SD, Nano Banana","macro photography, close-up, extreme detail, shallow depth of field, texture"
-25,Ukiyo-e,Traditional,"ukiyo-e, Japanese, woodblock, Hokusai, Hiroshige, Edo, waves","Traditional Japanese woodblock print style","Flat colors, bold outlines, wave patterns, woodgrain texture, calligraphy","Prussian blue, vermilion, muted ochre","Japanese themes, artistic","Midjourney, SD","ukiyo-e, Japanese woodblock print, Hokusai, flat colors, bold outlines"

package/.opencode/skills/ai-artist/data/subjects.csv

@@ -1,17 +0,0 @@
-STT,Subject Type,Category,Prompt Modifiers,Detail Keywords,Common Issues,Tips
-1,Human Portrait,People,"age (young/middle-aged/elderly), ethnicity, gender expression, emotional state, attire","detailed face, expressive eyes, natural skin texture, subtle wrinkles, individual pores, realistic hair strands","distorted hands, extra fingers, asymmetric face, uncanny valley, wrong eye direction","Specify age and ethnicity if important; mention hand position explicitly; use 'looking at camera' for eye contact; add 'realistic skin' for photorealism"
-2,Full Body Human,People,"body type, pose (standing/sitting/dynamic), clothing style, context/setting","anatomically correct, natural pose, proper proportions, realistic fabric, natural stance","extra limbs, wrong proportions, floating, awkward pose, disconnected limbs","Describe pose in detail; mention ground/surface; specify clothing completely; use reference poses like 'contrapposto' or 'T-pose'"
-3,Hands Close-up,People,"gesture, finger position, nail style, accessories (rings), activity","five fingers, anatomically correct hands, natural finger positions, realistic knuckles","extra fingers, merged fingers, wrong thumb position, impossible bends","Always specify 'five fingers'; describe exact gesture (holding pen, pointing); mention 'anatomically correct hands' explicitly; use negative prompts for deformities"
-4,Group of People,People,"number of people, arrangement, interaction, relationship, diversity","distinct faces, proper spacing, natural grouping, individual characteristics","face merge, clone faces, wrong count, floating people, overlapping bodies","Specify exact number; describe positions (standing behind, sitting next to); mention each person's distinguishing features; use 'diverse group' if needed"
-5,Animal Portrait,Animals,"species, breed, age, expression, pose, setting","detailed fur/feathers/scales, expressive eyes, natural anatomy, realistic texture","wrong anatomy, human-like features, distorted proportions, incorrect markings","Research breed-specific features; mention texture (fluffy, smooth, spotted); describe eyes and expression; use species-specific terms"
-6,Wildlife Action,Animals,"species, action, environment, time of day, weather","dynamic pose, motion blur appropriate, natural behavior, habitat accuracy","frozen motion, unnatural pose, wrong habitat, domestic behavior in wild animals","Describe specific action (hunting, flying, running); mention habitat; use 'wildlife photography' + lens specs; include environmental context"
-7,Fantasy Creature,Creatures,"creature type, size reference, features, personality, hybrid elements","detailed scales/fur/wings, glowing elements, magical effects, anatomical consistency","inconsistent features, wrong scale, unclear anatomy, conflicting elements","Provide size reference (as tall as a horse); describe hybrid elements clearly; mention texture for each body part; specify magical elements"
-8,Architecture Exterior,Architecture,"building type, style, era, condition, time of day, weather","detailed facade, accurate proportions, realistic materials, proper perspective","distorted perspective, floating elements, wrong scale, anachronistic elements","Specify architectural style (Gothic, Modernist); mention materials (brick, glass); describe lighting and weather; include surrounding context"
-9,Interior Design,Architecture,"room type, style, color scheme, lighting, furniture arrangement","realistic textures, proper scale, natural lighting, cohesive design","impossible physics, floating furniture, wrong proportions, inconsistent style","Describe room purpose; mention specific furniture pieces; specify light sources (window, lamp); include color palette or style (Scandinavian, Industrial)"
-10,Product Packshot,Product,"product type, angle, background, lighting setup, brand style","pristine condition, sharp edges, accurate reflections, professional lighting","dirty/scratched appearance, wrong reflections, distorted shape, unrealistic shadows","Specify exact angle (45-degree, front-facing); describe background (white, gradient); mention 'commercial photography' + 'studio lighting'"
-11,Food Photography,Product,"dish type, cuisine, plating style, props, background","appetizing colors, realistic textures, proper steam/moisture, natural garnish","unappetizing colors, wrong textures, plastic look, unnatural arrangement","Use food photography terms; mention 'food styling'; describe textures (crispy, juicy, creamy); include appropriate props (utensils, napkin)"
-12,Tech Product,Product,"device type, angle, screen content, environment, lifestyle context","sleek surfaces, accurate reflections, realistic screen, proper branding space","distorted screens, wrong proportions, unrealistic reflections, visible logos issues","Show device in use context; describe screen content if visible; mention 'product photography' + 'studio lighting'; be careful with text on screens"
-13,Nature Landscape,Landscape,"terrain type, time of day, season, weather, focal point","dramatic sky, layered depth, natural colors, atmospheric perspective","flat composition, unrealistic colors, scale issues, anachronistic elements","Use landscape photography terms; specify time of day (golden hour, blue hour); describe foreground, midground, background; mention weather conditions"
-14,Urban Cityscape,Landscape,"city/style, time of day, weather, aerial or street level, mood","architectural detail, city lights, atmospheric haze, realistic scale","repetitive buildings, wrong architecture style, perspective issues, empty streets","Specify city or architectural style; mention vantage point; describe lighting (neon, street lamps); include human elements for scale"
-15,Abstract Art,Abstract,"shapes, colors, texture, movement, emotion, style reference","flowing forms, color harmony, textural variation, balanced composition","muddy colors, lack of focal point, chaotic without intention, generic patterns","Specify color palette; describe movement or flow; reference art movements (Abstract Expressionism); mention texture (smooth, layered, impasto)"
-16,Text/Typography,Text,"font style, size, color, placement, background, effect","sharp edges, consistent letterforms, readable, proper kerning","illegible text, wrong letters, inconsistent font, bleeding edges","For DALL-E: describe font, size, exact text, placement; For MJ: use text in quotes, keep short; For SD: use ControlNet for text"

package/.opencode/skills/ai-artist/data/techniques.csv

@@ -1,19 +0,0 @@
-STT,Technique,Category,Keywords,Description,When to Use,Syntax Example,Platforms,Tips
-1,Emphasis Capitalization,Formatting,"caps, emphasis, important, critical, priority, MUST","Use ALL CAPS for critical requirements that must not be ignored","When specific elements are non-negotiable","MUST include blue sky. NEVER add watermarks. DO NOT modify face.","Nano Banana, DALL-E","Use sparingly - 2-3 emphasis points max; overuse dilutes impact"
-2,Weighted Prompting,Control,"weight, emphasis, priority, stronger, weaker, balance","Assign numerical weights to prompt terms for relative importance","When balancing multiple elements or emphasizing specific aspects","(important term:1.3), (less important:0.7) OR cat::2 dog::1","SD, Flux, Midjourney","1.0 is default; 1.2-1.5 for emphasis; 0.5-0.8 to reduce; Midjourney uses :: syntax"
-3,Negative Prompts,Refinement,"negative, avoid, exclude, remove, no, without, ban","Specify what to exclude from the generated image","To prevent common artifacts or unwanted elements","Negative: ugly, blurry, deformed, watermark, extra limbs","SD, Flux, Leonardo","Essential for SD/Flux; organize by category (anatomy, quality, style); keep concise"
-4,Multi-Image Reference,Identity,"reference, identity lock, face match, style transfer, consistency","Use multiple images to maintain subject identity or style","For consistent character generation or style matching","Upload 6 object + 5 human refs (Nano Banana up to 14 images)","Nano Banana, Midjourney, SD","Collage multiple refs into single image for efficiency; specify which image for what purpose"
-5,JSON Structured Prompts,Organization,"JSON, structured, organized, layered, metadata, schema","Use JSON format for complex, multi-layer prompt organization","For detailed scene descriptions with many parameters","{ ""subject"": {}, ""environment"": {}, ""camera"": {}, ""lighting"": {} }","Nano Banana, any","Helps organize complex prompts; include meta_data, subject_layer, environment_layer, composition_and_tech"
-6,Narrative Description,Natural,"narrative, paragraph, story, descriptive, natural language","Write prompts as flowing paragraphs like briefing a photographer","For models that understand natural language well (32K+ context)","A professional portrait of a woman in her 30s, standing in an urban setting at golden hour...","Nano Banana, DALL-E","More effective than keyword lists for Gemini; include context, mood, and intention"
-7,Photography Anchoring,Quality,"photography, camera, lens, DSLR, professional, shot","Use photography terms to anchor quality and realism","For photorealistic results and specific camera aesthetics","Captured with Canon EOS 90D, 85mm lens, f/1.8, shallow DOF, natural lighting","All platforms","Include camera model, lens, aperture, lighting setup; triggers photorealistic training data"
-8,Color Precision,Accuracy,"hex, color code, precise color, #, RGB, specific color","Use hex color codes instead of vague color names","When exact colors are critical","Background: #9F2B68 (dark magenta) instead of 'dark magenta'","Nano Banana, any","Hex codes are unambiguous; include color name for context; use for brand colors"
-9,Aspect Ratio Control,Composition,"aspect ratio, ar, dimensions, ratio, format, orientation","Specify exact aspect ratio for output dimensions","When specific dimensions are required","--ar 16:9 (Midjourney) OR aspect_ratio='16:9' (Nano Banana)","All platforms","Match platform requirements; 1:1 social, 9:16 stories, 16:9 widescreen, 21:9 cinematic"
-10,Iterative Refinement,Workflow,"iteration, refine, version, variation, A/B test, improve","Generate variations and refine based on results","For achieving optimal results through multiple generations","Generate 4 variations → Select best → Refine weights → Upscale","All platforms","Start broad, narrow down; save seeds for reproducibility; document successful prompts"
-11,Scene Layering,Composition,"foreground, midground, background, layers, depth, z-index","Describe scene in distinct depth layers","For complex scenes with depth","Foreground: cherry blossoms. Midground: person walking. Background: Mount Fuji at sunset.","All platforms","Creates visual depth; helps AI understand spatial relationships"
-12,Style Mixing,Creative,"blend, mix, fusion, combine, hybrid, mashup","Combine multiple artistic styles","For unique hybrid aesthetics","Art nouveau meets cyberpunk, or '80s synthwave crossed with ukiyo-e woodblock print","Midjourney, SD, Nano Banana","Use 'meets', 'crossed with', 'fusion of'; weight styles if needed"
-13,Negative Constraints,Safety,"NEVER, avoid, exclude, prohibit, ban, NO","Explicit statements of what must not appear","To prevent unwanted content or artifacts","NEVER include text or watermarks. DO NOT add any UI elements. Avoid red tones.","Nano Banana, DALL-E","More effective than negative prompts for some models; be specific and explicit"
-14,Camera Movement (Video),Motion,"pan, tilt, dolly, tracking, crane, zoom, motion","Specify camera movements for video generation","For AI video generation","Slow dolly forward, then gentle pan right revealing the landscape. Fade to next scene.","Veo, video platforms","Use cinematography terms; specify speed and direction; include transitions"
-15,Identity Lock,Consistency,"identity, face lock, same person, consistent, preserve","Techniques to maintain subject identity across generations","For consistent character representation","Use reference as EXACT facial reference. STRICT identity lock. NO face modification.","Nano Banana, SD (LoRA)","Upload clear reference; explicitly state preservation requirements; use JSON locks"
-16,Multi-Panel Composition,Layout,"panel, grid, collage, multi-image, split, diptych","Request images with multiple panels or sections","For comics, comparisons, before/after","2x2 grid showing: [top-left description], [top-right description], [bottom-left], [bottom-right]","Nano Banana, Midjourney","Describe each panel clearly; maintain consistency across panels; specify layout (2x2, 1x3, etc.)"
-17,Search Grounding,Real-time,"search, real-time, current, live data, grounding, factual","Enable real-time data for accurate current information","For current events, accurate data visualization","tools=[{'google_search': {}}] - enables real-time weather, charts, events","Nano Banana only","Use for infographics with current data; weather-accurate scenes; current event imagery"
-18,Thinking Mode,Complex,"thinking, reasoning, complex, planning, elaborate","Enable AI reasoning for complex compositions","For intricate scenes requiring planning","Enable thinking mode for complex multi-character scenes with specific interactions","Nano Banana Pro only","Response includes part.thought; use for complex logic like 'kittens MUST have eyes matching fur'"

package/.opencode/skills/ai-artist/data/use-cases.csv

@@ -1,16 +0,0 @@
-STT,Use Case,Category,Keywords,Prompt Template,Key Elements,Best Platforms,Aspect Ratios,Tips,Example
-1,Profile Avatar,Portrait,"avatar, profile, headshot, professional, LinkedIn, social media, portrait","A professional {style} portrait of [subject], {background}, {lighting}. High-quality, sharp focus on eyes.","Subject appearance, background, lighting style, expression","Nano Banana, Midjourney, DALL-E","1:1, 4:5","Use reference image for identity lock; specify skin texture preference","Professional LinkedIn headshot with soft daylight, blurred office background"
-2,Social Media Post,Marketing,"social, Instagram, Twitter, viral, engagement, post, story, reel","A {style} image for social media showing [concept]. {composition}. Vibrant colors, eye-catching, shareable.","Main subject, brand colors, call-to-action elements, mobile-first composition","DALL-E, Midjourney, Nano Banana","1:1, 9:16, 4:5","Design for mobile viewing; use bold colors; include negative space for text overlay","Minimalist product flat-lay for Instagram with pastel background"
-3,YouTube Thumbnail,Marketing,"thumbnail, YouTube, clickbait, attention, video, preview, engaging","A {style} YouTube thumbnail showing [scene]. Bold text '{text}' in {font}. High contrast, {emotion} expression.","Subject with expressive face, bold readable text, contrasting colors, clear focal point","Nano Banana, Midjourney","16:9","Use surprised/excited expressions; limit text to 3-5 words; ensure 1080p quality","Shocked reaction face with glowing background and 'YOU WON'T BELIEVE THIS' text"
-4,Product Marketing,Commercial,"product, commercial, advertising, e-commerce, hero, marketing, lifestyle","A {style} product shot of [product] on {surface}. {lighting} creating {mood}. {camera_angle} view.","Product as hero, clean background, professional lighting, brand consistency","Nano Banana, DALL-E, SD","1:1, 4:3, 3:2","Use studio lighting terms; specify material reflections; include lifestyle context","Premium cosmetic bottle on marble surface with soft rim lighting"
-5,E-commerce Main Image,Commercial,"e-commerce, Amazon, Shopify, product, main image, white background, listing","A clean {style} product image of [product] on pure white background. Studio lighting, multiple angles available.","Product isolation, pure white (#FFFFFF) background, consistent lighting, accurate colors","Nano Banana, SD, Midjourney","1:1, 4:3","Match platform requirements; ensure color accuracy; remove all shadows or use soft drop shadow","Wireless earbuds case on pure white background with soft shadows"
-6,Infographic Visual,Educational,"infographic, educational, diagram, chart, visual, data, explainer","A {style} infographic about [topic]. Bento grid layout, {color_scheme} palette, icons for each section.","Clear hierarchy, data visualization, iconography, readable text, logical flow","Nano Banana, DALL-E","16:9, 4:3, 1:1","Use Bento grid for modules; limit to 8 sections max; ensure text legibility","Glass-style infographic about nutrition with 8 data modules"
-7,Comic Storyboard,Narrative,"comic, manga, storyboard, panel, sequence, narrative, story","A {panels}-panel {style} comic showing [story]. Consistent character design, speech bubbles, {mood} atmosphere.","Panel layout, character consistency, speech bubbles, visual flow, action lines","Midjourney, SD, Nano Banana","2:3, 3:4, 16:9","Maintain character identity across panels; use manga techniques for action; clear panel boundaries","4-panel manga sequence showing character discovering a secret message"
-8,Game Asset,Gaming,"game, asset, sprite, character, icon, item, UI, gaming","A {style} game asset: [item/character]. Transparent background ready, {view} view, consistent with {art_style} aesthetic.","Isolation-ready design, consistent art style, multiple states/angles, scalable","SD, Midjourney","1:1, varies","Design for transparency; create sprite sheets; maintain style consistency across assets","Pixel art treasure chest with open/closed states"
-9,Poster Flyer,Print,"poster, flyer, print, event, promotional, announcement, advertising","A {style} poster for [event/product]. Headline: '{headline}', {layout} composition, {color_scheme} colors.","Typography hierarchy, visual hook, brand elements, print-ready composition","DALL-E, Midjourney, Nano Banana","3:4, 2:3, A4","Use CMYK-safe colors; ensure 300dpi concept; include bleed area concept","Vintage music festival poster with psychedelic typography and sunset gradient"
-10,App Web Design,UI/UX,"app, web, UI, UX, mockup, interface, screen, dashboard","A {style} {device} mockup showing [app/website]. {color_scheme} palette, {layout} layout, modern UI elements.","Device frame, UI components, realistic content, responsive hints","Nano Banana, Midjourney, DALL-E","varies by device","Show realistic content; use design system patterns; include status bar details","iPhone mockup showing a meditation app with glassmorphism cards"
-11,Quote Card,Social,"quote, inspiration, motivational, card, typography, wisdom","A {style} quote card with text: '{quote}' — {author}. {background} background, {font_style} typography.","Quote text, author attribution, decorative elements, readable font","Nano Banana, DALL-E","1:1, 4:5, 16:9","Use large quotation marks; ensure text contrast; add subtle decorative elements","Brown gradient quote card with Steve Jobs quote and portrait silhouette"
-12,Header Banner,Marketing,"header, banner, hero, website, blog, article, cover","A {style} header image for [topic]. {composition}, {mood} atmosphere, horizontal format ready for text overlay.","Wide aspect ratio, focal point consideration, text-safe zones, brand alignment","DALL-E, Midjourney, Nano Banana","16:9, 21:9, 3:1","Leave negative space for text; ensure horizontal composition; consider responsive cropping","Hand-drawn style header for tech blog with blue-green gradient"
-13,Character Design,Creative,"character, OC, original, design, concept, persona, avatar","A {style} character design of [description]. {pose} pose, {outfit} outfit, {personality} expression.","Full body or bust, consistent proportions, outfit details, personality expression","Midjourney, SD, Nano Banana","2:3, 3:4, 1:1","Include turnaround views; specify body proportions; describe personality through visual cues","Anime-style female character with cyberpunk outfit and neon accessories"
-14,Architecture Interior,Visualization,"architecture, interior, room, space, design, rendering, visualization","A {style} {view} of [space type]. {materials} materials, {lighting} lighting, {atmosphere} atmosphere.","Spatial composition, material textures, lighting quality, furnishing details","Midjourney, SD","16:9, 4:3, 3:2","Use architectural photography terms; specify time of day; describe material finishes","Modern minimalist living room with floor-to-ceiling windows and warm afternoon light"
-15,Food Photography,Commercial,"food, culinary, recipe, dish, restaurant, cooking, delicious","A {style} food photo of [dish]. {plating} presentation, {lighting} lighting, {props} styling.","Hero dish focus, complementary props, appetizing lighting, styled setting","Nano Banana, Midjourney","1:1, 4:5, 4:3","Use overhead or 45-degree angles; include human elements for scale; describe steam/freshness","Overhead shot of artisan pizza with stretchy cheese pull and rustic wooden board"

package/.opencode/skills/ai-artist/references/advanced-techniques.md

@@ -1,184 +0,0 @@
-# Advanced Prompt Engineering
-
-## Prompt Optimization
-
-### DSPy Framework
-Automatic prompt optimization through:
-1. Define task with input/output signatures
-2. Compile with optimizer (BootstrapFewShot, MIPRO)
-3. Model learns optimal prompting strategy
-4. Export optimized prompts for production
-
-### Meta-Prompting
-```
-You are a prompt engineer. Create 5 variations for [task]:
-1. Direct instruction approach
-2. Role-based approach
-3. Few-shot example approach
-4. Chain of thought approach
-5. Constraint-focused approach
-
-Evaluate each, select best.
-```
-
-### Self-Refinement Loop
-```
-Generate: [Initial response]
-Critique: "What's wrong? Score 1-10."
-Refine: "Fix issues, improve score."
-Repeat until score ≥ 8.
-```
-
-## Prompt Chaining
-
-### Sequential Chain
-```
-Chain 1: [Input] → Extract key points
-Chain 2: Key points → Create outline
-Chain 3: Outline → Write draft
-Chain 4: Draft → Edit and polish
-```
-
-### Parallel Chain
-Run independent subtasks simultaneously, merge results.
-
-### Conditional Chain
-```
-If [condition A]: Execute prompt variant 1
-If [condition B]: Execute prompt variant 2
-Else: Execute default prompt
-```
-
-### Loop Pattern
-```
-While not [success condition]:
-    Generate attempt
-    Evaluate against criteria
-    If pass: break
-    Else: refine with feedback
-```
-
-## Evaluation Methods
-
-### LLM-as-Judge
-```
-Rate this [output] on:
-1. Accuracy (1-10)
-2. Completeness (1-10)
-3. Clarity (1-10)
-4. Relevance (1-10)
-
-Provide reasoning for each score.
-Final: Pass/Fail threshold = 7 average.
-```
-
-### A/B Testing Protocol
-1. Single variable per test
-2. 20+ samples minimum
-3. Score on defined criteria
-4. Statistical significance check (p < 0.05)
-5. Document winner, roll out
-
-### Regression Testing
-- Maintain test set of critical examples
-- Run before deploying prompt changes
-- Compare scores to baseline
-- Block deployment if regression detected
-
-## Agent Prompting
-
-### Tool Use Design
-```
-You have access to these tools:
-- search(query): Search the web
-- calculate(expression): Math operations
-- code(language, code): Execute code
-
-To use: <tool_name>arguments</tool_name>
-Wait for result before continuing.
-```
-
-### Planning Prompt
-```
-Task: [Complex goal]
-
-Before acting:
-1. Break into subtasks
-2. Identify dependencies
-3. Plan execution order
-4. Note potential blockers
-
-Then execute step by step.
-```
-
-### Reflection Pattern
-```
-After each step:
-- What worked?
-- What didn't?
-- Adjust approach for next step.
-```
-
-## Parameter Tuning
-
-| Parameter | Low | High | Use Case |
-|-----------|-----|------|----------|
-| Temperature | 0.0-0.3 | 0.7-1.0 | Factual vs Creative |
-| Top-P | 0.8 | 0.95 | Focused vs Diverse |
-| Top-K | 10 | 100 | Conservative vs Exploratory |
-
-**Rule**: Tune temperature first. Only adjust top-p if needed. Never both at once.
-
-## Safety Patterns
-
-### Output Filtering
-```
-Before responding, check:
-- No PII exposure
-- No harmful content
-- No policy violations
-- Aligned with guidelines
-
-If any fail: "I can't help with that."
-```
-
-### Jailbreak Prevention
-- Clear system boundaries upfront
-- Repeat constraints at end
-- "Ignore previous" pattern detection
-- Role-lock: "You are ONLY [role], never anything else"
-
-### Confidence Calibration
-```
-For each claim, provide:
-- Confidence: High/Medium/Low
-- Source: [citation if available]
-- Caveat: [limitations]
-```
-
-## Production Patterns
-
-### Version Control
-- Git for prompt files
-- Semantic versioning (1.0.0, 1.1.0)
-- Changelog per version
-- Rollback capability
-
-### Caching
-- Cache common queries
-- TTL based on content freshness
-- Invalidate on prompt update
-
-### Fallbacks
-```
-Try: Primary prompt
-If fail: Simplified fallback prompt
-If still fail: Human escalation
-Log all failures for analysis.
-```
-
-### Cost Optimization
-- Shorter prompts = fewer tokens
-- Remove redundant examples
-- Use smaller model for simple tasks
-- Batch similar requests