anime-mj-prompt-builder
Generates anime/manga prompts for Midjourney Niji mode with 30+ artist styles, SREF code library
What this skill does
# Anime/Manga Prompt Builder Skill This skill helps users create authentic anime and manga art using Midjourney's Niji mode. It features comprehensive knowledge of 30+ manga artists, 14 anime studios, multiple genres, and technical Niji parameters. ## When to Activate This Skill Use this skill when users: 1. **Request anime or manga art** - "Create anime art of...", "Draw a manga character..." 2. **Mention anime artists** - "Ghibli style", "like Berserk", "Dragon Ball look" 3. **Ask about Niji mode** - "How do I use Niji?", "Anime settings in Midjourney" 4. **Want specific anime styles** - "magical girl", "shonen action", "cyberpunk anime" 5. **Reference anime studios** - "MAPPA style", "Kyoto Animation look", "Trigger aesthetic" 6. **Describe anime genres** - "seinen dark fantasy", "shoujo romance", "isekai adventure" 7. **Ask about SREF codes** - "What SREF code for Ghibli?", "Anime style reference codes" 8. **Want consistent styling** - "Make it look like...", "Same style as...", "Visual consistency" 9. **Need character consistency** - "Same character in different poses", "Keep my character consistent" 10. **Want reference sheets** - "Create a character sheet", "Multiple views of character" 11. **Ask about --cref** - "How do I use character reference?", "What is --cref?" 12. **Want to animate images** - "Animate my image", "Make it move", "Create video" 13. **Ask about video/animation** - "How do I animate?", "What is --video?", "Motion prompts" ## When NOT to Activate Do not use this skill when: - Users want photorealistic or non-anime images - Users are working on code unrelated to image generation - Users are asking about other AI tools (DALL-E, Stable Diffusion) - The request is for Western cartoon styles (not anime) ## Core Capabilities ### Supported Artists (30+) **Foundational**: Osamu Tezuka, Leiji Matsumoto, Go Nagai **Shonen**: Akira Toriyama, Eiichiro Oda, Masashi Kishimoto, Tatsuki Fujimoto, Hajime Isayama, Gege Akutami, Kohei Horikoshi **Seinen**: Kentaro Miura, Katsuhiro Otomo, Naoki Urasawa, Junji Ito, Tsutomu Nihei, Takehiko Inoue **Shoujo/Josei**: Naoko Takeuchi, CLAMP, Rumiko Takahashi, Ai Yazawa **Directors**: Hayao Miyazaki, Makoto Shinkai, Hideaki Anno, Satoshi Kon, Mamoru Hosoda, Hiroyuki Imaishi **Modern**: Hirohiko Araki, ONE, Yusuke Murata, Sui Ishida, Yoshitoshi Abe ### Supported Studios (14) Studio Ghibli, Kyoto Animation, MAPPA, Ufotable, WIT Studio, Bones, Madhouse, Trigger, Shaft, Production I.G, Sunrise, Toei Animation, A-1 Pictures, CloverWorks ### Genres - **Shonen** - Action, adventure, battles - **Seinen** - Mature, dark, psychological - **Shoujo** - Romance, magical girl - **Slice of Life** - Everyday, school, heartwarming - **Mecha** - Robots, sci-fi - **Horror** - Dark, disturbing - **Isekai** - Fantasy worlds - **Cyberpunk** - Dystopian, neon ### Model & Parameters - `--niji 6` (default, recommended for traditional anime) - `--v 7` (alternative, works well with SREF + anime keywords) - `--style raw` (optional, less stylized output) - `--ar` (aspect ratio) - `--s` (stylize 0-1000) - `--sref` (style reference) - `--sw` (style weight 0-1000) - `--cref` (character reference) - `--cw` (character weight 0-100) - `--oref` (omni reference, V7) - `--motion low` / `--motion high` (video motion intensity) - `--loop` (seamless video loop) - `--raw` (precise motion control) ### Character Consistency Support **Reference Sheet Types:** - Multi-view sheets (front, side, 3/4, back) - Expression sheets (happy, sad, angry, surprised, neutral) - Outfit variation sheets (same character, different clothes) - Turntable/360 views **Character Weight Guide:** - `--cw 100`: Full character (face + hair + clothes) - `--cw 50`: Moderate similarity (different outfit, same character) - `--cw 0`: Face only (complete costume change) ### Video/Animation Support > **Note**: Video generation requires Midjourney web app (not Discord bot). **Motion Styles:** - Action (dynamic movement, speed effects) - Slice-of-life (gentle breeze, subtle movement) - Dramatic (slow zoom, emotional moments) - Combat (fast motion, impact frames) **Camera Motion:** - Pan (left/right/up/down tracking) - Zoom (push in, pull out) - Orbit (circular movement around subject) - Static (subtle character animation only) **Motion Parameters:** - `--motion low`: Subtle, peaceful, cinemagraph-style (default) - `--motion high`: Dynamic, energetic, action-focused - `--loop`: Seamless looping animation - `--raw`: Precise motion control ### SREF Code Library (40+ Curated Codes) **Categories:** - **Ghibli/Soft**: Warm, nostalgic (codes: 3408846050, 918084796, 3161604773...) - **Shonen/Dynamic**: Bold, action-oriented (codes: 3730983883, 910384726...) - **Seinen/Dark**: Moody, atmospheric (codes: 416523183, 229704573...) - **Shoujo/Elegant**: Sparkles, soft lighting (codes: 2178024008...) - **Retro**: 80s/90s aesthetic (codes: 16809792746, 4292182277...) - **Modern/Clean**: Contemporary look (codes: 65, 20...) **Full library**: See `docs/sref-library.md` for complete reference. ## Interaction Pattern ### Step 1: Identify Genre Determine if the request is shonen, seinen, shoujo, slice of life, mecha, or horror. ### Step 2: Match Artist/Studio Suggest relevant artists or studios based on the genre and description. ### Step 3: Gather Details Ask about character, scene, action, and atmosphere. ### Step 4: Aesthetic & Technical Options Ask about desired aesthetic vibe: - Cute/Kawaii (adorable, soft, whimsical) - Dramatic/Expressive (intense, bold, dynamic) - Scenic/Atmospheric (cinematic, environmental) - Classic/Retro (80s/90s anime look) - Let the artist style guide it (skip) Then ask about aspect ratio. Based on aesthetic selection, automatically inject appropriate keywords (see Internal Reference at end of file). ### Step 5: Style Reference (Auto-Matched) Automatically suggest a matching SREF code based on user's genre, artist, and aesthetic selections. Don't ask users to browse or choose - offer a pre-matched code: - "I can add a style reference that matches your [genre/aesthetic]. Add it?" - If yes, ask about intensity (Light/Medium/Strong/Very Strong) - Reference the Internal Reference: SREF Auto-Matching section for matching logic ### Step 6: Character Reference (Optional) Ask if user needs character consistency: - Create new character → offer reference sheet templates - Use existing reference → get URL and suggest --cw weight - Skip for single images ### Step 7: Animation (Optional) Ask if user wants to animate their image: - Yes → guide through motion style, camera motion, intensity - No → skip to final output - Note: Web app only (not Discord) ### Step 7.5: Output Structure Ask user about prompt structure level: - Standard (6 sections - easy to modify key elements) - Granular (8 sections - more control over details) - Maximum (10 sections - full element-by-element control) ### Step 8: Build Prompt Construct and output the structured Niji prompt using selected level. ## Example Outputs (Standard Structure) ### Ghibli Style ``` [Character] young adventurer | [Action] discovering hidden forest spirit | [Scene] lush vegetation, enchanting forest | [Style] Studio Ghibli, Hayao Miyazaki | [Genre] magical realism, whimsical | [Mood] soft natural lighting --niji 6 --ar 16:9 --s 500 ``` ### Dark Fantasy ``` [Character] lone warrior, intense expression | [Action] facing demon, battle stance | [Scene] gothic cathedral, atmospheric | [Style] Berserk, Kentaro Miura | [Genre] dark fantasy, seinen | [Mood] hyper-detailed linework, dramatic shadows --niji 6 --ar 2:3 --s 800 ``` ### Magical Girl (Cute Aesthetic) ``` [Character] magical girl, adorable expression, big sparkling eyes | [Action] mid-transformation, dynamic graceful pose | [Scene] cosmic starry background, sparkles and ribbons | [Style] Sailor Moon, Naoko Takeuchi | [Genre] magical girl, shoujo, kawaii | [Mood] soft pastel colors, pink and lavender, soft glowing lighting --niji 6 --ar
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.