Higgsfield 图像提示导演，覆盖 Banana Pro、Soul Cinema 和 GPT-2。按严格顺序生成三种资产类型：角色服装参考图、多角度角色表、场景图板。支持超写实提示输出。
Banana Pro Director 是一个专为 Higgsfield 平台设计的 AI 技能，用于生成高质量的图像提示。它严格遵循三种资产类型的工作流程：首先是在白色无缝背景上生成单张角色服装参考图（可通过 Banana Pro 自定义风格或 Soul Cinema 使用角色参考和服装参考），然后基于该参考图生成6面板多角度角色表，最后生成带或不带角色、位于电影场景中的场景图板。此外，它还支持使用 GPT-2 生成细致的面部/胸部肖像。该技能能够读取参考图像中的头发、妆容、服装、珠宝和身份标记等细节，并输出包含锁定超写实堆栈（如皮肤毛孔、次表面散射、丝丝入扣的头发、织物纹理、Kodak Vision3 胶片效果）的提示。适用于任何角色服装参考、角色表、模型表、多角度表、场景图板、环境图板、面部细节特写或超写实静帧，即使没有明确提及'Banana Pro'、'Nano Banana' 或 'Soul Cinema' 等关键词也可使用。
npx skills add https://github.com/fulcrumsf/Claude-Agent-V1/tree/main/007_Resource_Library/Tutorials/Higgsfield-Video-Pipeline/Banana-Pro-DirectorHiggsfield 图像提示导演，覆盖 Banana Pro、Soul Cinema 和 GPT-2。三种资产类型按严格顺序生成：（1）白色无缝工作室背景上的单张角色服装参考图——锁定基础参考，可通过 Banana Pro（根据提示自定义风格）或 Soul Cinema（角色参考的脸/身体 + 服装参考的服装）生成；（2）基于该基础参考生成的6面板多角度角色表；（3）带或不带角色、位于电影场景中的场景图板。此外还支持使用 GPT-2 生成细致的面部/胸部肖像。读取参考图像中的头发、妆容、服装、珠宝、身份标记等细节。输出包含锁定超写实堆栈的提示——皮肤毛孔、次表面散射、丝丝入扣的头发、织物纹理、Kodak Vision3 胶片效果。可用于任何角色服装参考、角色表、模型表、参考表、多角度表、场景图板、环境图板、面部细节特写或超写实静帧——即使没有明确提及'Banana Pro'、'Nano Banana' 或 'Soul Cinema' 等关键词。
This repo contains 7 individual skills — each has its own dedicated page.
Universal cinema worldbuilding director for Seedance video prompts. Reads uploaded reference images for wardrobe, hair, makeup, identity markers, and environment, then composes production-ready Seedance prompts using a locked cinematography grammar — five cinema modes (Narrative, Studio, Action, Performance, Atmospheric), each with canonical camera/lens/movement/filtration/grade specs, plus diegetic audio design (footsteps, fabric, breath, room tone, weapon fire, crowd, weather — never music or lyrics). Use this skill whenever the user wants to create a Seedance video prompt, mentions Seedance, asks for a cinematic scene breakdown, uploads reference images for a scene they want to build, describes a scene for video generation, or asks for shot prompts for music videos, action sequences, performance scenes, narrative shorts, fashion films, or atmospheric environment plates — even if they don't explicitly say 'cinematic' or name a mode.
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subj
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subj
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.
Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague f
Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR topic explainer (/faceless-explainer). Unclear → /hyperframes.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".