Communitygithub.com

角色設計引擎

將 `aesthetic-director-core` 產出的創意摘要轉換為完整、模型無關的角色藍圖,包含設計論點、輪廓架構、視覺錨點、服裝工程(基底/結構/簽名延伸/配件系統)、材質對比、色調層級、行為姿勢與鏡頭、敘事殘留及展示格式,並執行減法運算。適用於 OC、人設、角色設計、服裝設計、立繪、高定服設、二遊角色、角色表、時尚概念。絕不撰寫特定模型的提示語法。

角色設計引擎 是什麼?

角色設計引擎是一款專業 AI 技巧,旨在將創意簡報轉化為模型無關的完整角色藍圖。它適用於各種角色設計場景,包括原創角色(OC)、遊戲角色設定、時裝設計等,並在 Cursor 等開發者工具平台上運作。該引擎的核心優勢在於其嚴謹的設計流程,從命題、輪廓策略、視覺錨點、四層服裝工程(基底/結構/簽名延伸/配件系統)、材質對抗、配色層級,到姿勢鏡頭、敘事殘留與展示方式,每一步都有明確的順序與依賴關係,確保設計決策紮實且富有深度。最後強制執行減法與反平庸檢查,刪除不必要的元素,杜絕過度裝飾。若直接調用而無簡報,引擎會先調用 `aesthetic-director-core` 的壓縮流程生成必要前提。引擎不寫特定模型的提示語法,而是輸出由名詞、位置和行為組成的純事實藍圖,可由任何模型適配器直接翻譯。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/02_creation/character-design-engine

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

角色設計引擎 是做什麼的?

定位

輸入:aesthetic-director-core 產出的 創意簡報(方向、矛盾、輪廓策略、因果鏈、瞬間、密度圖、刺點、留下的怪、刪掉的東西)。 輸出:一份角色 blueprint,任何模型適配器都能直接翻譯,且不需要再做設計決定。

如果被直接調用而沒有 Brief:先用 aesthetic-director-core 的 M1 / M3 / M6 / M7 壓縮跑一遍(內部完成,不必輸出完整 Brief),再進入下面的流程。不要跳過。 跳過的結果就是表單填充。

如果用戶明確要求極繁精美人設 / 極繁 OC,優先讀取 references/maximalist-oc-design-grammar.md;此模式允許高複雜度,但複雜度必須來自輪廓、服裝工程、統一母題、材質對抗和多尺度細節,而不是隨機堆配件。

本 Skill 不寫 Anima / NAI5 語法。本 Skill 不重新決定品味——品味來自 personal-identity-profile。

為什麼不是一張表

上一版的輸出契約是 Identity: / Background: / Silhouette: / Costume: / ... 十三個空格。空格會被填滿,而且每格填的都是最常見值。 這一版的輸出是一串有先後依賴的決定:後面的每一項都由前面的項推出。如果某一項推不出來,說明前面的決定沒做實。

執行流程

詳細手法見 references/oc-design-system.md(六層結構、輪廓策略、複雜度控制、反平庸檢查)。

Step 1  命題        從 Brief 的【方向】開始。一句話,含動詞。寫不出動詞 → 退回 director。
Step 2  輪廓策略    五選一:halo/radial · vertical spear · asymmetric cascade · cocoon/volume · fragmented orbit
                    寫出空間關係:behind the head / wrapping the torso / descending from one shoulder
Step 3  視覺錨點    1 個主錨點(頭/胸/腰/背/手中物 五選一)+ ≤2 個次錨點。主錨點 = Brief 的密集區。
Step 4  服裝工程    Base garment → Structural garment → Signature extension → Accessory system
                    每一層寫「形狀 + 位置 + 功能/運動」,不寫形容詞。詞彙見 references/garment-lexicon.md
Step 5  材質對抗    至少一組:啞光 vs 反光 / 柔軟 vs 硬質 / 織物 vs 生物 / 粗糙 vs 光滑。綁定到具體結構。
Step 6  配色層級    基底 60–75% / 結構色 20–30% / 刺點 ≤5%。每個顏色寫落點。刺點 = Brief 的刺點。
Step 7  姿勢 + 鏡頭 姿勢由 Brief 的【瞬間】和【因果鏈】給出。鏡頭由姿勢類型決定(展示/操控/回身/儀式/脆弱 → 對應機位)。
Step 8  敘事殘留    一件東西的狀態說明發生過什麼。必須是她行為的結果。
Step 9  展示方式    clean plate / decorated key visual / editorial plate / environmental vignette
Step 10 減法        對 Step 4–9 的每一件東西問「刪掉它命題還在嗎」。在 → 刪。寫下刪了什麼。
Step 11 反平庸檢查  references/oc-design-system.md § 4

輸出契約:Character Blueprint

用連貫的短段落寫,不用空表格。每段開頭是決定,後面是它的依據。適配器需要的所有事實都要在裡面,用名詞 + 位置 + 行為表達。

## [角色名或代號]

**命題**:一句話。
**輪廓**:策略 + 空間關係 + 縮略圖裡能認出的那個形狀。
**錨點**:主錨點在___;次錨點在___、___。安靜區在___。
**服裝**:
  - Base:
  - Structural:
  - Signature extension:
  - Accessory system(同形態語法):
**材質對抗**:___ vs ___,落在___。
**配色**:基底___ / 結構___ / 刺點___(位置)。
**外觀**:髮(形狀、長度分佈、顏色——不是「銀色長直」)、眼、膚、種族特徵。
**姿勢與鏡頭**:她正在___(瞬間)。因為___所以___(因果)。機位___,視線___,手___。
**敘事殘留**:___
**展示方式**:___
**留下的怪**:___,因為___。
**刪掉的**:___、___、___。
**否決的方向**:① ___ ② ___
**鎖定事實**(用戶明確給定、不可被適配器「優化」的):___

多套設計

用戶要 N 套時,每套之間至少在 命題、輪廓策略、主錨點、材質語言、動作邏輯 五項裡有兩項明顯不同。不要出同一個設計的三個配色。

參考圖輸入

用戶給參考圖時,先走 image-reverse-analysis 提取結構(輪廓、密度分佈、母題語法、顏色層級、材質、姿勢邏輯、留白),再在這裡換掉全部具體物件、保留結構。見 aesthetic-director-core/references/taste-calibration-pairs.md Pair 5。

自檢

  • 命題裡有動詞嗎?
  • 只有一個主錨點嗎?
  • 服裝四層每層都有形狀和位置,沒有一處是形容詞?
  • 刪掉顏色,輪廓還認得出?刪掉裝飾,基礎服裝還有獨立剪裁?
  • 姿勢會改變頭髮 / 衣擺 / 道具 / 光的位置嗎?
  • 敘事殘留是她造成的嗎?
  • 刺點只有一個、有精確位置?
  • 有「刪掉的」和「否決的方向」兩行嗎?
  • 踩了 personal-identity-profile/references/design-dislikes.md 嗎?
  • 鎖定事實完整傳下去了嗎?

References

  • references/oc-design-system.md — 六層結構、五種輪廓策略、姿勢-鏡頭對應、展示方式、複雜度控制、反平庸檢查、開放式請求默認行為
  • references/garment-lexicon.md — 穿搭原型、四層疊穿、不對稱手法、材質碰撞矩陣、領/袖/腰/裙詞彙(英文短語可直接進 prompt)
  • references/maximalist-oc-design-grammar.md — 極繁精美人設專用設計語法:宏觀輪廓、服裝多層、統一母題、非對稱重量、材質碰撞、多尺度細節與 pose activation

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

Tera-Dark/personal-agent-skills

Creative direction layer that turns a vague request into one committed design idea before any blueprint or prompt is written. Runs a sequence of generative "moves" (find the obsession, plant a contradiction, pick from the tail, build causality, subtract, keep one strange thing) and produces a short Creative Brief with rejected alternatives. Use for any OC / character / illustration / fashion / key-visual request, whenever output feels generic, "AI-flavored", too plain, too busy, or when the user asks for taste, direction, 审美, 创意方向, 人味, 高级感, 不要AI味.

Tera-Dark/personal-agent-skills

Persistent identity and taste layer for Tera-Dark's creative work. Holds the aesthetic signature (restrained base, one strange thing, a hint of danger, fashion-grade garment construction, female-oriented OC/gacha sensibility), hard dislikes (watches, cyber/mech, random butterflies-roses-particles, adjective costumes), business goals and workflow style. Does not generate prompts. Load first for any creative, design, illustration, prompt or aesthetic-judgment task; also when the user says 我的风格, 我喜欢, 按我习惯, 个人偏好.

Tera-Dark/personal-agent-skills

Entry point for all creative requests in this skill hub. Classifies intent (OC/character design, illustration, fashion, NAI5 prompt, Anima prompt, image reverse analysis, prompt review, ComfyUI/LoRA/dataset), loads identity + aesthetic direction first, then hands off to the right specialist and model adapter. Use whenever a request involves 设计, OC, 人设, 立绘, 插画, 服装, 提示词, prompt, NAI, NovelAI, Anima, 反推, 分析图片, ComfyUI, LoRA, or when it is unclear which skill should handle a creative task.

Tera-Dark/personal-agent-skills

Model adapter that compiles a finished character or illustration blueprint into Anima-ready English prompts in a disciplined Tag block + Natural Language block format. Handles Anima-specific format contract, length budgets, positive-first output, V1 faithful / V2 enhanced modes, model profiles and artifact troubleshooting. Use when the user asks for Anima prompts, Anima 提示词, or names an Anima checkpoint. Does not design — if no blueprint exists, route through aesthetic-director-core and character-design-engine / illustration-direction first.

Tera-Dark/personal-agent-skills

Model adapter that compiles a finished character or illustration blueprint into a natural-language image prompt for models that are not Anima or NAI5 — Midjourney, DALL-E / GPT Image, Google Imagen / Gemini image, Flux, SDXL-style checkpoints, or an unnamed target. Keeps parameters out of the prompt unless the target officially supports them, and labels every model-specific claim with an evidence level. Use when the user names any other image model, says 通用提示词, MJ, Midjourney, DALL-E, Imagen, Flux, SD, 或没说用什么模型. Does not design — if no blueprint exists, route through aesthetic-director-core first.

Tera-Dark/personal-agent-skills

Turns a Creative Brief into an authored, model-agnostic illustration blueprint — the image thesis, captured moment, visual motif, environment-character relationship, camera and framing, scale contrast, negative space, physical light sources, density map, narrative residue, and one coherent surreal detail. Use for 插画, 氛围图, 竖屏, 半留白, 印象风, 故事感, key visual, poster, scene illustration, cinematic composition, or whenever a character needs to be placed into a designed moment rather than displayed on a plate. Never writes model-specific prompt syntax.

Tera-Dark/personal-agent-skills

Model adapter that compiles a finished character or illustration blueprint into NovelAI V5 community-format prompts — weighted artist stack, global style layer, scene base, char1/char2 blocks, source#/target#/mutual# interaction tags, and targeted negative steering with weight::tag:: syntax. Use when the user asks for NAI5, NovelAI, NAI提示词, tag prompt, Danbooru-style prompt. Does not design — if no blueprint exists, route through aesthetic-director-core and character-design-engine / illustration-direction first.

Tera-Dark/personal-agent-skills

Decomposes a reference image into transferable design language — silhouette and mass distribution, motif grammar, garment construction, material contrast, palette hierarchy, pose logic, negative space and presentation format — instead of a tag dump. Output feeds aesthetic-director-core (for original work) or a model adapter (for faithful reproduction). Use for 反推, 分析图片, 提取提示词, 还原风格, 参考这张图, reverse prompt, image analysis.

Tera-Dark/personal-agent-skills

Reviews an existing image-generation prompt by separating design intent from model syntax — what it is trying to say, which design layer is weak (thesis, silhouette, garment structure, causality, density, punctum), what is noise, and what a rewrite should change. Use for 优化提示词, 这个 prompt 哪里有问题, prompt review, 分析这段提示词, why does this prompt not work.

Tera-Dark/personal-agent-skills

Technical placeholder for ComfyUI workflow organization, node troubleshooting, metadata and LoRA/model integration. Use when the user mentions ComfyUI, workflow json, nodes, 工作流. Does not handle design or prompt creativity.

Tera-Dark/personal-agent-skills

Technical placeholder for image dataset organization, caption/tag management and training preparation. Use when the user mentions dataset, 数据集, 打标, captions, 训练集. Does not handle visual design decisions.

Tera-Dark/personal-agent-skills

Technical placeholder for LoRA training pipelines: dataset prep, caption organization, training configuration, evaluation. Use when the user mentions LoRA, 训练, fine-tune, 炼丹. Does not decide character concepts or artistic direction.

Tera-Dark/personal-agent-skills

Evaluates a generated image or compiled prompt against the original Creative Brief and blueprint, using a fixed rubric (identity preservation, outfit binding, spatial clarity, unrequested additions, V1/V2 consistency, output contract) plus a design-layer read (thesis, silhouette, causality, density, punctum, one strange thing). Diagnoses which layer failed and routes the fix to that layer with a single-variable change. Use on any feedback round: 太平淡, 太乱, 不像, 没人味, 这版可以, 评价一下, 哪里不对, compare versions.

相關技能