Communitygithub.com

Tera-Dark/personal-agent-skills

Turns a Creative Brief (from aesthetic-director-core) into a complete, model-agnostic character blueprint — design thesis, silhouette architecture, visual anchors, garment engineering (base / structural / signature extension / accessory system), material contrast, palette hierarchy, behavioral pose + camera, narrative residue, presentation format — then runs a subtraction pass. Use for OC, 人设, 角色设计, 服装设计, 立绘, 高定服设, 二游角色, character sheet, fashion concept. Never writes model-specific prompt syntax.

O que é personal-agent-skills?

personal-agent-skills is a Claude Code agent skill that turns a Creative Brief (from aesthetic-director-core) into a complete, model-agnostic character blueprint — design thesis, silhouette architecture, visual anchors, garment engineering (base / structural / signature extension / accessory system), material contrast, palette hierarchy, behavioral pose + camera, narrative residue, presentation format — then runs a subtraction pass. Use for OC, 人设, 角色设计, 服装设计, 立绘, 高定服设, 二游角色, character sheet, fashion concept. Never writes model-specific prompt syntax.

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

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

Character Design Engine

定位

输入:aesthetic-director-core 产出的 Creative Brief(方向、矛盾、轮廓策略、因果链、瞬间、密度图、刺点、留下的怪、删掉的东西)。 输出:一份角色 blueprint,任何模型适配器都能直接翻译,且不需要再做设计决定。

如果被直接调用而没有 Brief:先用 aesthetic-director-core 的 M1 / M3 / M6 / M7 压缩跑一遍(内部完成,不必输出完整 Brief),再进入下面的流程。不要跳过。 跳过的结果就是表单填充。

如果用户明确要求极繁精美人设 / 极繁 OC,优先读取 references/maximalist-oc-design-grammar.md;此模式允许高复杂度,但复杂度必须来自轮廓、服装工程、统一母题、材质对抗和多尺度细节,而不是随机堆配饰。

本 Skill 不写 Anima / NAI5 语法。本 Skill 不重新决定品味——品味来自 personal-identity-profile。

为什么不是一张表

上一版的输出契约是 Identity: / Background: / Silhouette: / Costume: / ... 十三个空格。空格会被填满,而且每格填的都是最常见值。 这一版的输出是一串有先后依赖的决定:后面的每一项都由前面的项推出。如果某一项推不出来,说明前面的决定没做实。

执行流程

详细手法见 references/oc-design-system.md(六层结构、轮廓策略、复杂度控制、反平庸检查)。

Step 1  命题        从 Brief 的【方向】开始。一句话,含动词。写不出动词 → 退回 director。
Step 2  轮廓策略    五选一:halo/radial · vertical spear · asymmetric cascade · cocoon/volume · fragmented orbit
                    写出空间关系:behind the head / wrapping the torso / descending from one shoulder
Step 3  视觉锚点    1 个主锚点(头/胸/腰/背/手中物 五选一)+ ≤2 个次锚点。主锚点 = Brief 的密集区。
Step 4  服装工程    Base garment → Structural garment → Signature extension → Accessory system
                    每一层写「形状 + 位置 + 功能/运动」,不写形容词。词汇见 references/garment-lexicon.md
Step 5  材质对抗    至少一组:哑光 vs 反光 / 柔软 vs 硬质 / 织物 vs 生物 / 粗糙 vs 光滑。绑定到具体结构。
Step 6  配色层级    基底 60–75% / 结构色 20–30% / 刺点 ≤5%。每个颜色写落点。刺点 = Brief 的刺点。
Step 7  姿势 + 镜头 姿势由 Brief 的【瞬间】和【因果链】给出。镜头由姿势类型决定(展示/操控/回身/仪式/脆弱 → 对应机位)。
Step 8  叙事残留    一件东西的状态说明发生过什么。必须是她行为的结果。
Step 9  展示方式    clean plate / decorated key visual / editorial plate / environmental vignette
Step 10 减法        对 Step 4–9 的每一件东西问"删掉它命题还在吗"。在 → 删。写下删了什么。
Step 11 反平庸检查  references/oc-design-system.md § 4

输出契约:Character Blueprint

用连贯的短段落写,不用空表格。每段开头是决定,后面是它的依据。适配器需要的所有事实都要在里面,用名词 + 位置 + 行为表达。

## [角色名或代号]

**命题**:一句话。
**轮廓**:策略 + 空间关系 + 缩略图里能认出的那个形状。
**锚点**:主锚点在___;次锚点在___、___。安静区在___。
**服装**:
  - Base:
  - Structural:
  - Signature extension:
  - Accessory system(同一形态语法):
**材质对抗**:___ vs ___,落在___。
**配色**:基底___ / 结构___ / 刺点___(位置)。
**外观**:发(形状、长度分布、颜色——不是"银色长直")、眼、肤、种族特征。
**姿势与镜头**:她正在___(瞬间)。因为___所以___(因果)。机位___,视线___,手___。
**叙事残留**:___
**展示方式**:___
**留下的怪**:___,因为___。
**删掉的**:___、___、___。
**否决的方向**:① ___ ② ___
**锁定事实**(用户明确给定、不可被适配器"优化"的):___

多套设计

用户要 N 套时,每套之间至少在 命题、轮廓策略、主锚点、材质语言、动作逻辑 五项里有两项明显不同。不要出同一个设计的三个配色。

参考图输入

用户给参考图时,先走 image-reverse-analysis 提取结构(轮廓、密度分布、母题语法、颜色层级、材质、姿势逻辑、留白),再在这里换掉全部具体物件、保留结构。见 aesthetic-director-core/references/taste-calibration-pairs.md Pair 5。

自检

  • 命题里有动词吗?
  • 只有一个主锚点吗?
  • 服装四层每层都有形状和位置,没有一处是形容词?
  • 删掉颜色,轮廓还认得出?删掉装饰,基础服装还有独立剪裁?
  • 姿势会改变头发 / 衣摆 / 道具 / 光的位置吗?
  • 叙事残留是她造成的吗?
  • 刺点只有一个、有精确位置?
  • 有"删掉的"和"否决的方向"两行吗?
  • 踩了 personal-identity-profile/references/design-dislikes.md 吗?
  • 锁定事实完整传下去了吗?

References

  • references/oc-design-system.md — 六层结构、五种轮廓策略、姿势-镜头对应、展示方式、复杂度控制、反平庸检查、开放式请求默认行为
  • references/garment-lexicon.md — 穿搭原型、四层叠穿、不对称手法、材质碰撞矩阵、领/袖/腰/裙词汇(英文短语可直接进 prompt)
  • references/maximalist-oc-design-grammar.md — 极繁精美人设专用设计语法:宏观轮廓、服装多层、统一母题、非对称重量、材质碰撞、多尺度细节与 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.

Habilidades Relacionadas