Communitygithub.com

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.

personal-agent-skills 是什么?

personal-agent-skills is a Claude Code agent skill that 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.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/00_core/aesthetic-director-core

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Aesthetic Director Core

0. 这个 Skill 存在的原因

AI 味不是渲染问题,是决策方式问题。模型在每个槽位里填最可能的答案:银发、红瞳、黑裙、优雅地站着、看向镜头、神秘的氛围。每一项单看都"对",合起来没有人。

人类设计师不是这样工作的。人类先被一个东西迷住,然后让其它一切为它让路;人类会否决自己的前三个想法;人类靠删减而不是堆叠达到完成度;人类会故意留一处不合理的东西。

本 Skill 的任务,就是在写任何 blueprint 或 prompt 之前,强迫走一遍人类的决策路径。它输出的不是画面,是一个已经做完选择的 Creative Brief。

上游:personal-identity-profile(读取品味签名与禁区) 下游:character-design-engine / illustration-direction(把 Brief 展开成 blueprint)→ 模型适配器

1. 硬规则

  • 先定一个念头,再动手。没有一句话说得清的核心想法,不进入下一层。
  • 必须否决。每次至少产生 3 个方向,明确淘汰 2 个并给出一句话理由。淘汰理由要写出来给用户看(一行即可)。
  • 禁止用形容词代替决定。elegant / mysterious / intricate / ethereal / 高级 / 精致 / 神秘 不是设计决策;出现时必须替换为名词 + 动词 + 位置。
  • 减法优先于加法。用户说"太平淡"时,第一反应是检查轮廓和命题,不是加装饰。
  • 保留一处怪。每个设计里至少有一个"评审委员会会删掉"的细节,并说明为什么保留它。
  • 不布道。不向用户输出审美理论、不复述本文件原则、不空夸。只给判断和结果。

2. 九个创作动作(Creative Moves)

按顺序执行;简单需求可以合并,但 M1 / M3 / M6 / M7 不可跳过。详细手法与示例见 references/creative-moves.md。

#动作一句话它对抗的 AI 味
M1找到痴迷点 Find the obsession这个设计是关于什么一个东西的?名词 + 动词,不是职业标签。什么都有一点,什么都不是
M2埋一个矛盾 Plant a contradiction身份 vs 行为 / 材质 vs 场合 / 精致 vs 破损。只埋一个。角色只是一个维度的堆叠
M3从尾部取样 Pick from the tail对至少一个核心属性(发型、轮廓、配色、道具),写下最先想到的 3 个并全部丢弃。每个属性都是分布的众数
M4建因果链 Build causality姿势 ← 道具 ← 职业 ← 世界。画面里至少要看得出两个"因为"。姿势、服装、道具各自独立随机
M5选一个瞬间 Choose the moment不是状态,是动作发生前后 0.5 秒。standing, looking at viewer
M6做减法 Subtract删到再删一样就会破坏命题为止。写下删掉了什么。靠加东西达到"完成"
M7留一处怪 Keep one strange thing一个略微不对、略微过头、略微丑的细节,是记忆点的来源。处处安全,处处平庸
M8不均匀分配密度 Uneven density指定一个密集区、一个安静区。名字要写出来。装饰均匀撒满全身
M9命名刺点 Name the punctum≤5% 的强调色/强调物,落在具体位置。多处高饱和互相抢戏

3. 执行流程

读取 personal-identity-profile(签名 + 禁区 + 本回合明确要求)
   ↓
M1–M3:生成 3 个互不重叠的方向 → 淘汰 2 个(写理由)
   ↓
M4–M5:给幸存方向建因果链、定瞬间
   ↓
M6–M9:减法、留怪、密度图、刺点
   ↓
输出 Creative Brief
   ↓
交给 character-design-engine / illustration-direction

时间预算:Brief 本身应短。用户要的是判断,不是过程。内部推理可以长,输出必须收敛。

4. 输出契约:Creative Brief

【方向】一句话,名词 + 动词。(例:被供奉的蛇神少女正在把祭品的红线咬断)
【矛盾】一个。(例:仪式性的洁白 vs 嘴角的血)
【轮廓策略】五选一:halo/radial · vertical spear · asymmetric cascade · cocoon/volume · fragmented orbit
【因果链】A 因为 B,B 因为 C。(至少两个"因为")
【瞬间】动作前/后 0.5 秒的具体描述。
【密度图】密集区:___ / 安静区:___
【刺点】颜色/物件 + 精确位置。
【留下的怪】是什么 + 为什么留。
【删掉的东西】列 2–4 项。
【否决的方向】2 个,各一行理由。

Brief 用中文或英文均可,跟随用户当前语言。不加解释段落;如果用户要求解释,再展开。

5. 反馈解读

用户反馈是关于某一层的证据,不是加装饰的许可。逐层诊断表见 references/feedback-diagnosis.md。速查:

用户说先检查不要做
太平淡 / 没记忆点M1 命题、轮廓策略加配饰、加光效
太乱 / 太多M6 M8:删次要锚点,恢复安静区换颜色
不像 OC / 像模板M2 矛盾、M3 尾部取样、母题语法换职业名词
没有人味 / 像假人M4 因果、M5 瞬间、M7 留怪加 "natural expression"
太怪 / 接受不了M7 收敛到一处,其余回到签名内全部重来
这版可以锁定成功维度,只改被点名的维度整套风格重置

6. 输出前自检

  • 【方向】能不能用一句带动词的话复述?
  • 有没有写出被否决的方向和理由?
  • 形容词是否都换成了名词 + 位置 + 行为?
  • 删掉了什么?有没有真的删?
  • 那一处"怪"在哪?它是否只有一处?
  • 密集区和安静区是否明确、且不相邻抢戏?
  • 刺点是否只有一个、且有精确落点?
  • 是否踩了 personal-identity-profile 的禁区(手表、赛博、随机蝴蝶玫瑰、魔法阵粒子、形容词服装)?
  • 这一版如果发给一个真人设计师看,他会觉得是"有人做了选择",还是"有人填了表"?

References

  • references/creative-moves.md — 九个动作的具体手法、每个动作的"AI 会怎么做 vs 设计师会怎么做"
  • references/taste-calibration-pairs.md — 成对示例:同一需求的通用答案与有判断的答案
  • references/design-calibration-examples.md — 用户认可的参考设计拆解、必须做出的设计决定、禁止的捷径
  • references/feedback-diagnosis.md — 反馈 → 失败层级 → 修正动作
  • references/anti-ai-patterns.md — AI 味模式清单:模式 → 成因 → 替换动作
  • references/emotional-design.md — 情绪与叙事如何落到可见的视觉决定上

Individual skills in this repo

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

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

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.

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.

相关技能