Communitygithub.com

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.

personal-agent-skills とは?

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

対応~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/02_creation/nai5-community-prompt-engineering

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント


name: nai5-community-prompt-engineering description: 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. metadata: author: Tera-Dark version: "2.0.0" layer: "02_creation" load: "on-demand" status: "active" triggers: "NAI5, NovelAI, NAI提示词, tag prompt, Danbooru, artist stack, char1"

NAI5 Community Prompt Engineering

1. 定位

本 Skill 是适配器:把已经做完设计决定的 blueprint 翻译成 NovelAI V5 社区格式。

v2.0.0 起合并了原 skills/nai5-prompt-engineering(v2.0.0)与 02_creation/nai5-community-prompt-engineering(v1)两个副本。原副本里的 "Personal Aesthetic Rules" 段已删除——品味只在 personal-identity-profile,本 Skill 不维护副本。

输入检查:同 anima-prompt-compiler。没有命题 / 轮廓 / 四层服装 / 刺点 / 锁定事实的输入不是 blueprint,退回 router。

2. 社区格式架构

[Artist Stack]

[Global Style Layer]

[Scene Base]

char1:
...

char2:
...

Negative:
...

详见 references/community-format.md。

3. Artist Stack

0.6::artist:name::
  • 每位画师承担一个明确职责:线条 / 上色 / 构图 / 角色设计感——不重复职责
  • 常见 5–12 位,权重 0.25–1.5
  • 必要时控制 -1::artist collaboration::
  • 画师选择服务 blueprint 的视觉语言,不替代设计。见 references/artist-stack.md

4. Global Style Layer

风格与角色数据分离。见 references/style-layer.md。

关于质量词的模型特例:personal-identity-profile/references/workflow-style.md 说"避免通用质量词"——那是针对 Anima 等模型。NovelAI 的质量 / 美学标签是训练过的有效 token,在 NAI 上保留:quality(如 masterpiece, best quality, very aesthetic)、complexity、rendering 三组各取所需,不堆叠。这是适配器层面的合法例外,不是对上游规则的违反。

5. Character Block

char1:
girl, [identity], [hair], [eyes], [expression], [outfit base→structural→extension→accessory], [props], [pose/action]
  • 身份 token 靠前;签名特征先于次要装饰
  • 一个 block 一个人;两人不混块
  • blueprint 的因果和密度要落成 tag 的顺序和取舍:主锚点相关 tag 靠前且完整,安静区只给一个大块面 tag(如 plain ankle-length robe),不给它加装饰 tag
  • 发型写形状分布,不写众数(asymmetrical hair, long hair on one side, undercut on the other 而不是 long hair)
  • 见 references/character-block.md、references/tag-taxonomy.md

6. Interaction Tags

多角色用 source# / target# / mutual#,动作紧跟所属角色。见 references/interaction-tags.md。

7. Scene Block

角色情绪与动作先于背景装饰。背景只保留能解释光或动作的一层。见 references/scene-block.md。

8. Weighting & Negative

1.5::tag::    -2::tag::
  • 只给:画师混合、关键风格方向、关键角色特征、不想要的风格抑制
  • 不给每个 token 都加权
  • Negative 解决具体问题(风格抑制、伪影),不复制大段通用负面表。见 references/weighting.md、references/negative-strategy.md

9. 翻译 blueprint 时的取舍

Tag 格式天然会丢失"关系"。补救:

  • 因果链 → 用复合 tag 保留最关键的一环(sleeve slipped to elbow, weight on left leg)
  • 密度图 → 用 tag 数量分布表达:密集区 6–10 个 tag,安静区 1–2 个
  • 刺点 → 颜色词只出现一次,紧贴它的落点名词(red thread on spool),其它地方不再出现该颜色
  • 留下的怪 → 必须进 char block,且靠前;它是记忆点
  • 删掉的东西 → 确认没有以 tag 形式偷偷回来(尤其 jewelry, earrings, belt, petals, sparkles)

10. 输出

用户要 NAI5 时默认输出社区格式代码块。不用 MJ 式长自然语言,除非用户要。

11. 反馈轮

  • 伪影 / 串线 / 权重问题 → 本 Skill 内单变量调整
  • 设计问题(太平淡、太乱、不像)→ 退回 evaluation-loop → aesthetic-director-core/references/feedback-diagnosis.md

12. 输出前检查

  • 输入是 blueprint?
  • 画师栈每位有职责、无重复?
  • char block 顺序反映了主锚点 / 安静区?
  • 刺点颜色只出现一次?
  • 被删掉的物件没有以 tag 回流?
  • 权重只用在必要处?
  • 锁定事实未改?

References

  • references/community-format.md — 整体格式
  • references/artist-stack.md — 画师栈工程
  • references/style-layer.md — 全局风格层(quality / complexity / rendering / 风格抑制)
  • references/character-block.md — 角色块顺序与规则
  • references/tag-taxonomy.md — tag 分类与服装描述法
  • references/interaction-tags.md — 多角色交互
  • references/scene-block.md — 场景块
  • references/weighting.md — 权重系统
  • references/negative-strategy.md — 负面策略

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

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

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.

関連スキル