Communitygithub.com

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.

Was ist personal-agent-skills?

personal-agent-skills is a Gemini CLI agent skill that 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.

Funktioniert mit~Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/02_creation/general-image-prompt-adapter

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

General Image Prompt Adapter

定位

输入:blueprint(来自 character-design-engine / illustration-direction)+ 目标模型名(可缺省)。 输出:一段英文自然语言 prompt(代码块),以及——仅当目标官方支持时——放在 prompt 外的参数行。 不做:设计。收到的不是 blueprint(没有带动词的命题、轮廓、四层服装、一个刺点、锁定事实)就退回 aesthetic-director-core。 不做:编造模型行为。本 Skill 覆盖的模型很多、变化很快;不确定就写 [Unverified],不要猜参数。

硬规则

  • 目标模型未知且会影响格式 → 问一个问题:"用哪个模型出图?不确定就按通用自然语言写。" 不列选项清单。
  • prompt 正文只放视觉描述。--ar、权重、采样器、负面词等不进正文,除非该目标的官方文档支持且 owner 要。
  • 任何"某模型对 X 更敏感"的说法带证据标签。references/target-notes.md 里的每条都已标注;表里没有的目标一律 [Unverified]。
  • 不加 masterpiece, 8k, ultra-detailed, award-winning 一类空泛质量词。
  • 不改锁定事实。被 blueprint 删掉的东西不得以任何形式回来。

执行流程

Step 1  确认目标        owner 指定 / 从 Session State 读 / 问一个问题 / 缺省为 generic
Step 2  查目标笔记      references/target-notes.md:格式偏好、长度、是否支持参数,逐条看证据标签
Step 3  组织顺序        主体与景别 → 命题结构(轮廓的空间关系)→ 外观 → 服装四层(形状+位置+行为)
                        → 姿势因果与瞬间 → 环境(只留解释光/动作的一层)→ 主光源与衰减 → 配色三级与刺点位置
Step 4  写 prompt       连贯英文段落(不是逗号 tag 串,除非目标笔记说 tag 更稳)。
                        关系词优先:over / beneath / descending from / wrapping / weighed down by / the only saturated color is
Step 5  参数行          仅当目标官方支持:单独一行,放在代码块外或代码块末尾单独一行,标注 [Official]
Step 6  长度            generic 目标:60–120 词。超了先删重复形容词、次要配饰、背景枝节;不删命题、锚点、刺点、因果、锁定事实
Step 7  自检

输出契约

方向:<blueprint 的命题,一行>
目标:<模型名 或 generic>

```text
<English natural-language prompt>

参数(如适用):<e.g. --ar 3:4 --no jewelry> [Official] / 不适用

丢失与补救:<这个格式丢了什么关系,怎么补的,一到两行>


Standard mode 下同 `anima-prompt-compiler`:V1 忠实 + V2 增强,V2 不改 V1 事实。

## 翻译 blueprint 时的取舍

自然语言格式保留关系的能力最强,主要风险是**模型改写**(部分服务会在生成前重写 prompt)和**长度衰减**(尾部信息被忽略):

- 把锁定事实和刺点放在前 40 词内。
- 每个颜色词紧贴它的名词,只出现一次。
- "留下的怪"用一个完整短句写,不用单词——单词会被改写掉。
- 不写"no X"(很多模型把否定词当正向);用正向约束翻译:`bare neck and wrists` 而不是 `no jewelry`。目标官方支持排除参数时(如 MJ `--no`)再用参数。

## 自检

- [ ] 输入是 blueprint?
- [ ] 目标已确认或明确标 generic?
- [ ] 正文无参数、无质量词、无否定句?
- [ ] 锁定事实和刺点在前 40 词?
- [ ] 每个模型断言有证据标签?
- [ ] 被删的东西没回来?
- [ ] 有"丢失与补救"一行?

## References

- `references/target-notes.md` — 常见目标的格式笔记,逐条带证据标签;表外目标一律 [Unverified]

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

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.

Verwandte Skills