Communitygithub.com

Tera-Dark/personal-agent-skills

將參考圖像解構成可轉移的設計語言——輪廓與質量分佈、母題語法、服裝構成、材質對比、色調層級、姿勢邏輯、負空間與呈現格式——而非輸出標籤堆疊。輸出可饋送至美學指導核心(用於原創作品)或模型轉接器(用於忠實還原)。用於反推、分析圖片、提取提示詞、還原風格、參考這張圖、reverse prompt、image analysis。

personal-agent-skills 是什麼?

此技能(Image Reverse Analysis)專注於將參考圖像解析為結構性設計語言,而非簡單的關鍵詞標籤清單。它支援兩種主要任務路徑:忠實還原(輸出至模型轉接器,保留具體物件、構圖與配色)與原創參考(輸出至美學指導核心,僅保留結構原則,替換具體物件)。分析過程涵蓋 11 個維度,包括輪廓、質量分佈、母題語法、服裝構成、材質對比、色調層級、姿勢邏輯、光線、負空間、呈現格式與情感機制。最終輸出包含結構拆解、真正起作用的原則、可遷移與不可遷移部分,以及下一步行動指引。此技能適用於 Claude Code 等 AI 代理平台,特別適合設計師、藝術家與提示詞工程師進行風格分析、原創設計或提示詞提取。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/03_analysis/image-reverse-analysis

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

圖片反向分析

定位

參考圖 → 結構,不是參考圖 → 名詞。

v2.0.0 合併了原先三處重複的反推流程(本 Skill、skills/nai5-prompt-engineering/references/reverse-image-analysis.md、anima-prompt-compiler § 5)。適配器不再各自持有反推邏輯。

兩種任務,先分清

用戶要的是輸出去向
忠實還原這張圖("把這張圖的 prompt 反推出來")本 Skill → 模型適配器。保留具體物件、構圖、配色。
參考這張圖的感覺做原創("參考這張,但要原創")本 Skill → aesthetic-director-core → character-design-engine。只保留結構,換掉全部具體物件。

沒說清時問一句。默認是後者(這個用戶的絕大多數需求)。

分析順序

先看用戶給的這張圖,不要用網路搜尋的同類圖替代它。

1. Silhouette      外輪廓由哪幾個大形狀組成?縮圖裡認得出的是什麼?
2. Mass            裝飾 / 密度集中在頭、胸腰、背、四肢中的哪裡?哪裡是空的?
3. Motif grammar   重複出現的形態語言是什麼(蛇 / 骨 / 花 / 線 / 布褶 / 直線 / 弧)?在幾處出現?怎麼變形?
4. Garment         base / structural / signature extension / accessory 四層各是什麼?剪裁在哪裡?
5. Material        哪兩種材質在對抗?對抗落在哪個結構上?
6. Palette         基底 / 結構 / 刺點三級分別是什麼顏色、落在哪?刺點有幾個(理想是一個)?
7. Pose logic      她在做什麼?姿勢和道具 / 附屬結構有沒有物理接觸?因果鏈是什麼?
8. Light           主光源方向、衰減、陰影沉降區。有沒有無來源光?
9. Negative space  哪些區域刻意留白?為什麼?
10. Presentation   clean plate / decorated key visual / editorial plate / environmental vignette?
11. Mood mechanism 氣質是怎麼達成的?(不是"神祕"——是"生物的眼睛 + 她的鬆弛之間的反差")

輸出契約

## 結構拆解
1–11 每項一到兩行,指向圖上的具體位置。

## 真正在起作用的(3–5 條)
去掉具體物件後仍然成立的原則。例:"一個巨大環形輪廓讓白底上的剪影一眼可讀",而不是"有蛇"。

## 可遷移 / 不可遷移
可遷移:結構原則。
不可遷移:具體角色身份、商標、專屬構圖、版權元素。

## 下一步
→ 忠實還原:交給 [adapter],附鎖定事實清單。
→ 原創:交給 aesthetic-director-core,附"真正在起作用的"清單作為約束。

禁止

  • 輸出 white background, anime, detailed, intricate, elegant 這類無結構資訊的詞
  • 用"換名詞"當原創(蛇 → 龍)
  • 把用戶的參考圖替換成搜尋到的"類似圖"
  • 複製具體角色 / 版權設定,除非用戶明確要求忠實還原

範例

見 aesthetic-director-core/references/taste-calibration-pairs.md Pair 5:蛇形環繞參考圖 → 五條結構原則 → 蠶絲少女原創。

References

  • references/design-language-extraction.md — 輪廓 / 色彩 / 時裝結構 / 情緒的提取要點與重構原則

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

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

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