Communitygithub.com

Tera-Dark/personal-agent-skills

根據固定評估標準(身份保留、服裝貼合、空間清晰度、未授權添加、V1/V2一致性和輸出契約)以及設計層次解讀(主題、輪廓、因果、密度、刺點、一個奇怪之處),評估生成的圖像或編譯提示是否忠於原始創意簡報和藍圖。診斷出失敗的層次,並透過單一變數更改將修正路由到該層。適用於任何反饋回合:太平淡、太亂、不像、沒人味、這版可以、評價一下、哪裡不對、比較版本。

personal-agent-skills 是什麼?

該技能實現了一個嚴謹的生成評估循環,用於基於圖像的 AI 代理(如 Claude、Cursor、Codex)工作流程,特別是在需要迭代式視覺內容生成的創意項目中(例如角色設計、插畫或概念藝術)。它的核心是一套固定評估標準(身份保留、服裝貼合、空間清晰度、未授權添加、V1/V2一致性、輸出契約),加上深層設計層次分析(主題、輪廓、因果、密度、刺點、一個奇怪之處),能精確診斷生成的圖像或提示在哪個層面失敗。與其提供廣泛的建議,不如直接將修正路由到相關的專門技能(如 `aesthetic-director-core` 或 `character-design-engine`),並指定一個單一變數更改,同時鎖定其他所有內容,從而實現專注且高效的修正。該技能支援主觀反饋的翻譯(例如「太平淡」映射到密度層),記錄被批准的版本以建立個人品味檔案,並遵循嚴格的規則:每次只處理一個層次和一個變數。它提供一個六維評分錶、結構化輸出合約,並優先考慮設計層次問題(如沒有人味或缺乏宇宙因果關係),而不是純粹的技術缺陷。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/05_evaluation/evaluation-loop

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

評估循環

定位

生成 → 評估 → 定位失敗層 → 只修那一層 → 再生成。

本 Skill 不修 prompt。它決定該誰修:設計層問題回 aesthetic-director-core / character-design-engine / illustration-direction;語法與偽影問題回對應適配器。

評估順序(從上往下,第一個失敗的層就是要修的層)

1. 命題        看圖能不能說出「這是關於什麼的」?有動詞嗎?
2. 身份一致    鎖定事實(髮色、瞳色、服裝件、姿勢)是否 100% 保留?
3. 輪廓        縮圖尺寸認得出嗎?
4. 服裝結構    四層是否可讀?顏色是否綁定到正確的件?有沒有融色?
5. 因果 / 瞬間 姿勢有沒有解釋服裝和道具?是狀態還是時刻?
6. 密度 / 刺點 有密集區和安靜區嗎?刺點是一個還是多個?
7. 那一處怪    在嗎?只有一處嗎?
8. 未授權添加  有沒有出現 blueprint 裡沒有的東西(耳環、腰帶、手錶、粒子、翅膀)?
9. 空間 / 構圖 景別對嗎?多圖層是否隔離?背景搶戲嗎?
10. 光         有物理來源和衰減嗎?
11. 輸出契約   格式對嗎?有沒有禁用質量詞 / 多餘負面 / 參數?

技術質量(手、解剖、清晰度)排最後。 一張技術正確的圖仍然可以因為沒有人而失敗。

六維評分錶(與 tests/test-suite.md 一致)

維度PassFail
Identity Preservation鎖定事實 100% 一致改了髮色 / 瞳色 / 關鍵特徵
Outfit Attribute Binding材質與顏色緊貼對應服裝件外套顏色滲入內搭;領口材質混淆
Spatial & Layout Clarity景別 / 構圖 / 圖層隔離清楚展示板出雙胞胎;背景喧賓奪主
Unrequested Additions無未授權物件 / 世界觀出現賽博配件、翅膀、手錶、粒子
V1/V2 Fact ConsistencyV2 未改 V1 事實V2 把白髮改成金髮
Output Contract格式正確,無禁用詞,無多餘負面出現 masterpiece;夾帶獨立 Negative

外加一行 Design Read:命題 ___ / 輪廓 ___ / 因果 ___ / 密度 ___ / 刺點 ___ / 怪 ___(各一個詞:成立 / 弱 / 缺失)。

輸出契約

診斷:失敗在 [層]。原因一句話。
六維:IP ✓/✗ · OB ✓/✗ · SC ✓/✗ · UA ✓/✗ · VC ✓/✗ · OC ✓/✗
Design Read:命題 成立 / 輪廓 弱 / 因果 缺失 / 密度 成立 / 刺點 多於一個 / 怪 缺失
下一步:交給 [skill],只改 [一個變數],鎖定 [其它一切]。

不寫長篇評語。不誇。不列十條建議——一條,最上面那層的。

反饋翻譯

用戶原話 → 失敗層 → 動作,見 aesthetic-director-core/references/feedback-diagnosis.md。本 Skill 直接引用那張表,不另維護。

三條元規則

  1. 一次一層,一次一個變數。
  2. 用戶認可的版本:記錄成功維度到 personal-identity-profile/references/taste-signature.md § 5。
  3. 一次否決不升格為永久規則;≥3 次或用戶明說才寫入 design-dislikes.md。

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

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.

相關技能