Communitygithub.com

Tera-Dark/personal-agent-skills

所有創作請求的入口。分類意圖(角色/插畫/時裝/提示詞/反推/審查/技術),載入身分與美學方向,再導向對應專家與模型轉接器。

personal-agent-skills 是什麼?

這個技能路由器(Creative Skill Router)是創意工作流程的中央調度器,專門處理 AI 智能體(如 Claude Code、Cursor 等平台)上的創作類請求。它不做最終產出,而是聚焦於「分類→載入上游→交給下游」三步驟。首先,它根據使用者請求判斷意圖(例如 OC 角色設計、插畫氛圍圖、提示詞編寫、圖片反推或技術工作如 ComfyUI/LoRA),然後總是載入使用者的身分檔案與美學方向核心,產出一份創意簡報(Creative Brief),最後轉交給對應的專家技能(如角色設計引擎、插畫導向、提示詞分析)與模型轉接器(如 NAI5 提示詞編譯器、Anima 提示詞編譯器)。此路由器採用嚴格的設計原則:創作類請求不會直接跳到模型轉接器,除非使用者已經提供完整的設計;設計決策與模型語法分離;混合請求(如「設計 OC + 訓練 LoRA」)會拆分為順序步驟。此外,它支援多種平台(包括 NovelAI、Anima、Midjourney、DALL-E、Stable Diffusion 等),並透過模組化 frontmatter 自動更新路由索引,無需手動維護觸發詞列表。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/01_router/creative-skill-router

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

Creative Skill Router

目的

把使用者請求送進正確的創作管線。Router 不產出最終 prompt,只做三件事:分類 → 載入上游 → 交給下游。

Request
  ↓
Task Classification            (references/task-classification.md)
  ↓
personal-identity-profile      (always, for any creative task)
  ↓
aesthetic-director-core        (always for creative tasks → produces a Creative Brief)
  ↓
Specialist                     (character-design-engine / illustration-direction / image-reverse-analysis / prompt-analysis)
  ↓
Model Adapter                  (anima-prompt-compiler / nai5-community-prompt-engineering)
  ↓
evaluation-loop                (on feedback rounds)

核心規則

  1. 創作類請求不得直接跳到模型轉接器。 使用者說「給我一個 NAI5 提示詞,主題是 X」——如果 X 還沒有被設計過,先過 aesthetic-director-core 再過轉接器。只有當使用者提供的是已經完成的設計(明確的角色事實、服裝、姿勢)時,才允許直接進轉接器。
  2. 依意圖分類,不依關鍵字。 使用者提到「NAI5」不代表任務是「寫 tag」,可能是「設計一個角色然後用 NAI5 出」。
  3. 設計決策與模型語法分離。 轉接器不重新設計;設計層不寫模型語法。
  4. 使用者明確要求 > 身分檔案 > 審美方向 > 專家 Skill > 模型語法。
  5. 混合請求拆開。 「設計 OC + 訓練 LoRA」→ character-design-engine 完成後再進 dataset-management / lora-training。
  6. 反饋輪走 evaluation-loop + aesthetic-director-core/references/feedback-diagnosis.md,不是直接改 prompt。

快速路由表

意圖觸發詞範例管線
角色 / OC / 服裝設計OC, 人設, 角色設計, 服裝設計, 立繪, 高定, 二游角色identity → director → character-design-engine → adapter
插畫 / 氛圍圖 / 故事感插畫, 氛圍圖, 豎屏, 半留白, 印象風, 故事感, key visualidentity → director → illustration-direction → adapter
已有設計 → 提示詞提示詞, prompt, tag, NAI5, NovelAI, Anima(且設計已完整)identity → adapter
參考圖反推反推, 分析圖片, 提取提示詞, 還原風格, 參考這張identity → image-reverse-analysis → director(若需原創)→ adapter
提示詞審查 / 最佳化最佳化提示詞, 這個 prompt 哪裡有問題prompt-analysis → (adapter if rewrite needed)
反饋 / 迭代太平淡, 太亂, 不像, 這版可以, 換個方向evaluation-loop → feedback-diagnosis → 回到失敗層
其它影像模型 → 提示詞Midjourney, DALL-E, Imagen, Flux, SD, 通用, 沒說模型identity → (director if unfinished) → general-image-prompt-adapter
技術ComfyUI, LoRA, dataset, 訓練, 打標comfyui-workflow / lora-training / dataset-management(status: planned → 以通用知識作答,標 [no module],提議 /new-module)
擴充模組命中 06_extensions/* 或其它模組 description 裡的觸發詞該模組
非創作、無模組命中閒聊、問答、雜務不載入模組;直接依 kernel §6 的語氣回答

模型選擇規則見 references/model-selection.md。完整模組索引以 harness 的 KERNEL §5(由 bundle/manifest.json 生成)為準;docs/skill-registry.md 是同一份資料的可讀版本。

觸發詞來自模組自己

Router 不維護一份手寫的觸發詞總表。每個模組的 frontmatter description 和 metadata.triggers 就是它的觸發條件,build 會把它們彙總進索引。新增模組只要把自己的觸發詞寫好,Router 就能路由到它。

Router 的輸出

Router 本身不對使用者輸出長篇內容。它在內部決定管線後直接開始執行第一步。如果分類有歧義(例如「幫我做一個角色」沒說要不要 prompt、要什麼模型),用一個問題確認,不要列一堆選項。

References

  • references/task-classification.md — 分類規則與觸發詞
  • references/routing-rules.md — 優先級與衝突解決
  • references/model-selection.md — 何時選 Anima / NAI5 / 通用模型
  • references/execution-flow.md — 標準管線與失敗恢復
  • references/skill-map.md — 各層 Skill 一覽

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

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.

相關技能