Communitygithub.com

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.

personal-agent-skills 是什么？

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

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Tera-Dark/personal-agent-skills/tree/HEAD/01_router/creative-skill-router
查看原文→浏览所有技能

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

文档

Creative Skill Router

Purpose

把用户请求送进正确的创作管线。Router 不产出最终 prompt，只做三件事：分类 → 加载上游 → 交给下游。

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)

Core Rules

  1. 创作类请求不得直接跳到模型适配器。 用户说"给我一个 NAI5 提示词，主题是 X"——如果 X 还没有被设计过，先过 aesthetic-director-core 再过适配器。只有当用户提供的是已经完成的设计（明确的角色事实、服装、姿势）时，才允许直接进适配器。
  2. 按意图分类，不按关键词。 用户提到"NAI5"不代表任务是"写 tag"，可能是"设计一个角色然后用 NAI5 出"。
  3. 设计决策与模型语法分离。 适配器不重新设计；设计层不写模型语法。
  4. 用户明确要求 > 身份档案 > 审美方向 > 专家 Skill > 模型语法。
  5. 混合请求拆开。 "设计 OC + 训 LoRA" → character-design-engine 完成后再进 dataset-management / lora-training。
  6. 反馈轮走 evaluation-loop + aesthetic-director-core/references/feedback-diagnosis.md，不是直接改 prompt。

Quick Routing Table

意图触发词示例管线
角色 / OC / 服装设计OC, 人设, 角色设计, 服装设计, 立绘, 高定, 二游角色identity → director → character-design-engine → adapter
插画 / 氛围图 / 故事感插画, 氛围图, 竖屏, 半留白, 印象风, 故事感, key visualidentity → director → illustration-direction → adapter
已有设计 → 提示词提示词, prompt, tag, NAI5, NovelAI, Anima（且设计已完整）identity → adapter
参考图反推反推, 分析图片, 提取提示词, 还原风格, 参考这张identity → image-reverse-analysis → director（若要原创）→ adapter
提示词审查 / 优化优化提示词, 这个 prompt 哪里有问题prompt-analysis → (adapter if rewrite needed)
反馈 / 迭代太平淡, 太乱, 不像, 这版可以, 换个方向evaluation-loop → feedback-diagnosis → 回到失败层
其它图像模型 → 提示词Midjourney, DALL-E, Imagen, Flux, SD, 通用, 没说模型identity → (director if unfinished) → general-image-prompt-adapter
技术ComfyUI, LoRA, dataset, 训练, 打标comfyui-workflow / lora-training / dataset-management（status: planned → 以通用知识作答，标 [no module]，提议 /new-module）
扩展模块命中 06_extensions/* 或其它模块 description 里的触发词该模块
非创作、无模块命中闲聊、问答、杂务不加载模块；直接按 kernel §6 的语气回答

模型选择规则见 references/model-selection.md。完整模块索引以 harness 的 KERNEL §5（由 bundle/manifest.json 生成）为准；docs/skill-registry.md 是同一份数据的可读版本。

触发词来自模块自己

Router 不维护一份手写的触发词总表。每个模块的 frontmatter description 和 metadata.triggers 就是它的触发条件，build 会把它们汇总进索引。新增模块只要把自己的触发词写好，Router 就能路由到它。

What the Router Outputs

Router 本身不对用户输出长篇内容。它在内部决定管线后直接开始执行第一步。如果分类有歧义（例如"帮我做一个角色"没说要不要 prompt、要什么模型），用一个问题确认，不要列一堆选项。

References

  • references/task-classification.md — 分类规则与触发词
  • references/routing-rules.md — 优先级与冲突解决
  • references/model-selection.md — 何时选 Anima / NAI5 / 通用模型
  • references/execution-flow.md — 标准管线与失败恢复
  • references/skill-map.md — 各层 Skill 一览

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.

相关技能

steipete/sag

ElevenLabs text-to-speech with mac-style say UX.

community

steipete/oracle

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

community

steipete/peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

community

mattpocock/design-an-interface

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

community

mattpocock/prototype

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

community

mattpocock/grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

community