Communitygithub.com

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.

personal-agent-skills란 무엇인가요?

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

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

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서


name: evaluation-loop description: 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. metadata: author: Tera-Dark version: "2.0.0" layer: "05_evaluation" load: "always" status: "active" triggers: "太平淡, 太乱, 不像, 没人味, 这版可以, 评价一下, 哪里不对, compare"

Evaluation Loop

定位

生成 → 评价 → 定位失败层 → 只修那一层 → 再生成。

本 Skill 不修 prompt。它决定该谁修:设计层问题回 aesthetic-director-core / character-design-engine / illustration-direction;语法与伪影问题回对应适配器。

评价顺序(从上往下,第一个失败的层就是要修的层)

1. 命题        看图能不能说出"这是关于什么的"?有动词吗?
2. 身份一致    锁定事实(发色、瞳色、服装件、姿势)是否 100% 保留?
3. 轮廓        缩略图尺寸认得出吗?
4. 服装结构    四层是否可读?颜色是否绑定到正确的件?有没有融色?
5. 因果 / 瞬间 姿势有没有解释服装和道具?是状态还是时刻?
6. 密度 / 刺点 有密集区和安静区吗?刺点是一个还是多个?
7. 那一处怪    在吗?只有一处吗?
8. 未授权添加  有没有出现 blueprint 里没有的东西(耳环、腰带、手表、粒子、翅膀)?
9. 空间 / 构图 景别对吗?多图层是否隔离?背景抢戏吗?
10. 光         有物理来源和衰减吗?
11. 输出契约   格式对吗?有没有禁用质量词 / 多余负面 / 参数?

技术质量(手、解剖、清晰度)排最后。 一张技术正确的图仍然可以因为没有人而失败。

六维评分表(与 tests/test-suite.md 一致)

维度PassFail
Identity Preservation锁定事实 100% 一致改了发色 / 瞳色 / 关键特征
Outfit Attribute Binding材质与颜色紧贴对应服装件外套颜色渗入内搭;领口材质混淆
Spatial & Layout Clarity景别 / 构图 / 图层隔离清楚展示板出双胞胎;背景喧宾夺主
Unrequested Additions无未授权物件 / 世界观出现赛博配件、翅膀、手表、粒子
V1/V2 Fact ConsistencyV2 未改 V1 事实V2 把白发改成金发
Output Contract格式正确,无禁用词,无多余负面出现 masterpiece;夹带独立 Negative

外加一行 Design Read:命题 ___ / 轮廓 ___ / 因果 ___ / 密度 ___ / 刺点 ___ / 怪 ___(各一个词:成立 / 弱 / 缺失)。

输出契约

诊断:失败在 [层]。原因一句话。
六维:IP ✓/✗ · OB ✓/✗ · SC ✓/✗ · UA ✓/✗ · VC ✓/✗ · OC ✓/✗
Design Read:命题 成立 / 轮廓 弱 / 因果 缺失 / 密度 成立 / 刺点 多于一个 / 怪 缺失
下一步:交给 [skill],只改 [一个变量],锁定 [其它一切]。

不写长篇评语。不夸。不列十条建议——一条,最上面那层的。

反馈翻译

用户原话 → 失败层 → 动作,见 aesthetic-director-core/references/feedback-diagnosis.md。本 Skill 直接引用那张表,不另维护。

三条元规则

  1. 一次一层,一次一个变量。
  2. 用户认可的版本:记录成功维度到 personal-identity-profile/references/taste-signature.md § 5。
  3. 一次否决不升格为永久规则;≥3 次或用户明说才写入 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.

관련 스킬