Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add renky1025/agent-skills --skill spec-imagegit clone --depth 1 https://github.com/renky1025/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/renky1025/agent-skills/spec-image)<a href="https://agentmods.dev/skills/renky1025/agent-skills/spec-image"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/spec-image/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/renky1025/agent-skills/spec-image"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/spec-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00173 | $0.01735 |
| Opus 5 | $0.00086 | $0.00868 |
| Sonnet 5 | $0.00035 | $0.00347 |
| Haiku 4.5 | $0.00017 | $0.00173 |
Grade A, and why
spec-image scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-image: 工程化出图
核心思想：出图不是抽卡，是写工程规格书。 能用参数控制的属性绝不堆进 Prompt；Prompt 只聚焦视觉语义；编辑任务必须明确"改什么"与"绝对不改什么"。
用法
/spec-image <需求描述> [--ratio=1:1|3:2|2:3|16:9] [--quality=auto|low|medium|high]
[--transparent] [--edit=<原图路径>] [--ref=<图1,图2,...>] [--count=N]
执行流程（六步，不可跳步）
Step 1: 任务分类（决定走哪条流水线）
| 任务类型 | 判定条件 | 走法 |
|---|---|---|
| GEN 文生图 | 只有文字需求 | 加载 references/workflows.md 匹配最接近的场景模板 |
| EDIT 局部编辑 | 提供 --edit 原图 + 修改指令 |
套用"改动与约束分离"契约（见 Step 4） |
| MULTI-REF 多图合成 | 提供 >=2 张 --ref |
为每张图编号并指定角色分工（见 Step 4） |
| EXTRACT 透明抠图 | 提供 --edit + 要求透明底 |
参数 transparent + 反棋盘格/反阴影负向约束 |
| SERIES 一致性系列 | 需要多张图保持主体一致 | 两阶段法：先生成角色卡，再逐场景延续 |
Step 2: 参数决策（参数管物理，Prompt 管语义）
将需求映射到当前环境可用的图像生成/编辑工具的实际参数。若工具不支持某参数，则将等价指令折进 Prompt（如横竖版写明 "wide horizontal composition"）。
| 属性 | 决策规则 |
|---|---|
| 画幅 ratio | 电商主图/UI 原型/人像竖版 2:3；海报横版 3:2 或 16:9；头像/图标 1:1 |
| 质量 quality | 默认 medium；含精确文字/信息图/图表/多步骤流程一律 high；草稿初筛可 low |
| 透明通道 | 需要 PNG/WebP 透明底时显式开启，且 Prompt 必须同时声明"无实体底色、无棋盘格、边缘干净" |
| 数量 count | 探索阶段 2-4 张；定稿迭代阶段 1 张 |
禁止：把"4K、超高清、杰作、史诗感"写进 Prompt —— 分辨率归参数管，抽象修饰词只会引入噪声。
Step 3: 构建 Spec 结构化 Prompt
复杂需求必须四段式，简单需求至少含主体 + 约束：
[Scene] 场景与环境：地点、时间、光线（具体的：午后 45 度柔和侧光，而非"好的光照"）
[Subject] 主体定义：外观特征 + 三个关键维度（身体构图 / 视线朝向 / 与环境的真实交互）
[Details] 可见细节：材质（风化皮革、拉丝不锈钢）、色彩体系、拍摄介质（35mm 胶片、50mm 镜头）
[Constraints] 正向约束 + 负向约束（No extra text, no watermarks, no ...）
具体化三原则：
- 具体可见的细节取代情绪空话：写"可见毛孔皱纹、胶片颗粒、轻微暗角"，不写"超真实、大师级"。
- 人物必锁三维度：全身构图是否含双脚、视线看哪里、双手在做什么 —— 缺一会出现肢体僵硬/假人感。
- 文字渲染铁律：所有要出现在画面里的文字用双引号包裹 + 显式频次（"Render the tagline exactly once"）+ 字体特征与位置 + "No extra text"兜底。生僻词逐字母拼写。
Step 4: 编辑与多图契约
EDIT 模式核心公式（受保护属性必须逐条列出）：
仅修改 [X]。
严格保持：[人物身份特征 / 五官 / 姿态 / 光照 / 机位 / 背景 / 画面质量] 不变。
MULTI-REF 模式：每张图编号 + 明确分工。例："图 1 作为背景与光影基准；将图 2 中的主体提取置入图 1 的人物身旁，保持透视与投影一致。Do not change anything else."
SERIES 一致性两阶段：
- 阶段一：生成角色卡（Character: 服装/特征/气质逐项锁定；Style: 画风；Constraints: no text）
- 阶段二：每张新图重申 "Same [服装/五官/配色/气质]，Do not redesign the character"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 96 lines · 173 tokens per session scan A 52b4ad21ec3a
spec-image is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 1,735 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
create-xilehui-brand-poster
A design workflow for creating and reviewing branded event materials for Xiamen University's School of Management alumni association. It covers posters, digital tickets, registration graphics, social-media images, screen graphics, and editable designs.
xilehui-header-footer-template
A reusable template for the top identity section, bottom information section, and transparent middle overlay of a vertical alumni poster for Xiamen University’s School of Management ME alumni group.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.