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 IvanYangYangXi/artclaw_bridge --skill sd-learned-recipesgit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/sd-learned-recipes)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/sd-learned-recipes"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/sd-learned-recipes/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/ivanyangyangxi/artclaw_bridge/sd-learned-recipes"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/sd-learned-recipes.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 | $0.00149 | $0.01030 |
| Opus 5 | $0.00075 | $0.00515 |
| Sonnet 5 | $0.00030 | $0.00206 |
| Haiku 4.5 | $0.00015 | $0.00103 |
Grade A, and why
sd-learned-recipes 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 12d ago.
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.
What it actually says
SD 材质配方库
从 SD 12.1.0 全部 30 个内置 PBR 材质逆向分析，提炼出可复用的制作配方。 制作任何材质前，先查此库选择正确的管线设计和纹理源。
配方文件索引
通用配方（所有材质适用）
| 文件 | 内容 | 何时读取 |
|---|---|---|
recipes/_overview.md |
总览 + 跨材质统计 + 选择指南 | 必读：开始前 |
recipes/output_pipeline.md |
输出通道标准管线（Height优先原则） | 必读：构建输出时 |
recipes/coloring.md |
着色管线：灰度→彩色的三种方案 | 需要 BaseColor 时 |
recipes/weathering.md |
做旧/风化/污渍叠加的三级策略 | 需要真实感时 |
类别配方（按需读取）
| 文件 | 材质数 | 适用 |
|---|---|---|
recipes/concrete.md |
10 个 | 混凝土/水泥/路面 |
recipes/metal.md |
5 个 | 金属/金属板/锈蚀 |
recipes/tile.md |
5 个 | 瓷砖/地砖/马赛克 |
recipes/brick.md |
2 个 | 砖墙/砌体 |
recipes/fabric.md |
3 个 | 布料/织物/编织 |
recipes/wood.md |
2 个 | 木材/木板/木纹 |
recipes/organic.md |
3 个 | 碎石/纸张/纸板 |
快速决策树
要做什么材质？
├→ 硬质表面
│ ├→ 有规则排列？ → tile.md 或 brick.md
│ ├→ 金属？ → metal.md
│ └→ 粗糙不规则？ → concrete.md
├→ 有机/软质
│ ├→ 编织结构？ → fabric.md
│ ├→ 木纹方向性？ → wood.md
│ └→ 颗粒/纤维？ → organic.md
└→ 不确定 → 先读 _overview.md 的类别纹理源表
核心发现速查
- Height 优先: 先构建灰度高度图，Normal/AO/Height 三通道从同一源分叉
- Blend 是核心: 平均每材质 33 个 blend（SD 材质 = blend 叠加的艺术）
- 着色在末端: 灰度处理完成后才进入着色环节
- 做旧必备: moisture_noise(80%使用率) + bnw_spots(60%)
- tile_generator 万能: 不只用于瓷砖，碎石(6个)、木板(5个)、混凝土(3个)都用
使用方法
# 在 SD 中读取配方
import os
recipes_dir = os.path.expanduser(r"~\.openclaw\workspace\skills\sd-learned-recipes\recipes")
# 先读总览
with open(os.path.join(recipes_dir, "_overview.md"), "r", encoding="utf-8") as f:
overview = f.read()
# 再读对应类别
with open(os.path.join(recipes_dir, "concrete.md"), "r", encoding="utf-8") as f:
recipe = f.read()
What ships with it
11 files 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.
- 12d ago First seen · 85 lines · 149 tokens per session scan A 98cdf48f20ed
sd-learned-recipes is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 149 tokens to every session and 1,030 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
maya-pipeline
Domain skill — Maya asset pipeline orchestration: set up project directory structures, export scenes to USD, and coordinate multi-step DCC workflows. Use when initialising a Maya project or exporting assets for a downstream pipeline. Not for raw geometry editing — use maya-geometry for that. Not for low-level USD file…
imagemagick-tools
Infrastructure skill — image processing and manipulation via ImageMagick: resize, composite, convert formats, add watermarks. Use when batch-processing textures, thumbnails, or rendered images at the file level. Not for in-DCC texture or material editing — use a domain skill bound to the specific DCC for that.
asset-source
Gateway skill for cross-DCC asset import — search and resolve assets into a validated AssetDescriptor (local path + attribution). Demo source returns static catalog entries; production sources can add download or remote resolution without changing the contract.
usd-tools
Infrastructure skill — low-level OpenUSD scene inspection and validation: read layer stacks, traverse prims, validate USD schemas. Use when working directly with raw USD files (usda, usdc, usdz) or verifying USD compliance. Not for Maya-specific USD export — use maya-pipelineexportusd for that. Not for full DCC…
spatial-interchange
Plan deterministic coordinate-axis and unit conversions between DCCs, engines, and interchange formats from explicit right/up/forward axes and meters-per-unit values.