模型测试 SKILL.md skillC
模型测试 from exo101/sd-webui-forge-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add exo101/sd-webui-forge-agent/模型测试@git:20261001.a173e4dPins git:20261001.a173e4d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 14 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- exo101/sd-webui-forge-agent
- Path
webui/extensions/sd-webui-agent-dev-2.5/skills/模型测试/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261001.a173e4d, committed Oct 1, 2026
- Size
- 3,517 bytes
- Repository stars
- 67
- License
- none declared
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Model Tester Skill（模型测试技能） ## 简介 这是一个用于对比测试不同图像生成模型的智能体技能。支持 Krea2 Turbo、Z-Image Turbo、Anima 三种模型的公平对比测试。 ## 功能特点 - **统一测试条件**：所有测试使用相同的提示词和分辨率设置 - **模型专属参数继承**：采样器、调度器和迭代步数使用智能体内部按模型架构定义的 preset，不由技能自行写死 - **图像反推支持**：可以上传参考图片，自动反推提示词进行测试 - **9:16 竖版尺寸**：统一使用 1024×1792 分辨率 ## 支持的模型及配置 ### Krea2 Turbo - 文本编码器 (TE): qwen3vl_4b_fp8_scaled.safetensors - VAE: qwen_image_vae.safetensors - 采样器/调度器/迭代步数：使用 Krea2 对应的智能体 preset ### Z-Image Turbo - 文本编码器 (TE): qwen_3_4b.safetensors - VAE: flux-ae.safetensors - 采样器/调度器/迭代步数：使用 Z-Image 对应的智能体 preset ### Anima（二次元专用） - 文本编码器 (TE): qwen_3_06b_base.safetensors - VAE: qwen_image_vae.safetensors - 采样器/调度器/迭代步数：使用 Anima 对应的智能体 preset ## 使用流程 ### 方式一：直接提示词测试 1. 向智能体助手提供要测试的提示词 2. 确认测试请求。 3. 依次切换模型并调用 `txt2img`。**不要在 `txt2img` 参数中填写 `steps`、`sampler_name`、`cfg_scale` 或调度器参数**，让智能体根据当前模型的 `preset_arch` 自动使用对应 preset；不要用 WebUI 全局默认值覆盖模型 preset。 4. 三个模型使用统一提示词和尺寸，但采样器、调度器、迭代步数和 CFG 可以按各自模型 preset 不同；最终对比表必须记录每个模型实际返回的参数。 5. 三个模型都生成完成后，必须调用 `stitch_images`，把本轮三张结果按 3 列拼成一张横向对比图；不要只把三张图依次发出。`images` 参数传入三张结果，`labels=["Krea2 Turbo", "Z-Image Turbo", "Anima"]`，`columns=3`，`padding=16`，`background_color=(245,245,245)`。 …
Read the whole file at its exact version.
How to install
mdr add exo101/sd-webui-forge-agent/模型测试@sha256:f4de702eda204036The line at the top of this page pins the label git:20261001.a173e4d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hazi5mpkqmdc7det)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 1, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3517 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
exo101/sd-webui-forge-agent · 67 stars · license none declared · pushed 2026-10-12 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_hazi5mpkqmdc7det GET https://markdownregistry.com/api/v1/resolve?ref=exo101/sd-webui-forge-agent/模型测试 GET https://markdownregistry.com/api/v1/blob/f4de702eda2040369d34fb4482aac629249f5c6f357aceebe5e11a986ecfa33c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.