Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/image-enhanceWrote 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/zju-real/easel/image-enhance)<a href="https://agentmods.dev/skills/zju-real/easel/image-enhance"><img src="https://agentmods.dev/badge/skills/zju-real/easel/image-enhance/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/zju-real/easel/image-enhance"><img src="https://agentmods.dev/badge/skills/zju-real/easel/image-enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00187 | $0.00945 |
| Opus 5 | $0.00093 | $0.00473 |
| Sonnet 5 | $0.00037 | $0.00189 |
| Haiku 4.5 | $0.00019 | $0.00094 |
Grade A, and why
image-enhance 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 10d 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
图片增强 / 放大
高质量放大 + 去噪 + 锐化 + 调色，改善偏糊/偏暗/有噪点的图片。走
skills/shared/scripts/img_enhance.py。
⚠️ 传统确定性增强，不是 AI 超分——能改善轻中度模糊/噪点，但无法凭空造细节。 要 AI 超分/重绘用 ai-image-gen（图生图）。常规缩放/裁切/压缩/水印见 image-editing。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 图片 | 是 | 要增强的图片（没给就问） |
| 放大倍数 | 否 | 默认 2 倍；1 表示只增强不放大 |
| 增强项 | 否 | 一键 --auto，或分别指定去噪/锐化/对比/饱和 |
输出（outputs/主题名/）
- 增强后的图片
- 报告：原尺寸→新尺寸、执行了哪些增强
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/img_enhance.py（enhance -h 看参数）。
# 一键增强 + 2 倍放大（最常用）
python skills/shared/scripts/img_enhance.py enhance -i blurry.jpg \
-o outputs/主题名/out.jpg --scale 2 --auto
# 噪点多的照片：去噪 + 4 倍 + 强锐化
python skills/shared/scripts/img_enhance.py enhance -i photo.jpg \
-o outputs/主题名/out.png --scale 4 --denoise --sharpen 1.5
# 只调色不放大（偏暗/发灰的图）
python skills/shared/scripts/img_enhance.py enhance -i img.jpg \
-o outputs/主题名/out.jpg --scale 1 --auto
调参
- 还是糊：本工具无法造细节，改用 ai-image-gen 图生图超分。
- 锐化过头有噪点/白边：降低
--sharpen（默认 auto=1.0）。 - 颜色过饱和：
--saturation 1.0关闭增色，或调低。 - 噪点被放大：加
--denoise（放大前先去噪）。
规则
- 先设定预期：这是"改善"不是"重绘"，糊得厉害的图别承诺变高清。
- 有噪点务必
--denoise（放大前执行，避免噪点被放大）。 - 放大统一用 Lanczos 高质量重采样；倍数别盲目开 4x（文件暴涨且无新细节）。
- 产物统一进
outputs/主题名/。
参考来源
Lanczos 重采样 + UnsharpMask 锐化 + OpenCV fastNlMeans 去噪 + 自动对比度，是无 GPU 的传统 画质提升组合。真正的超分辨率（Real-ESRGAN 等）需 GPU/模型，此处以 ai-image-gen 图生图替代。
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.
- 10d ago First seen · 64 lines · 187 tokens per session scan A b46c6e6a5e7c
image-enhance is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed today), licensed Apache-2.0. It adds 187 tokens to every session and 945 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 2026-08-30.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…