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 TashanGKD/tashan-cursor-skills --skill ai-image-generatorgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-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/tashangkd/tashan-cursor-skills/ai-image-generator)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/ai-image-generator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/ai-image-generator/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/tashangkd/tashan-cursor-skills/ai-image-generator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/ai-image-generator.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 | $0.00086 | $0.03295 |
| Opus 5 | $0.00043 | $0.01648 |
| Sonnet 5 | $0.00017 | $0.00659 |
| Haiku 4.5 | $0.00009 | $0.00330 |
Grade A, and why
ai-image-generator scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.post(ENDPOINT, headers=headers, json=payload, timeout=120) Copies of this mod
1 near-identical copy found in the catalogue:
- ai-image-generator — 86% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI配图能力 Skill
这是一个能力层 Skill，被其他 Skill 调用，不直接面向用户任务。 任何需要生成图片的 Skill 都应该引用本 Skill，而不是自行嵌入 API 细节。
模型与 API
| 优先级 | 模型 | 适用场景 | API Key |
|---|---|---|---|
| 首选 | qwen-image-2.0-pro |
含中文文字的信息图、结构图 | sk-68b70d6863b94c299ecd27e9d49b41ba |
| 次选 | wan2.6-t2i |
纯视觉风格图（无需复杂中文文字排版） | 同上（dashscope） |
| 备用 | gpt-image-1（DMXAPI） |
英文为主的极简图 | sk-wzI4JscScaJ1pxVKRQ4qxmJcpH1OIgsqshlP55Tq6NtZ3H5p |
选择原则：信息图/结构图/有中文标注 → 用 qwen-image-2.0-pro；纯视觉风格图 → 用 wan2.6-t2i。
wan2.6-t2i API 调用（endpoint 不同）：
url = 'https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis'
body = {'model': 'wan2.6-t2i', 'input': {'prompt': 'PROMPT'}, 'parameters': {'size': '1024*1024', 'n': 1}}
⚠️ 已知问题：DMXAPI 上的 DALL-E 3 有较高概率网络超时（实测超时案例：2026-03-20 向日葵调研任务）。遇到超时时直接切换 qwen-image-2.0-pro，不要反复重试 DALL-E 3。
qwen-image-2.0-pro API 调用
import requests, base64
API_KEY = 'sk-68b70d6863b94c299ecd27e9d49b41ba'
ENDPOINT = 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation'
headers = {'Content-Type': 'application/json', 'Authorization': f'Bearer {API_KEY}'}
payload = {
"model": "qwen-image-2.0-pro",
"input": {"messages": [{"role": "user", "content": [{"text": "你的提示词"}]}]},
"parameters": {
"n": 1,
"watermark": False,
"prompt_extend": True,
"size": "1024*1024" # 标准图；小图同尺寸，HTML 中用 max-width: 65% 控制
}
}
resp = requests.post(ENDPOINT, headers=headers, json=payload, timeout=120)
img_url = resp.json()['output']['choices'][0]['message']['content'][0]['image']
# 下载并保存（URL 24 小时有效，立即保存）
ir = requests.get(img_url, timeout=60)
with open('output.png', 'wb') as f:
f.write(ir.content)
⚠️ 限速处理：遇到 429 时等待 30 秒后重试，最多重试 3 次。
风格库
风格库文件：_内部总控/产品定义/图片风格库.md（10种风格，当前文章使用 S03）
S03 标准提示词前缀（适合大多数中文信息图）：
简洁专业的信息图，适合微信文章，白色背景。[内容描述]
深蓝色#1a2f5e和橙色#e8622c为主色，圆角矩形，清晰中文标注，整体简洁商务风格。
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.
- 12d ago First seen · 253 lines · 86 tokens per session scan A 5c7888128e1f
ai-image-generator is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 3,295 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cognitive-creative-synthesis
A brainstorming workflow that combines concepts from different areas of a knowledge system to suggest unusual approaches to a problem. DMN refers to the brain network associated with free association, while CEN refers to the network used to maintain goals and constraints.
template-helpers
Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…
android-new-project
Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…
android-upgrade
Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…