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-writing-system --skill ai-image-generatorgit clone --depth 1 https://github.com/TashanGKD/tashan-writing-systemWrote 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-writing-system/ai-image-generator)<a href="https://agentmods.dev/skills/tashangkd/tashan-writing-system/ai-image-generator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/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-writing-system/ai-image-generator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/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 | $0.03234 |
| Opus 5 | $0.00043 | $0.01617 |
| Sonnet 5 | $0.00017 | $0.00647 |
| Haiku 4.5 | $0.00009 | $0.00323 |
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 11d 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) This is a copy
86% identical to ai-image-generator — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 | YOUR_DASHSCOPE_API_KEY |
| 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 | YOUR_DMXAPI_KEY |
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 = 'YOUR_DASHSCOPE_API_KEY'
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。
全景图优先原则(先于绘图流程执行)
核心规则:先建立完整的对象-关系模型,再决定画什么图
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.
- 11d ago First seen · 253 lines · 86 tokens per session scan A 7fd28da2f8e8
ai-image-generator is a skill published in the GitHub repository TashanGKD/tashan-writing-system (2 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 3,234 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to ai-image-generator, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.