Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aAAaqwq/AGI-Super-Team/plugin install agi-super-teamWrote 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/aaaaqwq/agi-super-team/content-cover-gen)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/content-cover-gen"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-cover-gen/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/aaaaqwq/agi-super-team/content-cover-gen"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-cover-gen.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 | $0.00127 | $0.03520 |
| Opus 5 | $0.00063 | $0.01760 |
| Sonnet 5 | $0.00025 | $0.00704 |
| Haiku 4.5 | $0.00013 | $0.00352 |
Grade A, and why
content-cover-gen 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容驱动封面生成
把文章核心观点变成一张3秒能看懂的封面图。
核心原则
❌ 封面不是背景图。套哪篇都能用的封面 = 没有价值。 ✅ 封面是视觉摘要。3秒内让读者知道这篇文章/视频在讲什么。
快速工作流
输入：文章标题 + 核心观点（一句话）+ 目标平台
↓
Step 1: 匹配视觉隐喻（从隐喻库选择或自创）
↓
Step 2: 构建提示词（5要素公式）
↓
Step 3: 调用出图（自动优先级回退：vectronode → qingyun → relay）
↓
Step 4: 输出封面文件路径 + 提示词（可追溯）
Step 1: 匹配视觉隐喻
隐喻速查表
| 文章角度 | 视觉隐喻 | 色彩情绪 | 示例场景 |
|---|---|---|---|
| 警告/封禁 | 盾牌、门锁、红叉、警告标志、墙 | 红黑 | 盾牌挡住机器人 |
| 对比/测评 | 天平、排行榜、VS分屏、赛车 | 蓝白 | 6个角色站在排行榜上 |
| 批判/反共识 | 破裂面具、气泡破裂、碎镜、空盒子 | 红金 | 礼物盒打开是空的 |
| 教程/攻略 | 地图、钥匙、阶梯、工具箱、指南针 | 蓝绿 | 打开的地图上有路径 |
| 个人故事 | 人影剪影+场景、时间线、日记本 | 暖色调 | 人站在岔路口 |
| 趋势/预测 | 望远镜、火箭、道路分叉、上升曲线 | 紫蓝 | 火箭升空 |
| 创业/商业 | 拼图、积木搭建、蓝图、种子发芽 | 金黑 | 积木搭成城堡 |
| 效率/工具 | 齿轮、涡轮、加速器、杠杆 | 青橙 | 杠杆撬动巨石 |
| 深度分析 | 放大镜、解剖图、层叠透视 | 深蓝白 | 放大镜下的芯片 |
| 热点/争议 | 火焰、火山、辩论台、麦克风 | 红橙 | 两个火焰对撞 |
| 真实经历 | 场景复现(工位/校园/咖啡厅) | 自然色 | 深夜工位+屏幕光芒 |
| 避坑/教训 | 地雷、陷阱、警告牌、路障 | 黄黑 | 前方有地雷标志 |
匹配逻辑
- 提炼文章核心观点(一句话,≤15字)
- 判断文章角度(从上表匹配,或自创隐喻)
- 如果没有现成隐喻,问自己:"这个观点像什么画面?"
- 选择对应色彩情绪
Step 2: 构建提示词
5要素公式
[主体场景] + [视觉隐喻/故事] + [色彩情绪] + [风格] + [格式]
| 要素 | 说明 | 要求 |
|---|---|---|
| 主体场景 | 封面主要视觉元素 | 必须具体,不能用"抽象图形" |
| 视觉隐喻 | 把观点变成画面 | 必须有故事性,让人一看就懂 |
| 色彩情绪 | 跟文章情绪匹配 | 最多2-3种颜色,高对比度 |
| 风格 | 插画/照片/3D等 | 推荐:editorial illustration / flat design |
| 格式 | 比例+约束 | 按平台规格,加 "no text overlay" |
❌ 错误示例
# 纯风格,跟内容无关
"Dark background with blue accent color, abstract geometric shapes, minimal design"
# 太抽象
"A beautiful image about AI, modern style, 3:4"
✅ 正确示例
文章:小红书封杀AI代发
Xiaohongshu app icon with a red shield and warning symbol overlaid on it, a robot arm being pushed away by a hand, dark red and black color scheme, social media concept art, clean modern illustration, no text overlay, 3:4 vertical format
文章:90% AI Agent是噱头
A cracked open gift box revealing a cheap toy robot inside with a big red X mark over it, next to it a plain cardboard box glowing gold from inside, metaphor for fake vs real value, bold editorial illustration, red and gold color scheme, 3:4 vertical format, no text
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.
- 6d ago First seen · 289 lines · 127 tokens per session scan A 219f40aa2b09
content-cover-gen is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 3,520 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
loom-artifacts
Receive files from the CodexLoom Thread composer and publish generated images or files back to the Thread as managed artifacts. Use when a user message contains loomattachments; an attached document, data file, image, or archive must be read; or the Agent has produced a file that the user should preview or download.…
exploring-zero-resource-designs
Use when exploring zero resource designs is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
framing-creative-challenge
Use when framing creative challenge is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
mutating-idea-genomes
Use when mutating idea genomes is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
scoring-contextual-creativity
Use when scoring contextual creativity is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
using-denial-ladders
Use when using denial ladders is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.