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-illustration-strategy)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/content-illustration-strategy"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-illustration-strategy/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-illustration-strategy"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-illustration-strategy.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 | $0.00135 | $0.02564 |
| Opus 5 | $0.00068 | $0.01282 |
| Sonnet 5 | $0.00027 | $0.00513 |
| Haiku 4.5 | $0.00014 | $0.00256 |
Grade A, and why
content-illustration-strategy 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文章配图决策
这不是“随便找几张图填空”的 skill。 这是把文章可信度、信息密度、点击感，映射成正确图片来源的决策流程。
核心原则
配图不是固定配额，而是为“证明这篇文章在说什么”服务。
判断顺序永远是：
- 这篇文章靠什么建立可信度？
- 什么图片最能证明这件事？
- 哪种图片会稀释主轴？
快速工作流
输入：文章标题 + 核心观点 + 平台 + 可用素材
↓
Step 1: 判断文章的证据类型
↓
Step 2: 选择图片来源（截图 / 官网图 / 生成图 / 流程图）
↓
Step 3: 决定图片数量与插入位置
↓
Step 4: 判断是否需要 Telegram 真实对话证据图
↓
Step 5: 输出可执行配图方案
Step 1：先判断文章的证据类型
把文章先归到下面四类之一（必要时可混合，但要分主次）：
A. 真实工作流证据型
适用：
- OpenClaw 技巧
- Agent 协作
- 自动化工作流
- “我真的这样跑起来了”的实战文
这类文章的可信度来自：真实过程与真实结果。
优先图片：
- Telegram 对话截图
- 后台执行截图
- 工作流节点截图
- 发布前后对比截图
B. 产品实测 / 工具横评型
适用：
- AI 工具评测
- 软件横评
- 功能对比
- 使用体验总结
这类文章的可信度来自：产品本身 + 实测判断。
优先图片：
- 工具界面截图
- 官网/产品页图
- 功能对比图
- 自制评分/定位图
C. 观点分析 / 趋势判断型
适用：
- 行业趋势
- 方法论
- 批判文
- 认知升级文
这类文章的可信度来自：逻辑结构与观点表达。
优先图片：
- 自生成概念插图
- 流程图 / 对比图 / 结构图
- 关键结论卡片图
D. 混合证据型
适用：
- 一边讲工具，一边讲真实使用方式
- 一边讲平台技巧，一边展示自己实操案例
这类文章必须先定主轴：
- 主轴是工具 → 工具图为主，证据截图为辅
- 主轴是工作流 → 证据截图为主，工具图为辅
Step 2：选择图片来源
按证据类型选来源，不要倒过来。
图片来源优先级
| 证据需求 | 首选图片来源 | 说明 |
|---|---|---|
| 证明“真的发生过” | Telegram / 后台真实截图 | 最强真实性 |
| 证明“真的测过产品” | 工具界面图 / 官网图 / 产品截图 | 最强相关性 |
| 解释“概念或结构” | 自生成示意图 / 流程图 | 最强表达力 |
| 增强阅读节奏 | 结论卡 / 对比卡 / 小结图 | 最强结构感 |
反向约束
不要这样配：
- 工具测评文，全塞聊天截图
- 工作流实战文，只放抽象插画
- 方法论文，硬塞无关官网图
- 为了“看起来丰富”塞没有证据价值的图
Step 3：什么时候该用 Telegram 真实对话截图
只有当截图本身能增强“证据链”时才用。
应该用 Telegram 图的情况
- 文章在讲你和 agent 的真实协作过程
- 文章在讲 OpenClaw / 自动化 / 工作流技巧
- 文章需要证明“这不是纸上谈兵，而是实际在跑”
- 对话本身就是案例的一部分
不必强行用 Telegram 图的情况
- 纯产品横评
- 纯行业分析
- 纯概念解释
- 聊天截图不能提供额外信息，只会打断阅读
Step 4：Telegram 截图脱敏规则
默认不要原样暴露私人信息。
三档处理
- A 完整保留：仅适合用户明确要求
- B 半脱敏：保留关键对话，弱化头像/时间/名称
- C 强脱敏（默认推荐）：只保留对话气泡内容，不保留账号身份特征
强脱敏原则
- 保留：能证明案例成立的关键对话内容
- 弱化/移除：头像、昵称、账号、精确时间、无关上下文
- 截图只截有价值的区域，不做聊天记录全屏搬运
Step 5：图片数量与插入位置
不要先定“这篇必须 5 张图”。 先看文章结构。
默认规则
- 1000-2000 字：2-4 张图
- 2000-3500 字：3-6 张图
- 3500+ 字：按章节分布，但仍然宁少勿滥
插图位置
优先插在：
- 开头 20% —— 建立主题感
- 第一段结论后 —— 给读者证据
- 章节切换处 —— 打断疲劳
- 复杂判断后 —— 给可视化支撑
避免：
- 连续堆两三张相似图
- 图文无关
- 文章尾部才突然塞图
Step 6：输出格式
What ships with it
3 files 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.
- 6d ago First seen · 256 lines · 135 tokens per session scan A ec53c5eb5963
content-illustration-strategy is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 2,564 once invoked, about $0.0007 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.