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 aiworkskills/wechat-article-skills --skill aws-wechat-article-imagesgit clone --depth 1 https://github.com/aiworkskills/wechat-article-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/aiworkskills/wechat-article-skills/aws-wechat-article-images)<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-images"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-images/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/aiworkskills/wechat-article-skills/aws-wechat-article-images"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-images.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 | $0.00144 | $0.07687 |
| Opus 5 | $0.00072 | $0.03844 |
| Sonnet 5 | $0.00029 | $0.01537 |
| Haiku 4.5 | $0.00014 | $0.00769 |
Grade A, and why
aws-wechat-article-images 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 today.
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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
配图
公众号封面 & 配图 AI 生成 —— 按文章内容自动匹配画风，一稿多方案，风格体系可复用。
套件说明 · 本 skill 属
aws-wechat-article-*一条龙套件（共 9 个 slug，入口aws-wechat-article-main）。跨 skill 的相对引用依赖同一skills/目录，建议一并clawhub install全套。源码：https://github.com/aiworkskills/wechat-article-skills
能力披露（Capabilities）
本 skill 调 image_create.py 调外部图像 API 生成封面与正文配图。会把图片提示词（可能含文章主题片段）发给用户配置的图像生成端点。 具体行为：
- 凭证读取：
aws.env的IMAGE_MODEL_API_KEY - 凭证外发：该 key 以
Authorization: Bearer头发送到image_model.base_url指定端点（常见为 DALL-E、gpt-image 兼容/v1/images/generations，或多模态模型/v1/chat/completions，具体由用户配置） - 内容外发：每张图片的 prompt（文本）作为 JSON POST body 发送；prompt 内容来自本篇
imgs/prompts/*.md（可能包含文章标题、章节摘要） - 下图 SSRF 防御：若 API 响应返回图片 URL（而非 base64），脚本仅允许下载 http/https 公网地址；内网 / 环回 / 链路本地 / 保留地址全部拒绝（防止恶意或被劫持的模型端点把脚本当作 SSRF 跳板）
- 文件读：仓库内
.aws-article/config.yaml、本篇article.yaml、article.md、imgs/prompts/*.md、references/cover-method.md、references/image-method.md、references/cover-examples/*.md、.aws-article/products/{产品名}/images/*（业务配图库，本篇涉及用户业务时优先复用） - 文件写：本篇
imgs/*.{png,webp}、可选img_analysis.md - shell：仅
{python} {baseDir}/scripts/image_create.py、user_image_prepare.py（{python}= 本机 Python 3 解释器，见 main SKILL 第 0 步：Windows 用py -3 -X utf8，macOS / Linux 用python3）
建议：用专用 key（最低权限、独立计费），避免使用 account 级 master key。
配套 skill（informational）
本 skill 是 aws-wechat-article-* 一条龙公众号套件的配图环节（入口 aws-wechat-article-main）。工作流中的若干步骤会读取同级 ../aws-wechat-article-main/references/*.md 等共享文档（首次引导、env/config 示例、articlescreening schema 等）。
- 套件完整装齐到同一
skills/根目录时，跨 skill 引用都能读到。 - 单独安装本 skill 时，跨 skill 引用的步骤会在读取阶段遇到
file not found；本 skill 内的生图脚本仍可用。
完整 9 slug 清单见 源码仓库。
路由
完整长文从选题到发布 → aws-wechat-article-main；图片消息/九宫格等多图推送 → aws-wechat-sticker。
读取文章中的配图标记，按内容形态生成图片：封面 12 个形态、正文配图 8 个形态，均按内容判断而非账号审美。专注于长文配图，贴图请用 sticker。
What ships with it
50 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.
- references/cover-examples/README.md 530 B
- references/cover-examples/书脊阶梯.md 445 B
- references/cover-examples/剖面.md 505 B
- references/cover-examples/双生.md 481 B
- references/cover-examples/双轨.md 499 B
- references/cover-examples/层积.md 504 B
- references/cover-examples/山峰折线.md 451 B
- references/cover-examples/引力汇聚.md 568 B
- references/cover-examples/折叠纸境.md 523 B
- references/cover-examples/星图.md 472 B
- references/cover-examples/根系电路.md 517 B
- references/cover-examples/沙漏城市.md 481 B
- references/cover-examples/涟漪.md 521 B
- references/cover-examples/潮线.md 500 B
- references/cover-examples/灯下.md 491 B
- references/cover-examples/破土.md 574 B
- references/cover-examples/空椅.md 482 B
- references/cover-examples/逆光剪影.md 554 B
- references/cover-examples/钥匙迷宫.md 424 B
- references/cover-examples/长廊尽头.md 546 B
- references/cover-examples/静物台.md 522 B
- references/cover-method.md 10 KB
- references/cover-styles/README.md 2.4 KB
- references/cover-styles/产品实拍.example.md 1012 B
- references/cover-styles/人物出镜.example.md 951 B
- references/cover-styles/信息表.example.md 984 B
- references/cover-styles/剧照氛围.example.md 888 B
- references/cover-styles/图上压字.example.md 946 B
- references/cover-styles/场景实拍.example.md 945 B
- references/cover-styles/对比式.example.md 1.0 KB
- references/cover-styles/截图标注.example.md 1.1 KB
- references/cover-styles/扁平插画.example.md 965 B
- references/cover-styles/数字冲击.example.md 1.1 KB
- references/cover-styles/纯色大字.example.md 1.0 KB
- references/cover-styles/菜品特写.example.md 1.0 KB
- references/image-method.md 12 KB
- references/image-styles/prompt-construction.md 5.1 KB
- references/image-styles/README.md 3.3 KB
- references/image-styles/场景还原.example.md 1.6 KB
- references/image-styles/对比两栏.example.md 1.1 KB
- references/image-styles/数据图表.example.md 1.2 KB
- references/image-styles/概念隐喻.example.md 1.9 KB
- references/image-styles/流程步骤.example.md 1.2 KB
- references/image-styles/清单要点.example.md 1.3 KB
- references/image-styles/结构分层.example.md 1.1 KB
- references/image-styles/金句卡片.example.md 1.4 KB
- references/specs.md 1.2 KB
- scripts/image_create.py 64 KB runs code
- scripts/user_image_prepare.py 3.2 KB runs code
- skill.json 500 B
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.
- today Changed · +8 lines eb4963658d54
- 5d ago Changed · +9 lines dccebe95ded1
- 6d ago Changed · +3 lines 357662f382ca
- 12d ago First seen · 251 lines · 144 tokens per session scan A 04032e580dc6
aws-wechat-article-images is a skill published in the GitHub repository aiworkskills/wechat-article-skills (589 stars, last pushed yesterday), licensed Apache-2.0. It adds 144 tokens to every session and 7,687 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 2026-08-30.
Other skills, from other repositories
article-visuals
A tool for planning and producing article visuals such as cover illustrations, charts, and relationship diagrams. It selects different formats for data, processes, concepts, and real-world objects.
ls-xhs-note
Use when the user wants a complete Xiaohongshu note workflow that can start from a topic and turn it into a source article, a native note, and image assets, or continue from an existing note draft. Supports framework selection, model-native note drafting, and image generation.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
short-drama
A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.