Cover Anchor System
ponyodong2026/ponyo-cover-anchor-system
Designs Xiaohongshu and WeChat article covers around information density and a visual anchor, then writes a complete image prompt, color plan and critique.
Agent skill
WeChat Article Cover and Image Generator
Chinese-language skill that generates a WeChat article's cover image and in-body illustrations by calling an external image API, matching art style to the article's content.
SKILL.md written in Chinese; this summary is our English description.
Install WeChat Article Cover and Image Generator
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-images --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aws-wechat-article-images .claude/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .claude/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-imagesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-images --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/aws-wechat-article-images .agents/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .agents/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-images --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/aws-wechat-article-images .cursor/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .cursor/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aiworkskills/wechat-article-skills.git --path skills/aws-wechat-article-images--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-images --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/aws-wechat-article-images .gemini/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .gemini/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-imagesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/aws-wechat-article-images .github/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .github/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-images --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiworkskills/wechat-article-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/aws-wechat-article-images .opencode/skills/aws-wechat-article-images && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "aws-wechat-article-images" agent skill from https://github.com/aiworkskills/wechat-article-skills/tree/main/skills/aws-wechat-article-images into .opencode/skills/aws-wechat-article-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aws-wechat-article-images", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
aws-wechat-article-images- GitHub stars
- 672
- Token cost
- ~1.8k tokens
- SKILL.md length
- 392 words
- Files
- 55 (incl. scripts, references)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Chinese-language skill that generates a WeChat article's cover image and in-body illustrations by calling an external image API, matching art style to the article's content.
- Works in 5 steps: 封面必须脚本生成，产出为文章目录下的 cover.png（或 .jpg /… → 正文优先用业务配图库，缺图才生成。判断顺序见 branches.md 第一节。 → 删图有上限：每篇最多删 1 个图位并写明理由。要删 2 个以上、或把本篇… → …
- Generating a cover image for a WeChat article
- SKILL.md covers 能力披露（Capabilities）, 路由, 五条硬规则 ⛔ and 工作流, plus 1 more section
- Needs IMAGE_MODEL_API_KEY
What it does
Written in Chinese, the skill is one of nine slugs in a WeChat article production suite and only illustrates a long-form article; it routes full write-through-publish requests to a main skill and multi-image sticker posts to a separate skill. It calls a script against an external image API, sending each prompt as a JSON body, reading the key from a config file and only downloading URLs resolving to public addresses, rejecting internal ones against request forgery. It reads only the article's own files plus its references, writes only into its image folder, and its shell access is limited to two scripts; it recommends a separately billed key over an account-level one.
Five hard rules govern image handling: the cover image must always come from the script, never a file copied directly from an asset library, except when the user explicitly uploads and designates one cover; body text should draw from an existing image library first and generate only when nothing fits; deleting an image slot is capped at one per article with a stated reason, and deleting more must first be flagged to the user as a mismatch between content and density; the image folder separates final images, prompts, source citations and raw intermediate crops into their own subfolders; and a content item is illustrated by either a layout component or a generated image, never both.
When your agent uses it
- Generating a cover image for a WeChat article
- Adding generated illustrations to a long article's body text
- Deciding whether to reuse an existing image or generate a new one
- Replacing an illustration a reader didn't like and reposting the draft
Example prompts
- “Generate a cover image for this article.”
- “The third paragraph needs an image. Check the library first, then generate one if needed.”
- “Readers didn't like this illustration. Swap it for the image I uploaded and resend the draft.”
Requirements
- An external image-generation API endpoint and its API key in a config file
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 封面必须脚本生成，产出为文章目录下的 cover.png（或 .jpg / .jpeg / .webp）。禁止把素材库文件直接复制成 cover.*。例外：用户明确上传封面并声明「只用这一张」，须在结果中注明「用户指定封面」。
- 正文优先用业务配图库，缺图才生成。判断顺序见 branches.md 第一节。
- 删图有上限：每篇最多删 1 个图位并写明理由。要删 2 个以上、或把本篇 image_density 改小（效果相同），都要先把「本篇内容与密度对不上」这个判断告诉用户。
- imgs/ 目录分工：根目录只放正文引用的最终图；prompts/ 放生图 prompt，sources/ 放实证图的来源说明，raw/ 放截图与裁切的中间产物。
- 先分工再选形态：排版组件和信息位配图干同一件事，同一份内容只给其中一个。但只有标准 markdown 够得到的组件才算数——判给够不到的组件等于图和组件两头落空。实测归属见 image-method 第一步半：只有金句卡片归组件，对比两栏与清单要点一律出图。
What it can do on your machine
Read from SKILL.md and the folder at commit ca036f7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
x.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
IMAGE_MODEL_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
WeChat Article Cover and Image Generator loads about 1.8k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 392 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from aiworkskills/wechat-article-skills at commit ca036f7, republished under its Apache-2.0 licence (© aiworkskills). 392 words, ~1,835 tokens.
Download SKILL.mdSave it as
.claude/skills/aws-wechat-article-images/SKILL.md (or your agent's skills folder). This skill also uses 54 other files; get the full folder from GitHub.- name
- aws-wechat-article-images
- description
- 公众号封面｜公众号配图｜公众号插图｜AI 生图 — 公众号 AI 封面与配图生成，按文章标题与内容自动匹配画风，一稿多方案，多风格预设可复用。面向公众号编辑、自媒体、品牌设计。触发词：「封面」「配图」「插图」「生成图片」「给文章加图」「做个封面」「文章插图」「配个图」。不写正文只发一组图请走 aws-wechat-sticker；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
- homepage
- https://aiworkskills.cn
- url
- https://github.com/aiworkskills/wechat-article-skills
配图
公众号封面 & 配图 AI 生成 —— 按文章内容自动匹配画风，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。
- 凭证：读
aws.env的IMAGE_MODEL_API_KEY，以Authorization: Bearer发往image_model.base_url - 内容外发：每张图的 prompt 作为 JSON POST body 发送，来自本篇
imgs/prompts/*.md - SSRF 防御：API 返回图片 URL 时仅允许下载 http/https 公网地址，内网 / 环回 / 保留地址一律拒绝
- 文件读：
.aws-article/config.yaml、本篇article.yaml/article.md/imgs/prompts/*.md、本 skill 的references/*、.aws-article/products/{产品名}/images/* - 文件写：本篇
imgs/**、可选img_analysis.md - shell：仅
{python} {baseDir}/scripts/image_create.py、user_image_prepare.py
建议用专用 key（最低权限、独立计费），不要用 account 级 master key。
单独安装本 skill 时，跨 skill 的引用会 file not found，但生图脚本仍可用。完整 9 slug 见 源码仓库。
路由
完整长文从选题到发布 → main；图片消息 / 九宫格等多图推送 → sticker。本 skill 专注长文配图。
用户说「这篇配图不满意，换成我上传的新图重发草稿箱」→ 不走下面的工作流，改走 branches.md 第三节「发布后换图重发」。
配置检查按 首次引导 执行；image_model 在 config.yaml、IMAGE_MODEL_API_KEY 在 aws.env。端点差异与比例传法见 branches.md 第六节。
| 脚本 | 用途 |
|---|---|
scripts/image_create.py | 调专用生图 API（generate / batch / check / test） |
scripts/user_image_prepare.py | 用户供图模式：建 imgs/ 并生成 img_analysis.md 模板 |
五条硬规则 ⛔
- 封面必须脚本生成，产出为文章目录下的
cover.png（或.jpg/.jpeg/.webp）。禁止把素材库文件直接复制成cover.*。例外：用户明确上传封面并声明「只用这一张」，须在结果中注明「用户指定封面」。 - 正文优先用业务配图库，缺图才生成。判断顺序见 branches.md 第一节。
- 删图有上限：每篇最多删 1 个图位并写明理由。要删 2 个以上、或把本篇
image_density改小（效果相同），都要先把「本篇内容与密度对不上」这个判断告诉用户。 imgs/目录分工：根目录只放正文引用的最终图；prompts/放生图 prompt，sources/放实证图的来源说明，raw/放截图与裁切的中间产物。- 先分工再选形态：排版组件和信息位配图干同一件事，同一份内容只给其中一个。但只有标准 markdown 够得到的组件才算数——判给够不到的组件等于图和组件两头落空。实测归属见 image-method 第一步半：只有金句卡片归组件，对比两栏与清单要点一律出图。
工作流
配图进度：
- [ ] 第1步：读配置与文章
- [ ] 第2步：解析配图标记
- [ ] 第3步：确定风格
- [ ] 第4步：写 prompt
- [ ] 第5步：展示方案并等待确认 ⛔
- [ ] 第6步：生成图片
- [ ] 第7步：插入文章 + 收尾自检 ⛔第1步：读配置与文章
- 全局
.aws-article/config.yaml：cover_aspect、image_density、caption_style、tone等以它为准（字段见 articlescreening-schema.md）。 - 本篇
article.yaml：default_cover_image_style（单元素，本篇已选的封面形态）、default_article_image_style（多元素候选池，正文形态逐个图位选，不收敛成单选——收敛等于整篇配图用同一种形态）。 - 读
article.md。 image_source: user时改走 branches.md 第二节「用户供图模式」。
第2步：解析配图标记
提取所有 。写手只用四个类型，它们定的是图位不是形态：
| 类型 | 含义 | 本 skill 做什么 |
|---|---|---|
封面 | 文章封面 | 走 cover-method.md |
实证 | 官方原帖截图、界面实拍 | 真实素材，不生成；来源说明写进 imgs/sources/ |
信息图 | 信息位，解释内容 | 按内容选形态，内容必须取自文章 |
氛围 | 节奏位，只为换口气 | 概念隐喻 / 场景还原，不放具体信息 |
存量草稿里的旧类型名（流程图 / 对比）按 信息图 处理。
第3步：确定风格
先跑一次，把候选池里认不出的形态名挑出来（不调 API）：
{python} {baseDir}/scripts/image_create.py styles退出码 1 说明 config.yaml 的候选池里有不存在的名字——先改名再往下走。实测网站导出的 config 写过「对比说明 / 板书白板 / 氛围烘托」，三个都没有对应模板（真名是 对比两栏 / 概念隐喻 / 场景还原，而「板书白板」是媒介不是形态）。挑中这种名字只能让模型自由发挥，整套形态方法论静默失效。
封面与正文分别定，各走各的预设目录。两者的加载优先级相同：用户当次指定 > 本篇 article.yaml > custom_* 候选池（为空即全选）。
- 封面：内置 12 个形态于
references/cover-styles/（<名>.example.md），用户自定义放.aws-article/presets/cover-styles/，同名覆盖。每个模板含用于 / 主体 / 影调 / 文案 / 版式五个字段，「文案」不可缺省——缺了产出的是背景图不是封面。挑选判据只有一条：主体在 345px 缩略图里能否一眼认出。 - 正文：内置 8 个形态于
references/image-styles/。判据只有一条：删掉这张图读者会看不懂（信息位）还是读不下去（节奏位）？都不影响就删掉该图位。
Show full SKILL.md (161 more words)Show less
第4步：写 prompt
- 封面：按 cover-method.md 走完前六步，产出一个 prompt 文件——frontmatter 含
aspect（取自cover_aspect，值须加引号，未加引号的16:9会被 YAML 解析成整数），正文是 150–300 字散文，标题文案（4–7 字，字高占画面 25–35%）连同位置、字体感、颜色一起写在里面。不要关键词清单，不要写「不要 X」，不要照抄范例场景。 - 正文：按 image-method.md 六步逐个图位处理。信息位的内容必须从文章里取——让模型自由发挥会生成无关鸡汤并自带 emoji。
- 图中文字必须为中文，且在 prompt 里直接写出要显示的那几个字，不要写 "labels in Chinese"。
- 通用规则（媒介优先、构图要求、禁用绘图库重画）见 prompt-construction.md。
第5步：展示方案并等待确认 ⛔
- 一条龙且用户对风格无特殊要求：按默认预设自动执行不单独确认，但结果里要列出每张图的类型、风格与 prompt 路径。
- 单独触发本 skill、用户提了风格要求、或方案涉及用业务配图库替换图位：先展示方案（位置 / 类型 / 风格 / prompt 要点 / 来源），等用户确认再进第 6 步。
第6步：生成图片
在仓库根执行，stdout 与 stderr 一起落盘：
{python} {baseDir}/scripts/image_create.py batch drafts/YYYYMMDD-slug/imgs/prompts/ \
-o drafts/YYYYMMDD-slug/imgs/ > drafts/YYYYMMDD-slug/image-generation.log 2>&1单张用 generate <prompt.md> -o <out.png>；重跑批量时加 --skip-existing，已生成合格的不重复付费。图片规格见 specs.md。
先检查返回比例与文字完整性。 脚本默认 fit: preserve，保留 API 返回的完整图；比例不符会告警，不再自动裁掉文字。目标比例仍须发布前验收。只有确认边缘可舍弃时，才在 frontmatter 写 fit: crop 或使用 --fit crop 恢复居中裁切。generate、batch 都支持，命令行优先。出现文字缺失先判断原图已有缺字还是裁切造成；保留图已完整时不要盲目重生成。详见 比例异常处理 和 可复查的使用示例。
⛔ 出字问题先改 prompt，不要换工具。 不许因为「API 出来的字有裁切」就改用 matplotlib / PIL 重画——那样媒介和形态整套方法论被绕开，钱还付两遍。理由见 prompt-construction.md。
封面回看（必做）：打开图片对四条——主体位置与标题区、元素 ≤3、缩略图可读、与文章相关。不过关回到出问题的那一步改 prompt 再生成，不要不改 prompt 盲目重跑。看不了图时退而用 image_create.py check cover.png（只有尺寸与近单色两项）。
脚本非零退出或 stderr 有 API / 网络错误 → 走 branches.md 第四节，必须分类并摘要报错，不得只说「生图失败」。
第7步：插入文章 + 收尾自检
替换 placeholder 为实际图片路径。封面不进正文：![封面：…] 仅用于微信封面上传，替换时跳过或删除该行，封面单独存为文章根目录的 cover.{ext}。
仅当 article.html 里确实存在 href="placeholder" 或 placeholder 被渲染成链接时，才去修 HTML；不要默认每次都执行「修复 HTML」。
⛔ 收尾自检（六条，缺一不可）
- 每张正文图各有一个
imgs/prompts/*.md，文件名主干与图片一致。先落 prompt 再生成，不许反过来——否则出了问题没法复现，想只重跑一张也做不到，只能整批重来（按张计费）。Agent 自己生图时同样要落盘。 - 实证图的说明放
imgs/sources/，不许放prompts/。batch是整目录 glob 的，混在里面会照着「来源：https://x.com/…」生成一张**伪造的原帖截图**覆盖掉真的那张——而文章正拿它当证据。脚本已有防线（首行「来源：」或 frontmattertype: source会跳过并告警），但目录放对才是根本。 article.yaml的image_medium非空，且等于第四步实际用的媒介。它是下一篇「平手时避开上一篇」的唯一依据。- 正文图数量与
image_density对得上。删过图位要写明删了哪个、为什么。 - 生成日志已落盘且看过有没有腰斩告警。封面为什么难看，正是靠日志里「已按 2.35:1 居中裁切: 1024x1024 → 1024x436」定位到的——屏幕上滚过去就没了。
imgs/根目录只剩正文引用的图，中间产物已归入raw/；本篇所有信息位配图共用同一个媒介，而每个图位的形态各自按内容选。
重跑生图后必须复核引用——返回格式会变（这次 PNG 下次 JPEG），引用会断且不报错。细则见 branches.md 第五节。
分支与异常
不在主路径上的情况全部写在 references/branches.md：正文配图来源优先级、用户供图模式、发布后换图重发、调用失败四分类、故障降级终点、重跑复核、端点差异与比例传法。
© aiworkskills, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 54 other files (scripts, references) in skills/aws-wechat-article-images of aiworkskills/wechat-article-skills.
- SKILL.md
- references/branches.md
- references/cover-examples/README.md
- references/cover-examples/书脊阶梯.md
- references/cover-examples/剖面.md
- references/cover-examples/双生.md
- references/cover-examples/双轨.md
- references/cover-examples/层积.md
- references/cover-examples/山峰折线.md
- references/cover-examples/引力汇聚.md
- references/cover-examples/折叠纸境.md
- references/cover-examples/星图.md
- references/cover-examples/根系电路.md
- references/cover-examples/沙漏城市.md
- references/cover-examples/涟漪.md
- references/cover-examples/潮线.md
- references/cover-examples/灯下.md
- references/cover-examples/破土.md
- references/cover-examples/空椅.md
- … and 36 more
Open the folder on GitHubat commit ca036f7
Compare with similar skills
WeChat Article Cover and Image Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| WeChat Article Cover and Image Generator this skillaiworkskills/wechat-article-skills | 672 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Cover Anchor Systemponyodong2026/ponyo-cover-anchor-system | 190 | — | ~1.1k | Automated safety check: Pass | None | |
| WeChat Article Cover MakerSpaceZephyr/creator-buddy | 1.6k | — | ~1.5k | Automated safety check: Pass | None | |
| Fantasy Qiqiguaiguaidacnay816y62-hub/fantasy-qiqiguaiguai-skill | 120 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Chart Image Generator for WeChat ArticlesSpaceZephyr/creator-buddy | 1.6k | — | ~1.7k | Automated safety check: Pass | None | |
| Thumbnail Creatormohitagw15856/pm-claude-skills | 1.4k | — | ~6.3k | Automated safety check: Pass | MIT |
Similar skills
WeChat Article Cover Maker
SpaceZephyr/creator-buddy
Creates a 2.35:1 header cover for a WeChat official account article with image generation, keeping the headline inside the area that survives sharing crops.
Fantasy Qiqiguaiguai
dacnay816y62-hub/fantasy-qiqiguaiguai-skill
将朋友圈碎片图片、截图、物件、人物与零散想法，整理成具有幽默、黑色幽默、玩梗和编辑感的社交内容；自动选择 T1 人像主体、T2 杂物拼贴或 T3 全图压字视觉模板，并输出可直接生成的视觉简报与成图提示词。Use when the user wants to turn life fragments, photos, screenshots, objects, portraits, pets…
Chart Image Generator for WeChat Articles
SpaceZephyr/creator-buddy
Draws chart images such as flowcharts, architecture diagrams, ER diagrams and SWOT boards for WeChat official account articles, in one of six visual styles.
Thumbnail Creator
mohitagw15856/pm-claude-skills
Generate article or newsletter thumbnail candidates using the Gemini API from inside Claude Code.
Guizang Social Cards
op7418/guizang-social-card-skill
Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.
More from aiworkskills/wechat-article-skills
All 9 skills in this repoWeChat Article Assets Library
aiworkskills/wechat-article-skills
Manages a local business-material library and .aws preset packs for a WeChat official-account article workflow, including product images and theme presets.
WeChat Article Formatter
aiworkskills/wechat-article-skills
Converts a Markdown WeChat article draft into themed, paste-ready HTML, with no network calls or credentials and a choice of built-in visual templates.
WeChat Official Account Pipeline
aiworkskills/wechat-article-skills
Orchestrates the full WeChat official account workflow from topic to draft, chaining sub-skills for writing, review, layout, images and publishing.
WeChat Official Account Publisher
aiworkskills/wechat-article-skills
Publishes a finished article and its images directly to a WeChat official account through its official API, as a draft or a live broadcast.
WeChat Article Rewriting
aiworkskills/wechat-article-skills
Rewrites, continues, or polishes an existing WeChat article draft using a configurable language model, sending the full draft text to that endpoint.
WeChat Article Compliance Reviewer
aiworkskills/wechat-article-skills
Local, offline pre-publish review for a WeChat official account article: sensitive words, typos and platform compliance, producing an actionable fix list.
Related
Works with
Categories
Questions about WeChat Article Cover and Image Generator
What does WeChat Article Cover and Image Generator do?
Chinese-language skill that generates a WeChat article's cover image and in-body illustrations by calling an external image API, matching art style to the article's content. Written in Chinese, the skill is one of nine slugs in a WeChat article production suite and only illustrates a long-form article; it routes full write-through-publish requests to a main skill and multi-image sticker posts to a separate skill. It calls a script against an external image API, sending each prompt as a JSON body, reading the key from a config file and only downloading URLs resolving to public addresses, rejecting internal ones against request forgery.
When should I use WeChat Article Cover and Image Generator?
WeChat Article Cover and Image Generator fits situations like: generating a cover image for a WeChat article; adding generated illustrations to a long article's body text; deciding whether to reuse an existing image or generate a new one; replacing an illustration a reader didn't like and reposting the draft.
How do I install WeChat Article Cover and Image Generator in Claude Code?
Run `npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a claude-code`. Or copy the skill folder (skills/aws-wechat-article-images in aiworkskills/wechat-article-skills) into .claude/skills/aws-wechat-article-images in your project. Claude Code loads it when a task matches its description.
How do I install WeChat Article Cover and Image Generator in Codex?
Run `npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a codex`. Or copy the skill folder (skills/aws-wechat-article-images in aiworkskills/wechat-article-skills) into .agents/skills/aws-wechat-article-images in your project. Codex loads it when a task matches its description.
Can I use WeChat Article Cover and Image Generator in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aws-wechat-article-images, .gemini/skills/aws-wechat-article-images, .github/skills/aws-wechat-article-images and .opencode/skills/aws-wechat-article-images in your project.
What does WeChat Article Cover and Image Generator need to run?
Going by SKILL.md and its folder, WeChat Article Cover and Image Generator needs credentials named IMAGE_MODEL_API_KEY. Our summary lists: An external image-generation API endpoint and its API key in a config file.
Does WeChat Article Cover and Image Generator access the network?
SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.
Is WeChat Article Cover and Image Generator safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does WeChat Article Cover and Image Generator use?
WeChat Article Cover and Image Generator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does WeChat Article Cover and Image Generator use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 21k tokens, read only when the agent opens those files.
What are the alternatives to WeChat Article Cover and Image Generator?
Skills that share tags, products or a category with WeChat Article Cover and Image Generator: Cover Anchor System (ponyodong2026/ponyo-cover-anchor-system, 190 stars), WeChat Article Cover Maker (SpaceZephyr/creator-buddy, 1.6k stars), Fantasy Qiqiguaiguai (dacnay816y62-hub/fantasy-qiqiguaiguai-skill, 120 stars) and Chart Image Generator for WeChat Articles (SpaceZephyr/creator-buddy, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains WeChat Article Cover and Image Generator?
aiworkskills (a GitHub user) maintains it in aiworkskills/wechat-article-skills, which has 672 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 23, 2026.
Source: aiworkskills/wechat-article-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.