Agent skill

WeChat Article Assets Library

by aiworkskills in 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.

Apache-2.0Auto-check passedWriting & Content

SKILL.md written in Chinese; this summary is our English description.

Install WeChat Article Assets Library

skills CLI
$ npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-assets -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiworkskills/wechat-article-skills aws-wechat-article-assets --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-assets .claude/skills/aws-wechat-article-assets && rm -rf skills-src

Use ~/.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/

Facts

Skill name
aws-wechat-article-assets
GitHub stars
672
Token cost
~1.5k tokens
SKILL.md length
295 words
Files
5 (incl. scripts, references)
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Manages a local business-material library and .aws preset packs for a WeChat official-account article workflow, including product images and theme presets.

  • Works in 5 steps: 确认产品名:ls… → 确认文件名:默认 项目介绍.md;可改成贴用户行业的 产品介绍.md /… → 建目录:mkdir -p… → …
  • Saving a business introduction to a product folder for later articles
  • SKILL.md covers 能力披露(Capabilities), 三件事, 设计意图(必读)⛔ and 一、业务介绍 .md 入库, plus 5 more sections
  • Runs Python scripts from its folder; reaches aiworkskills.cn

What it does

This Chinese-language skill is one part of a WeChat official-account article suite and also works on its own. It keeps the user's business material in a .aws-article/products/ folder organized by product name, with introduction Markdown files at the product root and images in an images subfolder, each paired with a same-name description file. The agent is told to check this library before writing about the user's own business and to prompt you to save newly produced business introductions there.

Two bundled Python scripts do the file work: product_image_ingest.py adds images to a product, and import_presets_aws.py imports .aws ZIP preset packs from a local file or an aiworkskills.cn URL and merges theme, color and font settings into .aws-article/presets/. Downloads are limited to HTTPS on that domain unless a flag relaxes it, archive paths are checked against ZIP slip, and an existing config.yaml is not overwritten, with a difference report printed instead. Importing a pack also writes keys from it into aws.env at the repository root, backing up the old file first.

When your agent uses it

  • Saving a business introduction to a product folder for later articles
  • Adding product images with descriptions to the material library
  • Importing a .aws preset pack from a local file or aiworkskills.cn link
  • Looking up existing product material before writing about your own business

Example prompts

  • “Save this product introduction to the library under the product name Lantern Tea.”
  • “Add ./photos/teapot.jpg to the Lantern Tea product images with a short description.”
  • “导入预设 ./downloads/brand-theme.aws 到素材库”

Requirements

  • Python, to run the bundled scripts
  • Network access to aiworkskills.cn, only for downloading .aws packs

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 确认产品名:ls .aws-article/products/,已有目录提示复用;新产品向用户拿名字。
  2. 确认文件名:默认 项目介绍.md;可改成贴用户行业的 产品介绍.md / 服务介绍.md / 品牌介绍.md。
  3. 建目录:mkdir -p .aws-article/products/{产品名}/images/(即便暂时为空也把骨架建齐)。
  4. 写入:Write 工具落到 .aws-article/products/{产品名}/{文件名}.md。
  5. 反馈:「已存到 <完整路径>,下次涉及 [产品名] 业务的文章会自动用上」。

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 2 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • aiworkskills.cn

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

WeChat Article Assets Library loads about 1.5k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 295 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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). 295 words, ~1,465 tokens.

Download SKILL.mdSave it as .claude/skills/aws-wechat-article-assets/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
aws-wechat-article-assets
description
公众号素材|业务资料库|预设包|.aws 预设包|主题包|品牌包|aiworkskills.cn — 用户业务资料库与预设包管理:业务资料按产品名组织在 `.aws-article/products/{产品名}/`(介绍 .md 直挂产品根 + 配图归 `images/` 子目录含同名说明 .md),AI 与用户对话产出业务介绍内容时引导用户保存;图片入库走 `product_image_ingest.py --product <产品名> --stem <中文名>`。导入 .aws ZIP 预设包(本地文件或 `https://aiworkskills.cn/**/*.aws` URL)合并主题/配色/字体配置到 `.aws-article/presets/`;`config.yaml` 仅本地不存在时从包内复制,已存在则 stdout 输出差异 JSON 不覆盖。面向内容运营、品牌团队、设计支持岗。触发词:「素材库入库」「stock images」「上传图到素材库」「.aws」「预设包」「导入预设」「主题包」「aiworkskills.cn 链接」「.aws 下载地址」。
homepage
https://aiworkskills.cn
url
https://github.com/aiworkskills/wechat-article-skills

用户业务资料库与预设(Assets)

业务资料按产品名分目录 — .aws-article/products/{产品名}/ 直挂业务介绍 .md、images/ 存配图(含同名说明 .md)。写涉及用户自身业务的文章/配图前必须先查这里;新生成的业务介绍内容应引导用户保存到这里。预设包合并到 .aws-article/presets/。

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 管理本地业务资料库与预设包,可选从 aiworkskills.cn 域下载 .aws 预设包(ZIP)。

  • 凭证:无(但导入 .aws 会把包内密钥写进仓库根 aws.env,见下)
  • 网络:可选 https://*.aiworkskills.cn/**/*.aws 下载预设包。白名单强制:仅 HTTPS + aiworkskills.cn 及其子域,非白名单直接报错退出。--allow-any-host 可放宽,调试用
  • 文件读:用户指定的本地图片或 .aws 文件;引导入库前会 ls .aws-article/products/ 看已有产品名
  • 文件写:
    • .aws-article/products/{产品名}/*.md(业务介绍,AI 用 Write 工具直接落库)
    • .aws-article/products/{产品名}/images/*(图片 + 同名 .md,由脚本写)
    • .aws-article/presets/<白名单子目录>/*、.aws-article/downloads/*.aws、.aws-article/tmp/*
    • 仓库根 aws.env:导入 .aws 时按映射表增量写入密钥(覆盖现有键前自动备份 aws.env.bak.{ts},stderr 只打印键名不打印值)
  • 归档安全:解压 .aws(ZIP)到 .aws-article/tmp/。已内置 ZIP slip 防御——逐项校验成员路径,拒绝绝对路径、.. 段、或解析后指向解压目录外的路径,任一违反立即退出且不写入任何文件
  • shell:仅 {python} {baseDir}/scripts/ 下的 product_image_ingest.py、import_presets_aws.py

除 aws.env 外,所有写入都限制在仓库根的 .aws-article/ 内。

单独安装可用:两个脚本都不依赖兄弟 skill,只要有 .aws-article/ 目录就能工作。

三件事

能力说明
业务介绍 .md 入库对话中产出的业务介绍 → products/{产品名}/<文件名>.md(Write 工具直接落库,无脚本)
业务图入库用户业务图 → products/{产品名}/images/ + 同名说明 .md(脚本,--product 必填)
预设包 .awsZIP(本地文件或 https://aiworkskills.cn/**/*.aws)→ 合并 presets/ 白名单子目录

设计意图(必读)⛔

.aws-article/products/{产品名}/ 是用户自家业务(卖货 / 卖软件 / 卖服务 / 自媒体 IP)的资料库——既是 AI 写业务相关内容时的底稿来源,也是 AI 与用户协作产出新介绍时的保存目的地。

.aws-article/products/{产品名}/
├─ 项目介绍.md                # 业务介绍 .md 直挂产品根(命名按用户行业:服务介绍.md / 品牌介绍.md…)
├─ (其他业务文档.md)
└─ images/
   ├─ 配置首页.png
   └─ 配置首页.md             # 图片说明 .md(同名)

双向触发:

方向触发条件行为
读当前任务涉及用户自家业务(对外介绍 / 教程 / 案例 / 自家安利 / 业务配图)先 ls .aws-article/products/,识别相关产品,读它根下的 *.md、查 images/ 同名 .md,把已有素材当底稿与配图候选
写AI 刚生成或改写的内容语义属于用户业务介绍走下面「业务介绍 .md 入库」;用户说「保存为产品介绍」等也走这条

什么时候不要触发见 branches.md「一」。

一、业务介绍 .md 入库

无需脚本,AI 用 Write 工具直接落库。两种触发:

  • AI 主动识别:刚生成/改写的内容明确属于用户自家业务介绍(产品 / 服务 / 品牌 / 项目 / 团队 / 业务范围)时提示用户:

    「这段是 [产品名] 的业务介绍,要不要保存到产品资料库?我可以存到 .aws-article/products/{产品名}/{文件名}.md,下次写涉及业务的文章时会自动用上。」

  • 用户主动指令:「保存为产品介绍 / 业务介绍 / 服务介绍 / 入库到产品 / 存到产品资料库」等。

保存流程:

  1. 确认产品名:ls .aws-article/products/,已有目录提示复用;新产品向用户拿名字。
  2. 确认文件名:默认 项目介绍.md;可改成贴用户行业的 产品介绍.md / 服务介绍.md / 品牌介绍.md。
  3. 建目录:mkdir -p .aws-article/products/{产品名}/images/(即便暂时为空也把骨架建齐)。
  4. 写入:Write 工具落到 .aws-article/products/{产品名}/{文件名}.md。
  5. 反馈:「已存到 <完整路径>,下次涉及 [产品名] 业务的文章会自动用上」。

二、业务图入库

脚本不会读图——读图定文件名、写画面描述是 Agent 的活,入库命令要带 --content:

bash
{python} {baseDir}/scripts/product_image_ingest.py <源图片路径> \
  --product "公众号AI运营助手" --stem "配置首页" \
  --content "客观中文描述,一两句即可"

--product / --stem 必填,产品目录与 images/ 不存在时自动创建。产出 配置首页.png + 配置首页.md。

不传 --content 会写占位句(预期行为,不是故障)、.md 的固定格式,见 branches.md「二」。

三、预设包导入(.aws)

扩展名 .aws,实质是 ZIP。包根应含与仓库一致的预设文件夹(可以多出别的文件,脚本只处理白名单):

closing-blocks、cover-styles、formatting、image-styles、sticker-styles、structures、title-styles

另可有根级 config.yaml、writing-spec.md。不在白名单的目录会被跳过并打日志——components/ 与 review-rules.yaml 就不由 .aws 管理,原因见 branches.md「三」。

工作流:

  1. 准备来源:本地 .aws 文件,或符合白名单的 HTTPS URL。
  2. 先 --dry-run 看将写入哪些路径。
  3. 在仓库根执行:
bash
# 本地路径
{python} {baseDir}/scripts/import_presets_aws.py path/to/bundle.aws
{python} {baseDir}/scripts/import_presets_aws.py path/to/bundle.aws --dry-run

# URL(仅 aiworkskills.cn 及子域)
{python} {baseDir}/scripts/import_presets_aws.py https://aiworkskills.cn/bundles/brand-a.aws

三条要先知道的语义 ⛔:

  • 预设目录是替换式:包内有该子目录 → 先清空本地同名目录再写;包内没有 → 本地保持不动。
  • config.yaml 不覆盖:本地已有时只把差异以 JSON 打到 stdout,须问过用户再手改。本地没有才复制。
  • 密钥会进 aws.env:包内 wechat_appid / wechat_appsecret / writing_model.api_key / image_model.api_key 按映射增量写入,覆盖前备份 aws.env.bak.{ts}。

完整规则(映射表、写入策略、包根优先级、URL 白名单、tmp 语义)见 branches.md「三~五」。

脚本

脚本参数
product_image_ingest.pysource、--product(必填)、--stem(必填)、--content、--repo
import_presets_aws.pybundle(路径或白名单 URL)、--dry-run、--repo、--allow-any-host(调试)

分支与细则

不该入库的情况、业务图入库两步、.aws 合并语义、密钥映射、URL 白名单 → references/branches.md。

过程文件

场景产出
业务介绍 .md 入库.aws-article/products/{产品名}/{文件名}.md(同时 mkdir images/)
业务图入库.aws-article/products/{产品名}/images/*.{png,…} + 同名 *.md
.aws 导入.aws-article/presets/** 更新;config.yaml 首次复制或 stdout 差异 JSON;密钥增量写入 aws.env(覆盖前备份);解压缓存在 .aws-article/tmp/
.aws URL 导入下载缓存 .aws-article/downloads/*.aws;其余同本地导入

© 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 4 other files (scripts, references) in skills/aws-wechat-article-assets of aiworkskills/wechat-article-skills.

  • SKILL.md
  • references/branches.md
  • scripts/import_presets_aws.py
  • scripts/product_image_ingest.py
  • skill.json

Open the folder on GitHubat commit ca036f7

Compare with similar skills

WeChat Article Assets Library 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.

WeChat Article Assets Library compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
WeChat Article Assets Library this skillaiworkskills/wechat-article-skills672—~1.5kAutomated safety check: PassApache-2.0
Ex-Partner Persona CreatortherealXiaomanChu/ex-skill6.5k—~2.7kAutomated safety check: NotesMIT
Release Announcement PosterNanmiCoder/cc-haha15k—~516Automated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
Knowledge Searchdataelement/bisheng12k—~1.1kAutomated safety check: PassApache-2.0
Self Skill Creatornotdog1998/yourself-skill3.4k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • Ex-Partner Persona Creator

    therealXiaomanChu/ex-skill

    Builds a local conversational persona and relationship memory of a former partner from chat exports, photos and social posts, with corrections and later additions.

    6.5k GitHub stars~2.7k tokensUpdated 6 mo ago
    Writing & ContentAuto-check: notes
  • Release Announcement Poster

    NanmiCoder/cc-haha

    Turns the latest release notes into a short WeChat group message and a tall PNG poster, with contributor GitHub IDs checked and real avatars embedded.

    15k GitHub stars~516 tokensUpdated today
    Writing & ContentAuto-check passed
  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated 2 days ago
    EducationAuto-check passed
  • Knowledge Search

    dataelement/bisheng

    Search the user's knowledge bases and knowledge spaces (企业知识库检索).

    12k GitHub stars~1.1k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Self Skill Creator

    notdog1998/yourself-skill

    Builds a personal self skill from your chat logs, diaries and photos, then lets you extend or correct it, working in English or Chinese.

    3.4k GitHub stars~2.5k tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check: notes
  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    86k GitHub stars~1.5k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed

More from aiworkskills/wechat-article-skills

All 9 skills in this repo
  • 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.

    672 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed
  • WeChat Article Cover and Image Generator

    aiworkskills/wechat-article-skills

    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.

    672 GitHub stars~1.8k tokensUpdated 17 days ago
    Auto-check passed
  • 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.

    672 GitHub stars~2k tokensUpdated 17 days ago
    Auto-check passed
  • 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.

    672 GitHub stars~1.5k tokensUpdated 17 days ago
    Auto-check passed
  • 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.

    672 GitHub stars~2.2k tokensUpdated 17 days ago
    Auto-check passed
  • 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.

    672 GitHub stars~1.5k tokensUpdated 17 days ago
    Auto-check passed

Works with

Questions about WeChat Article Assets Library

What does WeChat Article Assets Library do?

Manages a local business-material library and .aws preset packs for a WeChat official-account article workflow, including product images and theme presets. This Chinese-language skill is one part of a WeChat official-account article suite and also works on its own.aws-article/products/ folder organized by product name, with introduction Markdown files at the product root and images in an images subfolder, each paired with a same-name description file.

When should I use WeChat Article Assets Library?

WeChat Article Assets Library fits situations like: saving a business introduction to a product folder for later articles; adding product images with descriptions to the material library; importing a .aws preset pack from a local file or aiworkskills.cn link; looking up existing product material before writing about your own business.

How do I install WeChat Article Assets Library in Claude Code?

Run `npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-assets -a claude-code`. Or copy the skill folder (skills/aws-wechat-article-assets in aiworkskills/wechat-article-skills) into .claude/skills/aws-wechat-article-assets in your project. Claude Code loads it when a task matches its description.

How do I install WeChat Article Assets Library in Codex?

Run `npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-assets -a codex`. Or copy the skill folder (skills/aws-wechat-article-assets in aiworkskills/wechat-article-skills) into .agents/skills/aws-wechat-article-assets in your project. Codex loads it when a task matches its description.

Can I use WeChat Article Assets Library 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-assets -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-assets, .gemini/skills/aws-wechat-article-assets, .github/skills/aws-wechat-article-assets and .opencode/skills/aws-wechat-article-assets in your project.

What does WeChat Article Assets Library need to run?

Going by SKILL.md and its folder, WeChat Article Assets Library needs Python for the scripts in its folder. Our summary lists: Python, to run the bundled scripts; Network access to aiworkskills.cn, only for downloading .aws packs.

Does WeChat Article Assets Library access the network?

SKILL.md names 1 domain. In commands or code: aiworkskills.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is WeChat Article Assets Library 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 Assets Library use?

WeChat Article Assets Library 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 Assets Library use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 1.3k tokens, read only when the agent opens those files.

What are the alternatives to WeChat Article Assets Library?

Skills that share tags, products or a category with WeChat Article Assets Library: Ex-Partner Persona Creator (therealXiaomanChu/ex-skill, 6.5k stars), Release Announcement Poster (NanmiCoder/cc-haha, 15k stars), DeepTutor CLI (HKUDS/DeepTutor, 41k stars) and Knowledge Search (dataelement/bisheng, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains WeChat Article Assets Library?

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.