Junta Leiloeiros
sickn33/agentic-awesome-skills
Coleta e consulta dados de leiloeiros oficiais de todas as 27 Juntas Comerciais do Brasil.
Agent skill
by Moore-developers in Moore-developers/moore-wechat-article-downloader
Downloads and manages WeChat official account articles from URLs, an account's history or subscriptions, adding engagement metrics and top comments when a valid session exists.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloader --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .claude/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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.
$ npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloader --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .agents/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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 Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloader --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .cursor/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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.
$ npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloader --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .gemini/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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 Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloaderInstalls 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 Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .github/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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 Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Moore-developers/moore-wechat-article-downloader moore-wechat-article-downloader --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "moore-wechat-article-downloader" agent skill from https://github.com/Moore-developers/moore-wechat-article-downloader/tree/main into .opencode/skills/moore-wechat-article-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moore-wechat-article-downloader", 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.
moore-wechat-article-downloaderDownloads and manages WeChat official account articles from URLs, an account's history or subscriptions, adding engagement metrics and top comments when a valid session exists.
Written in Chinese, this skill archives articles from WeChat official accounts and prefers to run locally. A wizard script picks the scenario: direct download of full article URLs or a txt, csv or json list; history for a named account through an Exporter login, which is the default, or a proxy fallback; WeChat favorites for comments, reads and likes; and scheduled sync of several subscribed accounts.
The wizard returns gates such as need_login, need_proxy_confirm and need_account_choice, which the agent handles by guiding a QR-code scan, confirming the system proxy or listing candidates in chat. Exporter mode fetches only account searches, history lists and article text, so engagement data comes from a separate batch flow that works only while the user's short WeChat session is valid. After a run the agent checks index.csv, the Markdown, the image folder and page status. It does not bypass logins or paywalls, and does not turn into rewriting, summarizing or a cloud service.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit dea919b. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
mp.weixin.qq.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
WeChat Article Downloader loads about 3.4k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 577 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.
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.
The full file from Moore-developers/moore-wechat-article-downloader at commit dea919b, republished under its MIT licence (© Moore-developers). 577 words, ~3,354 tokens.
.claude/skills/moore-wechat-article-downloader/SKILL.md (or your agent's skills folder). This skill also uses 39 other files; get the full folder from GitHub.| 用户意图 | 场景 | 入口 |
|---|---|---|
| 提供了完整文章 URL | 场景 1:直接下载 | wechat_wizard.py run "下载:<url>" |
| 给公众号名 / 样例 URL,想要历史文章 | 场景 2A:Exporter(默认) | wechat_wizard.py run "历史文章:<名称或URL>" |
| 明确说"不登录"或"用代理" | 场景 2B:代理(备选) | wechat_wizard.py run "代理历史:<url>" |
| 想抓评论/阅读/点赞/页面风格 | 场景 2C:微信收藏 | wechat_downloader.py proxy-enhancer-session-start --yes |
| 管理多个公众号 / 定时同步 | 场景 3:订阅同步 | 见场景 3 |
统一入口优先。wizard 返回以下 gate 时按表处理,不要立刻降级为底层命令:
| Gate | 处理 |
|---|---|
need_login | 引导扫码 → login-status 轮询 → login-complete 恢复任务 |
need_proxy_confirm | 向用户确认启用系统代理 → 确认后继续 |
need_account_choice | 聊天中列出候选公众号 → resume --choice "<序号>" |
need_article_choice | 聊天中列出文章标题+日期 → resume --choice "<选择>" |
只有 wizard 返回 blocked 或 failed_recoverable 并明确给出底层命令时,才使用底层命令。
可以做:下载公开的 mp.weixin.qq.com 文章、抓取历史文章列表、Exporter 扫码登录和账号管理、定时增量同步。
不要做:绕过登录/付费墙/私密内容;打印 auth-key/cookie/token;把历史列表抓取和 URL 下载混为一谈;扩展成内容改写、总结、SaaS。
success_count 只表示流程没有抛错。结束前必须检查 index.csv、Markdown、图片目录和源页面状态。exporter-login-qr-status;只有状态为 confirmed / ready_to_complete=true 才运行 exporter-login-qr-complete。触发:用户提供一篇或多篇完整文章 URL,或 .txt/.csv/.json 文件。
python3 {baseDir}/scripts/wechat_wizard.py run "下载:<url 或文件路径>"重跑会跳过已成功的 URL。失败项重试:
python3 {baseDir}/scripts/wechat_wizard.py retry "<task-id>"下载完成后报告:成功数量、失败数量、失败 URL(如有)、output_dir、index.csv。
触发:用户提供公众号名、关键词或样例文章 URL,想要历史文章列表。
优势:API 稳定、无需代理、支持按名称搜索、一次登录 4 天有效、SQLite 持久化可复用。
边界:Exporter 模式只做公众号搜索、历史文章同步和文章下载;不获取评论、阅读数、点赞数、收藏数、转发数等互动数据。互动数据只在代理快照模式验证通过后再提供。
带评论/互动数据的硬规则:
exporter-sync -> exporter-download,只用于不带评论/互动数据的正文下载。exporter-sync -> engagement batch download。exporter-download。wechat-collection-sync-engagement / wizard 的 engagement 批量任务处理。python3 {baseDir}/scripts/wechat_wizard.py run "获取公众号「<名称>」的历史文章"wizard 自动处理:检查登录 → 搜索公众号 → 同步文章 → 列出结果。
文章列表展示(强制要求):
抓取完成后必须在聊天中直接罗列,格式:
- **YYYY-MM-DD**:文章标题不要只给 CSV/JSON 路径。不要只给编号,必须同时展示标题和日期。
让用户按标题关键词、日期、最新 N 篇或编号范围选择后再下载。
触发:用户明确说"不登录"或"用代理",或 Exporter 模式失败。
python3 {baseDir}/scripts/wechat_wizard.py run "代理历史:<sample-article-url>"硬性规则:
https://mp.weixin.qq.com/mp/profile_ext?action=home&__biz=<biz>&scene=124#wechat_redirectchannels.weixin.qq.com/web/pages/mp_profile(视频号壳页,不触发 getmsg 接口)history-capture-finish 恢复系统代理127.0.0.1:23344;切换公众号时不要停止代理服务,直接运行新的 history-capture-prepare 复用进程告诉用户:把旧版入口发到微信文件传输助手,用桌面客户端内置浏览器打开,看到历史列表后向下滚动。
触发:用户要评论、阅读数、点赞数、收藏数、在看数、完整页面快照、公众号排版风格。
此模式保存用户当前浏览的文章,也可在短时凭证有效期内恢复同公众号已授权任务的互动同步。历史列表仍默认走 Exporter;旧代理历史列表只作为备用。只同步精选评论,不承诺全量评论或完整回复树。
批量互动任务必须使用已经同步出的文章列表和 URL 创建,不要先用普通 Exporter 下载正文。用户说“下载某公众号最新 N 篇文章的评论和互动数据”时,正确链路是:
exporter-sync -> engagement batch download主流程不再使用 proxy-snapshot-prepare --yes。
每次新会话从 23032-24045 选择一个空闲随机端口。启动前先固定当前 upstream,再启动增强代理并切换系统 HTTP/HTTPS 代理。端口、PID、upstream 和恢复状态写入活动会话;同一会话安全重载时必须复用这些值。
启动成功后会终止旧的微信 WeChatAppEx WebView 进程。微信主进程和登录状态保持不变;用户下次打开文章时,微信会创建使用当前代理的新 WebView。代理增强代码安全重载后也执行同样的 WebView 重置,避免旧进程继续使用缓存页面。
系统/微信 -> 127.0.0.1:<会话端口> -> 会话启动时确定的上游代理或直连 -> 外网启动命令:
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-session-start --upstream-proxy none --yes如果修改了代理增强代码或需要重载,只能使用安全重载。该命令自动读取并复用活动端口与 upstream:
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-restart --upstream-proxy none --yes不要在系统代理指向活动端口时直接 kill、proxy-enhancer-stop 或 stop && start;这会让系统代理指向死端口。安全重载会临时恢复上游或直连,使用原端口重启,再切回活动端口。
启动后常见链路:
系统/微信 -> 127.0.0.1:<会话端口> -> 启动时确定的上游代理 -> 外网以下命令自动读取活动端口,不要手工猜端口:
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-route-help
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-check-ingress --minutes 10
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-logs --hours 24 --limit 80
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-video-links --hours 24 --limit 100增强代理常驻期间会额外捕获公开的 channels.weixin.qq.com 视频号页面地址,写入 proxy-snapshots/video-links.jsonl。只提供页面链接,不下载视频;禁止保存或展示 finder.video.qq.com 临时媒体地址以及 token、ticket、exportkey、session、auth 等签名凭证。
视频号链接捕获规则:
proxy-enhancer-check-ingress;确认微信流量到达,再让用户在微信里打开视频号卡片或页面。channels.weixin.qq.com 页面 URL;finder.video.qq.com 通常是短时签名媒体地址,不作为结果。proxy-enhancer-session-finish --yes,避免系统继续指向已停止的本地端口。视频下载入口:
python3 {baseDir}/scripts/wechat_exporter.py exporter-download --account-id <id> --latest <N> --include-video --video-quality highest。输出在账号目录 videos/ 下,文件名前缀为 [视频]。channels.weixin.qq.com/web/pages/... 页面注入“下载视频”按钮;按钮只在用户当前有权限播放、页面 JS 暴露 objectDesc.media[] 后可下载。needs_capture,不得报告视频下载成功。处理方式是保持/启动 proxy-enhancer-session-start --yes,重新打开目标视频页,等按钮显示“下载视频”后再重跑。urlToken、decodeKey、签名媒体 URL、Cookie 和请求头只在代理进程内短时保存和下载使用;禁止写入 SQLite、Markdown、JSONL、调试日志或聊天输出。结果只报告页面 URL、descriptor id、文件路径、大小、是否解密。decodeKey 生成 128 KiB key stream 并 XOR 文件头,失败时标记 failed / decrypt_failed。调试日志位于 ~/.moore/wechat-article-downloader/proxy-snapshots/debug.jsonl,只记录脱敏事件:请求路径、响应状态、是否识别为文章页、是否注入脚本、页面脚本是否执行、按钮是否放置成功。日志只保留 24 小时;清理动作每 12 小时最多执行一次。
成功识别并注入的文章 HTML 响应必须写入 Cache-Control: no-store,并移除 ETag / Last-Modified,防止微信 WebView 在下一次会话继续复用未更新的注入代码。已禁用的系统代理状态视为没有 endpoint;不要保存或展示其残留的 server/port。
不要在用户点击保存后自动恢复系统代理。只有用户明确要求恢复时才运行:
python3 {baseDir}/scripts/wechat_downloader.py proxy-enhancer-session-finish --yes该命令先恢复系统代理,再停止并回收本次会话的随机端口进程。
用户之后正常打开公众号文章。页面加载完成后应自动出现注入按钮:顶部元信息行一个,评论区标题旁一个,点击任意一个都会保存当前文章现场。
收藏到本地用户点击后读取最近快照:
python3 {baseDir}/scripts/wechat_downloader.py snapshot-latest
python3 {baseDir}/scripts/wechat_downloader.py snapshot-list --limit 10如果用户说“已保存”“处理刚才保存的快照”“整理今天保存的快照”,默认不要只处理 latest。先看快照收件箱,再把所有未处理快照归档到文章库:
python3 {baseDir}/scripts/wechat_downloader.py snapshot-inbox --limit 50
python3 {baseDir}/scripts/wechat_downloader.py snapshot-attach --all-unprocessed归档规则:
~/Downloads/wechat-articles/<公众号名>/。## 页面数据 区块;同一篇文章重复归档时替换旧区块,不重复追加。latest.json 和 metrics_history.jsonl。把最近快照提取成后续处理用的结构化文件:
python3 {baseDir}/scripts/wechat_downloader.py snapshot-extract latest也可以指定快照:
python3 {baseDir}/scripts/wechat_downloader.py snapshot-extract <snapshot-id> --output-dir <dir>输出位于:
~/.moore/wechat-article-downloader/proxy-snapshots/<snapshot-id>/主要文件:
snapshot.json:DOM 快照和基础字段dom.html:脱敏后的完整页面 DOMjs_content.html:正文 DOMcomments_dom.html:页面已渲染评论 DOMengagement_dom.html:互动区域 DOMmetrics.json:阅读、点赞、在看、评论、收藏、分享的可观察结果network.jsonl:脱敏后的网络响应摘要style_profile.json / style_summary.md:页面风格摘要report.md:本次快照报告snapshot-extract 默认输出到 <snapshot-dir>/extracted/:
article.md:正文 Markdowncomments.json:已加载评论文本和原始评论 DOM,complete=falsecomments_structured.json:结构化评论,包含昵称、地区/时间、点赞、回复数、内容metrics.json:可观察互动数据style_profile.json:页面风格特征image_urls.json:正文图片 URL 列表engagement.html:互动区域 DOMreport.md:提取报告规则:不承诺一定拿到所有互动字段;页面未暴露时必须标记 missing。不要保存或打印 cookie、auth-key、token、pass_ticket、key 等敏感值。
文章落盘规则:标题和 Markdown 文件名必须带 [图文] 或 [贴图] 前缀;微信 item_show_type=8 判定为贴图,其他文章判定为图文。贴图 Markdown 先集中输出全部图片,再输出文字内容。
item_show_type=8 是贴图;不要根据图片数量、正文长度或是否存在 content_noencode 猜类型。普通图文也可能包含 content_noencode。#js_content;为空或缺失时安全解码 content_noencode,禁止执行页面 JavaScript。<img> 时,优先读取 share_imageinfo[].cdn_url 中公开的 mmbiz.qpic.cn 原图地址。排除 watermark_info、cover_url、头像、封面和同图不同尺寸派生项,再按规范化 URL 或内容哈希去重。该兜底只用于贴图,避免普通图文误收装饰资源。untitled、空标题或删除提示时,回退到 Exporter 已同步的数据库标题。frontmatter、index.csv 和文件名必须一致。content_type=贴图、item_show_type=8、image_count>0、所有本地图片存在,以及第一个图片引用位于正文内容之前。还要抽查图片确为文章内容图,不能只看数量;若 image_count=0,必须继续排查元数据图片清单,不能直接结束。[图文] 前缀、正文非空、Markdown 图片引用对应本地文件。图片下载失败要在 error 中保留原因。下载后建议按以下顺序验收:
命令结果 -> index.csv 类型/数量 -> Markdown 标题与排序 -> 图片文件存在 -> 删除/风控页面检查 -> 聊天中报告真实结果触发:用户需要长期跟踪多个公众号,希望每天自动同步并下载新文章。
已有能力:
# 搜索并添加公众号
python3 {baseDir}/scripts/wechat_exporter.py exporter-search "关键词"
python3 {baseDir}/scripts/wechat_exporter.py exporter-add --fakeid "<fakeid>" --nickname "<name>"
# 查看已订阅的公众号列表
python3 {baseDir}/scripts/wechat_exporter.py exporter-accounts
# 同步单个账号文章
python3 {baseDir}/scripts/wechat_exporter.py exporter-sync --account-id "<id>" --limit 200
# 下载指定账号最新 N 篇
python3 {baseDir}/scripts/wechat_exporter.py exporter-download --account-id "<id>" --latest 20# 同步所有已订阅账号(默认每个账号最新 50 篇)
python3 {baseDir}/scripts/wechat_exporter.py exporter-sync-all
python3 {baseDir}/scripts/wechat_exporter.py exporter-sync-all --per-account-limit 100
# 下载所有尚未下载的新文章
python3 {baseDir}/scripts/wechat_exporter.py exporter-download-new
# 每日一键运行:sync-all + download-new(适合 cron)
python3 {baseDir}/scripts/wechat_exporter.py exporter-daily-run设置 cron 定时任务时,用 AI 帮用户生成 launchd plist 或 crontab 条目,指定绝对路径调用 exporter-daily-run。
QR 流程(首选):
python3 {baseDir}/scripts/wechat_exporter.py exporter-login-qr-start --open
python3 {baseDir}/scripts/wechat_exporter.py exporter-login-qr-status "<login-id>"
python3 {baseDir}/scripts/wechat_exporter.py exporter-login-qr-complete "<login-id>"降级:手动 auth-key(QR 不可用时):
python3 {baseDir}/scripts/wechat_exporter.py exporter-login-start --open
python3 {baseDir}/scripts/wechat_exporter.py exporter-config --auth-key "<auth-key>"规则:扫码时必须选公众号/服务号,不要选小程序;auth-key 有效期约 4 天;不在聊天中打印完整 auth-key;auth-key 优先存 macOS Keychain。
二维码交互要求:
exporter-login-qr-start --open;命令会先复用未完成且未过期的二维码会话,只有过期后才生成新二维码,不要省略 --open。qrcode_path 文件存在且为 .png / .jpg / .jpeg,再按平台调用系统打开命令。exporter-login-qr-status,不要靠等待时间猜测状态。exporter-login-qr-complete,只向用户报告登录是否成功和有效期,不展示 auth-key 或其预览。系统打开命令:
| 环境 | 首选命令 | 备用命令 |
|---|---|---|
| macOS | open "<qrcode_path>" | open "file://<absolute-path>" |
| Windows PowerShell | Start-Process -FilePath "<qrcode_path>" | explorer.exe "<qrcode_path>" |
| Windows CMD | start "" "<qrcode_path>" | explorer.exe "<qrcode_path>" |
| Linux 桌面 | xdg-open "<qrcode_path>" | gio open "<qrcode_path>" |
| WSL | explorer.exe "$(wslpath -w '<qrcode_path>')" | cmd.exe /c start "" "$(wslpath -w '<qrcode_path>')" |
执行规则:
os.startfile(),避免 cmd /c start 的引号陷阱。DISPLAY / WAYLAND_DISPLAY 时不要反复调用打开命令,改为聊天展示二维码图片。本地管理页(仅用户明确要求时启动):
python3 {baseDir}/scripts/wechat_exporter.py exporter-server-start --port 8765{baseDir} = 本 SKILL.md 所在目录,脚本位于 {baseDir}/scripts/。
内部会话数据:~/.moore/wechat-article-downloader/
默认下载目录:
~/Downloads/wechat-articles/<公众号名>/;多公众号 URL 会按公众号拆分目录~/Downloads/wechat-articles/<公众号名>/~/Downloads/wechat-articles/<公众号名>/输出结构:
index.csv
articles/<safe-title>.md
images/<safe-title>/<image-number>.<ext>URL 模式和 Exporter 模式都不再使用可见的 <run-id> 交付目录。run_id 只保存在运行记录里。Exporter 下载会先检查账号目录里的 index.csv 和实际 Markdown/图片文件;SQLite 标记为已下载但文件缺失时会重新下载。
每次结束报告:使用的模式、成功/失败数量、失败 URL(如有)、output_dir、index.csv。
报告中的“成功”必须区分:正文完整、图片完整、源文章已删除。不要把 HTTP 请求成功或 Markdown 文件生成成功描述成“全文和图片均已获取”。
Exporter 模式额外报告:auth-key 是否有效、公众号/文章数量、SQLite 路径。
历史文章模式:必须先在聊天中列出文章标题和日期,让用户选择,不要自动全量下载。
保持回复简洁,详细内容由文件承载。
references/backend-design.md:两模式架构references/skill-cli-flow.md:Skill 驱动 CLI 流程references/output-formats.md:输出文件结构references/compliance.md:安全和权限规则references/troubleshooting.md:常见失败和处理© Moore-developers, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 39 other files (scripts, references) in the repository root of Moore-developers/moore-wechat-article-downloader.
Open the folder on GitHubat commit dea919b
WeChat Article Downloader 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 Downloader this skillMoore-developers/moore-wechat-article-downloader | 294 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Junta Leiloeirossickn33/agentic-awesome-skills | 47k | 2 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Create Experkfly/ex-skill | 2.5k | — | ~3.7k | Automated safety check: Notes | MIT | |
| WeChat Article Searchzjp1997720/wechat-article-search | 268 | 1 repos | ~730 | Automated safety check: Notes | MIT | |
| Cron Opsczl9707/build-your-own-openclaw | 1.9k | — | ~593 | Automated safety check: Pass | MIT |
sickn33/agentic-awesome-skills
Coleta e consulta dados de leiloeiros oficiais de todas as 27 Juntas Comerciais do Brasil.
Skyvern-AI/skyvern
Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.
perkfly/ex-skill
Distill an ex-girlfriend into an AI Skill. An agent skill from perkfly/ex-skill.
zjp1997720/wechat-article-search
Searches WeChat public account articles by keyword through Sogou WeChat Search and returns titles, summaries, dates, source accounts and links.
czl9707/build-your-own-openclaw
Create, list, and delete scheduled cron jobs. An agent skill from czl9707/build-your-own-openclaw.
claw-codes/wx4py
微信自动化操作 skill,用于帮助用户快速完成微信消息群发、文件发送、群管理、聊天记录获取、多群监听、AI 自动回复等自动化任务。当用户需要批量发送微信消息、管理微信群、获取聊天记录、监听群消息、或接入 AI 群聊机器人时使用此 skill。
Downloads and manages WeChat official account articles from URLs, an account's history or subscriptions, adding engagement metrics and top comments when a valid session exists. Written in Chinese, this skill archives articles from WeChat official accounts and prefers to run locally. A wizard script picks the scenario: direct download of full article URLs or a txt, csv or json list; history for a named account through an Exporter login, which is the default, or a proxy fallback; WeChat favorites for comments, reads and likes; and scheduled sync of several subscribed accounts.
WeChat Article Downloader fits situations like: downloading a WeChat official account article from its URL; pulling an account's history list and saving the articles locally; saving comments and engagement data for chosen articles; setting up scheduled incremental sync of several accounts.
Run `npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a claude-code`. Or copy the skill folder (the Moore-developers/moore-wechat-article-downloader repository) into .claude/skills/moore-wechat-article-downloader in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a codex`. Or copy the skill folder (the Moore-developers/moore-wechat-article-downloader repository) into .agents/skills/moore-wechat-article-downloader in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Moore-developers/moore-wechat-article-downloader --skill moore-wechat-article-downloader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moore-wechat-article-downloader, .gemini/skills/moore-wechat-article-downloader, .github/skills/moore-wechat-article-downloader and .opencode/skills/moore-wechat-article-downloader in your project.
Going by SKILL.md and its folder, WeChat Article Downloader needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3 to run the wizard scripts; A QR-code login for history sync; A valid short WeChat session for engagement data.
SKILL.md names 1 domain. In commands or code: mp.weixin.qq.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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.
WeChat Article Downloader is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.4k tokens (SKILL.md is roughly 13k 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 8.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with WeChat Article Downloader: Junta Leiloeiros (sickn33/agentic-awesome-skills, 47k stars), Skyvern Browser Automation (Skyvern-AI/skyvern, 23k stars), Create Ex (perkfly/ex-skill, 2.5k stars) and WeChat Article Search (zjp1997720/wechat-article-search, 268 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Moore-developers (a GitHub user) maintains it in Moore-developers/moore-wechat-article-downloader, which has 294 GitHub stars. The repository was last updated on August 1, 2026.
Source: Moore-developers/moore-wechat-article-downloader on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.