搜索微信公众号文章技能。通过微信搜索获取文章列表,覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯;可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。
npx skills add https://github.com/zjp1997720/wechat-article-search --skill wechat-article-search
该脚本依赖NodeJS依赖包 cheerio,建议先执行全局安装或在项目中安装:
npm install -g cheerio
1、 确认关键词与数量
1、执行常规搜索命令
node scripts/search_wechat.js "关键词"
1) 执行包含数量限制的搜索命令
node scripts/search_wechat.js "关键词" -n 15
2) 如果用户需要保存结果到文件,执行命令
node scripts/search_wechat.js "关键词" -n 20 -o result.json
3) 若想要获取微信文章域名的真实链接”,执行如下命令
node scripts/search_wechat.js "关键词" -n 5 -r
query:搜索关键词(必填)-n, --num:返回数量(默认 10,最大 50)-o, --output:输出 JSON 文件路径(可选)-r, --resolve-url:尝试把中间链接解析成微信文章真实链接(会额外请求每条结果)文章标题、文章地址、文章概要、发布时间、来源公众号名称
> 以下内容由大鹏的 vault 自动追加,用于把本 skill 接入 Obsidian 仓库生态。原版说明见上方。
本 skill 在仓库内自包含依赖,不要全局安装。首次使用或克隆仓库后,在本 skill 目录执行一次:
cd .claude/skills/wechat-article-search
npm install
cheerio 会装到本目录的 node_modules/,已被 .gitignore 排除。脚本通过 Node 的向上查找机制能 require('cheerio'),无需配 NODE_PATH。
.claude/skills/wechat-article-search/scripts/sync-claude-skills.sh 自动软链到 .agents/skills/、.opencode/skills/、~/.codex/skills/、~/.config/opencode/skills/、.workbuddy/skills/(LaunchAgent 监听 .claude/skills 目录变化 + git hook 兜底)。.claude/skills/wechat-article-search/,不要直接改其它位置的软链。wxmp-article-harvester 的衔接两个 skill 职责互补,可串联使用:
| 环节 | skill | 输入 | 输出 |
|------|-------|------|------|
| 关键词发现(本 skill) | wechat-article-search | 关键词,如「AI Agent」 | 文章列表 JSON(标题/链接/摘要/来源/时间) |
| 按账号/URL 抓正文 | wxmp-article-harvester | 公众号名或 mp.weixin.qq.com/s/... 链接 | 结构化索引 + Markdown 正文 |
典型链路:先用本 skill 按关键词发现一批文章 URL 和来源公众号 → 再用 harvester 对感兴趣的账号或具体 URL 抓取正文导出到 ~/.dapeng/wxmp-harvester/exports/。
-o 写到 00_收件箱/Clippings/ 或对应项目的来源目录,文件名带关键词和日期,如 wechat-search-AI培训-2026-07-06.json。weixin.sogou.com),受反爬策略影响,偶发返回空结果或被 antispider 拦截属正常现象,换关键词或稍后重试即可。-r 解析真实链接在反爬收紧时成功率低,失败会保留搜狗中间链接并标记 url_resolved: false。Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take zjp1997720/wechat-article-search from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm.
Without those the skill loads but fails at the first command.