Updated 3mo ago
by smithjohn78390
smith--skills
自用/精选的 Claude Code / Codex 技能:内容创作、客服、市场调研、SEO、Agent 工作流循环、Grok X 实时抓取与评审工具
44 GitHub stars (44)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +1 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 19 skills (19 skills found in its SKILL.md files)
- 10 forks (10 forks)
- 3mo ago last update (Last updated 3mo ago)
Install
Skills CLI
npx skills add smithjohn78390/smith--skills
Asks which skills and agents to install. Just one: npx skills add smithjohn78390/smith--skills --skill ai-readability-audit — add -g for every project.
Claude Code
git clone https://github.com/smithjohn78390/smith--skillscp -r "smith--skills/ai-readability-audit" ~/.claude/skills/
Copies the ai-readability-audit skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add smithjohn78390/smith--skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
ai-readability-audit
AI 可读性审计:检查网站是否适合大模型抓取、理解和引用,并给出优化建议。
ai-readability-audit/SKILL.md on GitHub (opens in a new tab) -
claude-review
Claude 无界面评审:用一次 `claude --print` 审查 plan、架构文档、用户文档或 work-log,并返回结构化报告。
claude-review/SKILL.md on GitHub (opens in a new tab) -
cold-email-personalizer
冷邮件个性化:根据潜在客户信息生成定制主题行和邮件正文。
cold-email-personalizer/SKILL.md on GitHub (opens in a new tab) -
competitor-price-monitor
竞品价格监控:跟踪竞品定价页面,对比历史价格,并报告变化。
competitor-price-monitor/SKILL.md on GitHub (opens in a new tab) -
competitor-research
竞品全网调研:收集公司、产品、定价和评价信息,生成结构化分析报告。
competitor-research/SKILL.md on GitHub (opens in a new tab) -
ecommerce-support
电商客服助手:识别客户意图,处理订单查询、商品推荐、投诉和工单。
ecommerce-support/SKILL.md on GitHub (opens in a new tab) -
email-assistant
智能邮件助手:摘要邮件、判断优先级,并生成专业回复草稿。
email-assistant/SKILL.md on GitHub (opens in a new tab) -
geo-content-optimizer
GEO 内容优化:调整文章结构,让内容更容易被 AI 搜索引用。
geo-content-optimizer/SKILL.md on GitHub (opens in a new tab) -
grok
Grok X 实时抓取:让 Claude 调用本地 grok-build 获取真实 X (Twitter) 帖子。 X 模式必须优先驱动 Grok 原生 X 工具族:x_keyword_search、x_semantic_search、 x_user_search、x_thread_fetch;必要时再用 web_search/open_page 交叉验证。 返回带 @用户名、点赞/浏览数、链接、时间的真实帖子。复用用户已登录的 grok.com 订阅, 调用零额外成本(不像 MCP 方案要 xAI API key 按 token 付费)。 三种模式:x(X 实时抓取,主力)、ask(把 Grok 当独立第二意见)、continue(续接追问)。 当用户需要真实 X/Twitter 实时数据时使用,例如: 问问 grok X 上在聊什么、让 grok 搜 X 上对某事的实时讨论、grok…
grok/SKILL.md on GitHub (opens in a new tab) -
influencer-evaluator
网红评估:分析社交账号公开数据,计算评分,辅助筛选 KOL 合作对象。
influencer-evaluator/SKILL.md on GitHub (opens in a new tab) -
linkedin-post-creator
LinkedIn 帖子创作:根据品牌调性和主题生成专业帖子,并支持反馈优化。
linkedin-post-creator/SKILL.md on GitHub (opens in a new tab) -
loopforge
Loopforge:把模糊工作流整理成可复用的 AI Agent 工作流循环规范和提示词。
loopforge/SKILL.md on GitHub (opens in a new tab) -
seo-analyzer
SEO 分析:检查网站结构、技术指标和内容质量,输出搜索优化建议。
seo-analyzer/SKILL.md on GitHub (opens in a new tab) -
social-trend-monitor
社交趋势监控:追踪多平台热点,生成趋势报告和内容机会判断。
social-trend-monitor/SKILL.md on GitHub (opens in a new tab) -
storm-research-agent
STORM 调研助手:用多视角证据分析选题、产品、工具或工作流是否值得推进。
storm-research-agent/SKILL.md on GitHub (opens in a new tab) -
video-creator
AI 短视频创作:生成视频脚本、制作素材,并整理多平台发布流程。
video-creator/SKILL.md on GitHub (opens in a new tab) -
viral-post-creator
病毒式帖子创作:生成高互动社交文案、配图方向和发布建议。
viral-post-creator/SKILL.md on GitHub (opens in a new tab) -
youtube-video-analyzer
YouTube 视频分析:提取字幕或转录文本,输出摘要、观点和关键概念。
youtube-video-analyzer/SKILL.md on GitHub (opens in a new tab) -
z-image
Z-Image 文生图:调用 ModelScope Z-Image-Turbo 生成多风格图片。
z-image/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.