Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair,...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that...
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable...
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages,...
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating,...
Opinionated constraints for building better interfaces with agents.
>
Copy Claude Code project context from one directory to another
Generate daily work summaries from Slack messages, GitHub PRs, AI conversations, and Obsidian notes for a specified...
Expert guidance for working with Espanso text expander configuration files. Use when user mentions espanso, text...
Install a personal skill by symlinking it to ~/.claude/skills/
Interview the user in-depth about their plan or problem, asking detailed questions about technical implementation,...
How to write a Claude Code skill for adroll-dev-ai
How to write a Claude Code skill
|
每日财经简报生成系统。整合全球财经媒体 RSS 源(华尔街日报、金融时报、CNBC 等),使用 Claude API 生成精炼的中文财经简报。当用户需要生成财经简报、抓取财经新闻、或自动化生成每日财经摘要时使用此 Skill。
Agent skill for QR Coin auctions on Base blockchain
>
Build AWS SES email features with reCAPTCHA v3, Zod validation, XSS sanitisation, and rate limiting. Uses...
Initialise new or imported projects. New projects get a private git repo created in the website/app subfolder....
Run Claude Code programmatically via CLI (-p flag), Python SDK, or TypeScript SDK. For automation, CI/CD, session...
Create effective Claude Code skills and agents. Covers official frontmatter spec, global vs project scope, and the...
Configure Supabase authentication with single callback URL pattern. Covers redirect URLs, auth flow types (recovery,...
Deep architectural planning with --ultrathink (32K tokens) followed by phased creation with fresh context. Two-stage...