1,753 boosters for "ai" — open source, verified from GitHub, ready to install
You audit a single plugin in the monorepo before release. You do NOT fix anything — you report findings. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . For domain plugins, the three core-version fields (, , for ) must r
Parse PDF, Office (Word/PPT/Excel), and image files into clean Markdown — with LaTeX formulas, tables, images, and OCR. One zero-dependency script, two backends, No , no API key. The free Agent API handles files ≤ 10 MB / ≤ 20 pages.
"description": "Let local Claude Code sessions talk to each other in natural language.", "name": "vildanbina", "url": "https://github.com/vildanbina"
This is a TypeScript project — AI content pipeline using Claude Agent SDK + MCP. Use strict TypeScript, follow ESLint rules, prefer async/await.
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
You run a single plugin's test suites and report results. You do NOT fix anything — you report pass/fail. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . Plugins in this monorepo ship one of two test conventions. Detect a
"name": "backpressured", "version": "0.1.10", "description": "Drive a goal to completion autonomously while enforcing backpressure (lint, tests, verification) at every step.",
Generate professional-grade structured project Wiki to directory. 1. 完整可运行：包含 import、初始化、调用、结果处理 2. 覆盖导出接口：每个主要导出 API 至少 1 个示例
The definitive SEO and Generative Engine Optimization agent. LLM-agnostic — works on any platform that reads . Merges Google's official SEO guidance, 2026 GEO research, and practitioner best practices into one universal framework. Every finding comes with a
You are a read-only structural validation agent for a single plugin in the monorepo. Your job is to check the plugin's structural integrity and report issues. You do NOT fix anything — you report findings. Check 0 (the native validator) is the authority for schema compliance. Checks 1–7 add hermit-
Root entry point for the DaisyWriter skill collection. Other AI coding assistants can load this collection via:
Official MCP Server for Mailtrap that enables Claude to integrate with Mailtrap's email testing and delivery platform. Developers building email workflows, testing email functionality, or managing transactional emails will benefit from direct Claude integration with Mailtrap services.
"description": "Know GitHub Trending - Generate plain-language GitHub Trending briefings in Chinese and English", "name": "wahahaazhe" "./skills/productivity/github-trending-briefing/knowgt",
Turn your AI agents into pixel-art NPCs in a retro virtual office. Watch them work, complete quests, earn XP, and chat at the water cooler. This installs OpenClawfice and deploys to all agent workspaces automatically. Then deploy to agent workspaces:
每一个工具都是一面镜子。你不想看的，往往正是你一直在重复的东西。 这套 skill 的目标不是把用户写得更“深刻”，而是把行为证据翻译成用户能承受、也能继续行动的真相。 用户说"digital life"或"考古工具箱"时，列出全部 skill 并附引导语，让用户选择。蒸馏人生是偏实用的第 6 个 skill：前 5 个帮用户照见自己，它帮用户复用自己。
You are a TDD specialist for the ZAQ project (Elixir 1.19, Phoenix 1.7, LiveView, Oban). You write failing tests first, then implement the minimal code to make them pass. 1. Red — write a failing ExUnit test that defines the desired behavior 2. Green — write the minimal Elixir code to make it pass
ScrapeGraphAI Scrapegraph MCP enables Claude and other language models to perform intelligent, enterprise-grade web scraping directly within their conversations. Developers, data analysts, and researchers benefit from automated data extraction without building custom scraping infrastructure.
"email": "help@calif.io", "url": "https://github.com/califio/skills" "description": "Claude Code plugins from Calif.io for AI-assisted security research and code auditing"
Advance the claim directly. Say what is true, what the text argues, what the evidence shows, or what the method does. Do not default to explaining what the text does not claim, does not prove, does not imply, does not cover, or does not attempt. Use a calm, competent authorial posture. Write as an a
Work Item Show is a CLI skill that displays comprehensive details about a specific work item, including status, dependencies, session history, and git information—useful for developers managing complex projects in Claude Code environments.
"source": "./plugins/fulcrum", "description": "Task orchestration for Claude Code",
"name": "equilateral-agents", "description": "EquilateralAgents - 22 self-learning AI agents with community standards contribution. Features agent memory, pattern recognition, and workflow optimization for security, quality, deployment, and compliance.", "name": "HappyHippo.ai",
An MCP server that extracts and analyzes components from Storybook design systems, enabling AI assistants to understand and work with design system documentation. Useful for designers, developers, and AI teams building design-aware applications.
"name": "ai-marketing-skills", "name": "SuperAmped", "url": "https://superamped.com"
