skills
Logfire, Pydantic AI, and Pydantic plugins for Claude Code, Codex, and Cursor. Instrument your code with Logfire, query and export the resulting telemetry, build LLM agents with Pydantic AI, and validate data with Pydantic.
4,248 plugins found in public marketplaces and GitHub repositories, indexed and searchable. Plugin skills also install in Codex, Cursor and 4 more agents. In Claude Code, the 99 that get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → fire as you prompt.
Logfire, Pydantic AI, and Pydantic plugins for Claude Code, Codex, and Cursor. Instrument your code with Logfire, query and export the resulting telemetry, build LLM agents with Pydantic AI, and validate data with Pydantic.
Multi-model orchestration subagents for Claude Code. One model is rarely the right model for every task. Whole-codebase analysis wants a huge context window; a tight bug fix wants fast iteration.
A Claude Code subagent for pastry recipe lookup and Baker's Percentage calculation, built around a professional pastry recipe library.
Claude skills for building modern web applications with Hotwire (Turbo and Stimulus). These skills are extracted from the Hotwire Club knowledge base and organized into 6 topic-based skills covering common patterns and best practices.
Push it to GitHub and send us the link. We read it, then it goes live.
The skill skill can help you find, improve, and publish skills, install it with npx sundial-hub add skill. You'll be able to peruse this library of curated skills, plus 50,000+ more aggregated from the web.
Governance and quality gates for AI coding agents, with skills for specification, context documents, verified local Git commits, and blocking broken cryptographic code. Works in Claude Code, Codex CLI, and Pi.
Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.
Portable, evidence-bound security skills for authorized defensive assessment, penetration testing, red teaming, detection engineering, purple teaming, and engagement operations. The collection contains 56 skills in 10 installable plugins from zero-lab.ai.
A Claude skill for professional motion design with correct Persian typography. Films that don't play like slideshows, and Persian that doesn't fall apart. Most generated motion fails in two predictable ways.
paad 2.0.0 is out. You can now tailor paad to your own needs with config files, and security findings now stay out of your committed reports. See the 2.0.0 release notes and the changelog.
This document explains how to run, build, and maintain the project locally.
Proof before done. Move from vibe coding to agentic engineering. Give Claude Code or Codex your project rules, a definition of done, and checks that produce evidence.
Generate paste-ready Power Apps Canvas App YAML from screenshots, mockups, or text, directly inside Claude Code.
One macOS app for Claude Code, Codex, and every agent runtime you use, scheduled runs, global hotkey launcher, per-run git worktrees, one review board.
Web search MCP server that does search result reranking locally on your machine, formerly known as mcp-local-rag. no API keys.
Now with Jev, optional, near-free triage that keeps the lead focused. Set it up. Fable Foreman teaches Claude Fable or Opus, the lead, to plan coding work, assign it to capable agents, and personally verify the result.
Protocol-agnostic CesiumJS AI control runtime for MCP, WebMCP, function calling, and browser agents.
A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls.
Science-backed AI team assembly. From goal to agents to artifacts. Forge is an open-source system that uses controlled multi-agent scaling research (Kim et al., Google Research/MIT), persona science, and context engineering to assemble AI agent teams.
A self-evolution system for AI coding assistants "auto-triggers every 3 days" but had no enforcement mechanism, the review only ran when manually invoked, and the tracker went stale silently.
Kept saves your AI conversations as local Markdown files, then gives you a desktop app to search, browse, connect, and reuse them. It works with ChatGPT, Claude, Gemini, Grok, and Kimi.
Writes captions and descriptions for social media posts and reels on Instagram, TikTok, Threads, Facebook, and YouTube Shorts. Turn your text, script, or a competitor's post into ready-to-post copy tailored to each platform.
Open-source framework for building PumpFun Telegram bots on Solana. Claim monitors, channel feeds, group trackers, whale alerts, build your own or use ours. PumpKit Web App + Documentation.
Make short-form UGC ads (TikTok, Reels, Shorts) for the product you're building, from inside Claude Code, OpenAI Codex, or any agent that speaks MCP.
HBG Agent Skill for Chinese life-simulation narrative videos with consistent comic IP, rapid multi-life openings, Edge TTS, synchronized captions, zoom/pan motion and final MP4 QA.
Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Code can spawn subagents via Task().
175 expert marketing methodologies for AI agents. Free. Open source. MIT licensed. Dunford on positioning. Schwartz on copywriting. Cialdini on persuasion. Ogilvy on advertising. Hormozi on offers. Voss on negotiation.
Please star Taskuary if you find it helpful, it is how other people find it.
Import C++ and Rust like JavaScript modules (WebAssembly & React Native)
A Claude Code skill that provides systematic first principles thinking methodology for evaluating designs, challenging assumptions, and building solutions from fundamental truths.
Reference packs, a trace-first development workflow, and specialized reviewers that make AI coding assistants work from your real Odoo source instead of from memory. Odoo 16–19.
Open-source AI director agent that turns one plain sentence into a full short film, storyboard, shoot, review, retake, deliver.
The first Claude skill for writing production-grade, security-first Solana programs. Built by a Solana security researcher, for Solana developers, so your code arrives at audit already hardened.
Claude Code skills for Emacs integration. These skills enable tighter integration with agents running inside Emacs, for example agent-shell.
The Octagon MCP server provides specialized AI-powered financial research and analysis by integrating with the Octagon Market Intelligence API, enabling users to analyze and extract insights from public filings, earnings calls, financial metrics, stocks &
A Go CLI tool to track blog articles, detect new posts, and manage read/unread status. Supports both RSS/Atom feeds and HTML scraping as fallback.
Process documents 100x larger than your LLM's context window, without vector databases or chunking heuristics.
Bu repo, YouTube videomdaki Claude Code ajanları + skill'ler setup'ının tam halidir. Kopyala, kendi makinene kur, 20 dakikada aynı sistem sende. Bölüm 1, bu video · Ajanlar + Skills temel yapı Bölüm 2, sonraki video · Ajanlar + Obsidian (kalıcı hafıza)
Built by agents, for agents. Command-line interface for the Nansen API, designed for AI agents to research on-chain data, manage wallets, and trade through nansen trade. Use it for both analytics and execution: nansen research.
Connect your agent with the world. Blocks provides the developer tools and Network to connect, call, and earn everywhere AI agents are at work. This repository contains the public SDKs, CLI, MCP server, and runnable examples for building on Blocks Network.
A Claude Code plugin providing skills and comprehensive documentation for building plugins, skills, MCP servers, and other Claude Code extensions.
Part of the linkedin-skills family (400+ stars). Same voice engine and approve-before-publish flow, now for Facebook. Also available for Instagram · X · YouTube · TikTok · Threads. 8 skills that turn Claude Code and Codex into your Facebook Page content team.
Make Claude talk like a human: 17 installable output styles for Claude Code, built on credited methodologies.
An agent skill that sources accurate, on-brand b-roll for talking-head video, and places each cutaway on the exact word.
Answer product management's hardest questions in minutes, not days Expert product management guidance powered by frameworks from Teresa Torres, Marty Cagan, April Dunford, and more - without hiring a product manager. Right feature. Right users. Right time.
A persistent, reviewed multi-agent runtime for long-horizon research and engineering.
AskUserQuestion pushed to the max A complete toolset that enables maximum level of human-(intention-)in-the-loop onto any long-running, multi-agentic AI workflows (like Ralph Loop!).
A comprehensive agent skill for building production-ready email systems. Covers everything from DNS authentication to webhook processing, with a focus on deliverability, compliance, and reliability.
Adversarial bug finding skill for Claude Code. Uses 3 isolated AI agents to find and verify real bugs with high fidelity.
A collection of Agent Skills for structured, reproducible troubleshooting and security assessment of Alibaba Cloud ECS instances.
Hermes One-Click: Windows desktop client for Hermes, one-click setup, Tauri + embedded Python. Build from source with clear docs.
Building the social economy for AI agents? Star the repo and help others find the path.
An agent skill that produces a beat-synced 1920×1080 30 fps motion-graphic video: the scene cuts land on the music's beats, the reveals land on the spoken words, and the audio is broadcast-clean. MIT licensed.
Run Claude Code 24/7 from Telegram. Drop-in upgrade for the official plugin: voice notes both ways, a self-healing daemon, memory across restarts, and Agentic Mode (watch every tool call live). One-line install.
一套完整的學術研究 Skill 套件,符合 Agent Skills 開放標準。支援 Claude Code、ChatGPT / Codex CLI、Gemini CLI。
The production-grade fork of obra/superpowers, same trusted workflow, dramatically leaner, safer, and more intelligent.
Create handoff documents that let any AI coding agent continue your work.
Gearcoleco is a very accurate, cross-platform ColecoVision and Coleco ADAM emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Ever lost a conversation session with Claude Code, Codex, pi or Grok and wish you could resume it? This skill lets your agents search across all your past conversations with full-text search.
A Claude Code skill for building web interfaces that move well. Most generated pages come out static. Default scrollbars, sections that just appear, hover states that do nothing.
One command drops a tested, versioned skill into your agent. No more ad-hoc prompts. The same rigorous steps run every time. Skills are independent files.
Bring Your Own Browser, let your AI assistant use the Chrome you already have open. byob is a local MCP server that lets AI coding tools (Claude Code, Cursor, Cline, Windsurf, etc.)
Agent skills that give coding agents your team's context at session start, so they stop working like strangers.
A comprehensive Claude Code skill for architecting production-ready Elixir/Phoenix applications with complete documentation, ADRs, guardrails, and handoff materials.
Instructions for writing production grade solidity code and working with BattleChain.
analytics-tracking-automation is a local-first AI skill for planning, reviewing, and delivering GA4 + GTM tracking.
Open-source GEO skill for Claude Code and Codex. Run a first-mile AI visibility audit for a brand website, then generate buyer prompts for ChatGPT, Gemini, DeepSeek, Grok, Perplexity, Claude, and other AI answer engines.
An AI skill for one-shotting Bricks Builder designs as JSON, hero sections, full landing pages, headers/footers, query loops with faceted filters, ACF-driven layouts, conditions, animations, and popups.
Research Application Toolkit is a single repository that ships host-specific integrations for both Claude Code and Codex.
From automating App Store submission to deciding whether an iOS app is actually ready to submit, and helping recover when review fails.
Professional agent skills and plugins to help mobile developers ship better apps faster with AI assistance.
Persistent memory for AI coding agents. Your agent remembers what it learned across sessions.
A two-layer skill for writing prompts, agent directives, skill descriptions, slash commands, and anywhere else an LLM reads instructions. Works the same in Claude Code and OpenAI Codex CLI. Same SKILL.md, same trigger surface, same outcome.
Stop losing an afternoon to chasing dozens of reference PDFs by hand. One DOI in, every reference PDF out, using your existing institutional access. Status: beta (v0.4.1). Windows + Microsoft Edge verified path. macOS / Linux / Chromium untested.
Opinionated AI coding agent and dev environment automation for macOS that dominates your dev setup like cats rule the Internet. This project is named after Arthur C.
The ServiceNow SDK brings modern developer workflows to the Now Platform: build applications as source code, version them with git, and ship them using the tools you already know.
A local structural code graph and context toolkit for AI coding agents. Engram indexes source entities, Git relationships and selected project memory, then exposes focused context through a CLI, agent hooks, MCP and an authenticated local dashboard.
LLM-optimized skill documentation and development resources for the GenerateBlocks WordPress plugin.
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.
A Claude skill that converts working Claude Code prototypes into structured Figma design files, exploding each interaction flow into separate frames, using your design system components, and annotating interaction details natively in Figma.
Shows how to get more out of Claude Code in day-to-day development, with ready-made skills for structured feature planning, release version bumps, code review run by parallel or persistent reviewers, and keeping the website's component reference up to date.
Nemp - The memory plugin for Claude Code that remembers everything.
한국어 버전 (Korean) A skill that gathers opinions from multiple AI CLIs (Codex, Gemini, ...) and lets a configurable Chairman synthesize a conclusion. Inspired by Karpathy's LLM Council.
A Claude Code plugin for static analysis and security auditing of Java JAR and WAR packages. It builds a SQLite analysis database and runs audit queries such as method call tracing and vulnerability pattern detection.
This repository is an Agent Skill package for Android development with Kotlin and Jetpack Compose. It provides a structured set of instructions, templates, and references that help agents build production-quality Android apps consistently and efficiently.
Agent skills for fallow. They teach coding agents (Claude Code, Codex, Cursor, and others) to check health, complexity, duplication, architecture, styling drift, and unused code with fallow.
Claude Code · Codex · ChatGPT · OpenClaw · Cursor. Summarize YouTube, Bilibili, podcasts, and local files via the bibi CLI or hosted MCP. AI Agent skills for BibiGPT. Multiple skills, one CLI (bibi), one account.
Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.
Deterministic research MCP server, web + social + academic + news + code + docs, all in one place. No API keys, no in-server LLM, structured outputs for agent chaining. 100% Free & Open Source, No API keys or subscriptions for core tools.
Verification-first Agent Skills for Codex OS, with optional compatibility adapters for Claude Code, Gemini, Cursor, and Windsurf.
Your library to write discord apps in C# with focus on always providing access to the latest discord features.
Lets Claude create and update Linear issues, check project status and manage team workflows, so you can handle tracker work from your coding session instead of switching to the Linear app. It works through Linear's MCP tools, SDK and GraphQL API.
Let AI agents share your everyday, logged-in Chrome through a Skill + CLI, locally or across multiple machines.
Co-Researcher is an academic research plugin for Claude Code, Gemini CLI, OpenAI Codex and OpenCode. It runs literature reviews, systematic reviews, peer review and citation checks inside the AI assistant you already use.
A Claude Code skill that turns natural language into professional draw.io diagrams, flowcharts, architecture diagrams, comparisons, and more.
A curated collection of Agent Skills for the Ant Design ecosystem.
A marketplace of agent skills by VerySmallWoods, content creation, publishing, analytics, and security scanning. Works with Claude Code, Codex, Cursor, Windsurf, and any other coding agent that supports the skills.sh format.
Claude Code plugins from BuildAtScale - slash commands, hooks, and skills for enhanced productivity.
Rewrites Russian text that shows signs of AI generation so it reads as human-written, removing bureaucratic phrasing, ChatGPT-style stock phrases, and filler. It keeps numbers, dates, names and caveats unchanged.
Premium SwiftUI animation and interaction skills for AI coding agents, generate production-ready micro-interactions from plain English prompts. Built from legendary-Animo: 84 hand-crafted SwiftUI animation demos.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.