claude-recap
Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.
Claude Code plugins, indexed and searchable. The ones 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, and they are only on Flowy.
2,582 plugins indexed. 99 of them fire as you prompt.
Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.
Connect your AI coding agent to Snowflake. Plugins for Claude Code and OpenAI Codex that automatically detect Snowflake prompts and route them to Cortex Code — where 55+ built-in skills handle SQL, data governance, dynamic tables, ML, and more.
Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable
Public Netlify skills for AI coding agents. Each skill is a focused, factual reference for a Netlify platform primitive — designed to help agents build correctly on Netlify without needing to search docs.
Push it to GitHub and send us the link. We read it, then it goes live.
English · 中文 · Documentation AI Rules Sync (AIS) — Install, compose, update, and publish native agent assets from multiple Git repositories across all your projects. AIS is an asset federation toolkit, not a format converter.
**Turn an idea into a real brand — name, identity, voice, and a brand book — without leaving your AI agent.** 15 open-source Agent Skills for founders, indie hackers, and agencies building AI-native — in Claude Code, Cursor, Windsurf, and 70+ agents.
A Claude Skill that orchestrates multiple LLMs as a "council" to achieve collective intelligence through peer review and synthesis.
A Claude Code skill that forces AI to understand before executing. A good prompt solves the problem fast — not through decoration, but by aligning with the AI from the very first message and on every one after.
Threat hunting command system for agentic IDEs
Claude Code skills for founders, developers, and web3 builders. This repository publishes reusable skill folders under skills//, ships stable bundle downloads through GitHub Releases, and publishes changed skills to ClawHub.
YOINK (You Only Implement Native Knowledge) is an AI agent that removes complex dependencies by reimplementing only what you need. YOINK is currently built as a Claude Code plugin that decomposes third-party dependencies into internal replacements.
Claude plans. Cursor writes. Claude reviews. A Claude Code plugin that delegates coding execution to Cursor's Composer — without ever leaving the Claude Code TUI.
Distribution repo for the OutSystems MCP. To install, paste the matching prompt below into your AI assistant. Every harness section below sets up two artifacts and says how to keep the skill current.
Portable skills, agents, hooks, and Pi-native extensions for Claude Code, Codex CLI, GitHub Copilot, Cursor, Grok, and Pi. Gemini is retired.
Make every model cheaper or better. Measured on four Claude models — none got worse. What it actually is: a zero-config Claude Code plugin.
AIX Skills is a public collection of Agent Skills, templates, and references for building repeatable AI workflows.
A multi-model AI orchestration MCP server for automated code review and LLM-powered analysis.
A Claude Code plugin that makes AI coding agents follow engineering discipline. Plan before coding. Verify before claiming done. Find root cause before patching. Review before merge. Skills activate based on file type and task signals, not manual toggling.
Textbook-Writer-Skills 是一套装进编程智能体(Claude Code / Codex / 国内 WorkBuddy)的教材写作 skill 组合。它把成熟的教学设计方法装进 AI 的工作流:先想清楚「学生学完该带走什么」,再倒推章节和习题,一章一章写出有主线、有梯度、题目答案可信的成体系教材——中途断了随时续写。当前 v0.6.2:5 个 skill(1 个主调度 + 3 个流水线子 skill + 1 个独立辅助)覆盖从工作目录规划到审核定稿的五阶段全流程,理科、人文社科与经济学都能写。
A collection of AI agent skills for working with SpecStory session histories. Built for developers who want Claude Code (or similar AI coding assistants) to help analyze, organize, and extract insights from their AI-assisted coding sessions.
Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.
A Claude Code plugin that enforces hexagonal architecture (ports & adapters) in Symfony projects. Works with both new projects (full scaffolding) and existing projects (progressive, module-by-module refactoring).
Real-time observability for AI coding agents — Claude Code & OpenCode Monitor tokens, costs, tool calls, agents, MCP, sessions, quotas and multi-agent orchestration locally. Most tools read your logs after a session ends.
A harness that wraps Claude Code with enforcement, specialist agents, and alignment gates to deliver consistent, production-grade software engineering outcomes.
Claude Skills for Ableton Live producers. Workflows for Claude Code, Cursor, Codex, and Gemini CLI. Pairs with any Ableton MCP server. MIT.
把任意文本、文章链接或线程内容,转成一张可以直接发布的 HTML 信息卡。 它的目标不是“做漂亮图片”,而是让卡片本身完成信息传达:先可读,再有审美,再适合传播。
Make Claude Opus 4.8 in Claude Code behave as much like Claude Fable 5 as possible. The doctrine was transcribed by Fable 5 itself; hooks enforce it at the harness level; an eval loop measures convergence against golden Fable transcripts.
Turn Claude Code into a structured delivery loop: plan the work, run modules in parallel, validate deeply, retry intelligently, and carry forward what worked.
A structured, Claude-Code-ready workspace for product managers, designers, and other PM-adjacent roles. Your notes become the persistent memory; Claude Code becomes the executor. This is a template.
A toolkit of Claude Code skills for long-form content creators — research, score, rewrite, and publish, end to end. 中文版: README.zh-CN.md 5 skills extracted from a real working writing setup. They are opinionated, narrow in scope, and meant to compose.
🚀 Marketplace of domain-specific plugins for building enterprise AI agents. Enable AI agents to perform finance, banking, legal, and sales workflows using modular domain plugins.
Lovable Claude.ai / ChatGPT / Lovable skill upload: Download paymob-integration.zip — do not use GitHub's Code → Download ZIP. Give any AI coding agent expert, workflow-driven knowledge of the Paymob payment gateway across Egypt, UAE, KSA, and Oman.
Arness — H not required. Structured AI workflows for Claude Code. From first idea to production deploy. Seven entry commands. That's all you need to remember.
Research, audit, compete, and publish. A complete social media intelligence and content production system for any brand, built as a Claude Code skill.
Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.
A transparent proxy that gives Claude Code rolling context compression — old messages get automatically summarized while recent messages stay fully verbatim. You never hit the context wall, and you never lose important details. Zero config.
Persistent project-scoped memory for Claude Code. Auto-loads on session start, structured by schema, hot/cold layered.
Live Asian-priced football & basketball odds, scores, and de-vigged fair lines — packaged as an Agent Skill for Claude Code, Codex, OpenClaw, or any agent that can run a shell script.
AI skills for German legal practice and EU compliance. 66 plugins, 291 skills: general law, Fachanwaltschaften, high-volume practice areas, EU frameworks (KI-VO, NIS2, KRITIS, DORA, CSRD, Data Act, BFSG, MiCAR) and VDuG collective redress. Claude, Gemini, GPT. Statutes linked to primary sources; case law marked verified or [unverifiziert].
Describe a deck and get one built. Or drop in an old PDF or PPTX to rebuild it. Either way: a polished, interactive HTML deck. An open-source deck builder for coding agents.
👉 ⭐ Star on GitHub if Hardstop keeps you safe! Pre-execution safety validation for AI coding agents.
Production-grade Claude Skills for building, debugging, and shipping n8n workflows — distilled from 100+ production workflows by an n8n Verified Creator. Give Claude Code the instincts of a senior n8n engineer.
Build with Claude Code without your brain going numb. No-Numb quizzes you on the code Claude just wrote — and, by default, blocks the session from continuing until you pass. The middle ground: built fast like an agent, understood like you wrote it yourself.
I used to spend weeks building multi-agent systems with LangGraph, CrewAI, and AutoGen. Hundreds of lines of Python orchestration code, custom state machines, fragile message passing between agents.
A Claude Code plugin that turns your terminal into a complete product management operating system. 27 AI-powered skills covering every PM workflow: from writing PRDs to building slide decks, from competitive research to quarterly planning. No empty templates.
A Claude Code skill that takes a user from raw documents (Form 16, AIS, Form 26AS, broker Tax P&L, payslips) to a fully reconciled, schedule-by-schedule computation and a portal-ready data-pack JSON — designed to be handed to another agent (or a human) that
Your agent writes. You decide. The open-source writing surface for the agentic era. OpenWriter is a markdown-native rich text editor built for humans and agents working side by side. Your agent writes, and you review and approve every change before it lands.
Claude Code plugin that exposes Codex CLI's built-in imagegen skill as /codex-image:* user-invoked plugin skills. The plugin does not implement image generation itself.
A Claude Code plugin - and a set of standalone skills for any AI assistant: skills, agents, and commands for AI-native development. In Claude Code it runs locally against your own codebase using whichever model you already pay for.
Persistent, self-evolving memory for Claude Code. Stop re-explaining your project every session.
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
Most monitoring tells you something broke. A doctor opens the pull request that fixes it.
A Claude Code / Claude.ai skill that turns a single request — a myth, a premise, or nothing at all — into a finished, narrated mythic short film in a layered cut-paper diorama style: stacked matte cardstock worlds, a strict three-colour palette, exposure that
Browse every recent Claude Code session across all your projects and jump back into any of them. Shows project path, summary, git branch, model, turn count, and a ready-to-paste resume command. --open re-opens a whole working set in terminal tabs. Local files only: no network, no telemetry.
Community-maintained Agent Skills for Julia development. Installable into Claude Code, Codex CLI, Cursor, Gemini CLI, Windsurf, and any tool supporting the Agent Skills standard.
Want Claude Code, Codex, or Cursor to drive Grok Build? If you already pay for a Grok subscription, this gives any of those agents live X search and data right in their context. A couple of ways to wire it up.
A Claude Code plugin that stops vague prompts before they run. Detects your stack, asks targeted questions, and forges a structured prompt. Zero credits wasted.
This Claude Code plugin repo assists complex software projects in their first steps towards agentic coding: Scaffolding and gradually augmenting an existing codebase with an efficient harness setup.
🌐 Read this in: English · हिन्दी · 中文 · 日本語 · 한국어 · Español · Português · العربية · اردو · தமிழ் · বাংলা · Русский You need to ship 30 articles this quarter that sound human, cite real sources, link into your funnel, and survive an editor who checks.
Agent Guard is a local-first guardrail for Claude Code, Codex, Git hooks, GitHub Actions, and direct shell use. It blocks common secret-exposure paths before a supported tool runs, redacts supported tool output, and scans changed files after mutations.
An agentic framework for building games on any platform — for Claude. Like gstack is for software, but for games. Questions, feedback, or just want to follow along: Discord · @metatransformr on X
An agent skill that turns a topic into a fully-designed, print-ready PDF book — researched outline, per-chapter writing, cover, table of contents, per-chapter illustrations, polished typesetting, and a fact-check pass.
A local NotebookLM, multi-agent deep research, and 21 more commands — for Claude Code, powered by Google Antigravity (agy / Gemini 3.x), the official CLI that replaces the now-deprecated gemini-cli.
Self-hosted semantic code search platform — Go server with web dashboard, CLI, and AI-agent skills. Search code by meaning, not text: hybrid BM25 + dense embeddings via llama.cpp.
Pre-1.0 · stable v0.9.4 · pip install aiswmm==0.9.4 · CHANGELOG Headaches from tedious model setup? Try our another project SWMMCanada, our automated model-building project: draw an area anywhere in Canada and get a ready-to-run SWMM model. Up and running now.
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Agent Skills for modern software development frameworks with best practices and coding standards.
Design direction for AI coding agents—grounded in product behavior, platform idiom, and rendered evidence. Stark routes UI work across web, Windows, Apple, Android, cross-platform, UX, and design tokens.
The official Helius AI tooling repository — everything you need to interact with Helius and Solana from the command line, from AI assistants like Claude, or autonomously as an agent.
Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents to coordinate with each other seamlessly, whether you're working from a browser, a terminal, or any other client.
Remove AI writing patterns from text, making it sound more natural and human. Focused on Traditional Chinese (Taiwan). One skill, seven hosts.
Practical agent workflows for Python, ML, and open-source maintenance. AI-Rig turns recurring work—scoping a change, reproducing a bug, reviewing a pull request, running an experiment, or checking release readiness—into explicit workflows with specialist
54 production architecture principles your AI coding agent (Claude Code, Cursor) follows automatically. Drop-in CLAUDE.md, .cursor/rules/, and .claude/skills/ for FastAPI, Next.js 15, and Go 1.22+. MIT.
Ask for a diagram. Get a hand-drawn animation — one HTML file, one seamless-loop GIF.
A curated library of 137 production-grade skills for Claude and other AI coding agents. Every skill follows one structure, speaks with one voice, and earns its place by changing what the agent does.
GTM without the SaaS layer. An outbound pipeline built as agent skills for Claude Code and Codex: describe an ICP in plain English and the chain takes it from company discovery to verified, signal-ranked contacts - every step running on raw vendor APIs, not
Turn your AI assistant into a senior web developer. Production-ready guides for SEO, performance, agent-readiness, and more.
Autonomous software development for Claude Code. ERPAVal stands for Explore · Research · Plan · Act · Validate — the five-phase loop, plus a sixth Compound phase that writes durable lessons to disk so the next session inherits what this one learned.
繁體中文 · Public harness contract · 0.4 migration · 0.5 goal-slice migration Provider-neutral collaboration skills plus an optional, standard-library-first Python harness for bounded, resumable, human-authorized agent work.
One reliable control plane for every Claude Code session on your machine. Run more than two or three Claude Code sessions and you lose track of them: which terminal is which, which one is blocked on a permission prompt, and which two are editing the same file.
The most comprehensive Apple platform engineering skill for AI coding assistants. ~100KB of production-tested patterns across Swift 6 concurrency, SwiftUI, Metal, RealityKit, and visionOS — areas no other skill covers in depth.
AI coding assistant skills for building CrowdStrike Falcon Foundry apps. Build Foundry apps from a natural language prompt — API integrations, workflows, UI pages, functions, and collections — all scaffolded with the Foundry CLI and deployed to the Falcon
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
Two frontier models, one job each. The model that wrote the diff never grades it.
Superpowers & Beads task memory for AI coding agents - supports Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Kimi Code, Antigravity, Factory Droid, and Pi.
Agent skills for work that needs more control than a single prompt: long-running execution, high-recall code review, and measurable self-improvement loops. These are not vibe-coding macros.
Evidence-based SEO diagnostic skill built from Google Search Central, Ahrefs SEO checklist, and Microsoft's AEO/GEO guidance. Reference sources: Google Search Central Ahrefs SEO + AI Search Checklist Microsoft AEO & GEO Guide
Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).
Covers the complete WordPress plugin development lifecycle — build, test, audit, release, and ship to WP.org — for Claude Code, Gemini CLI, Cursor, Windsurf, Cline, Codex, GitHub Copilot, opencode, and more.
Team memory sharing for claude-mem — sync AI memories across developers via git.
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.
How do I check brand visibility in AI? Use open-geo. It measures whether your brand shows up in ChatGPT, Google AI Overview, Claude, Gemini, Yandex Alice, DeepSeek and Perplexity by reading the rendered answer a logged-in user actually sees — not the engine's
Your skill first, the process skill second, gates and memory on the card — before any tool fires. A hook-driven router for Claude Code.
Fable 5 holds the baton. The orchestra plays. A Claude Code plugin that makes Fable 5 the orchestrator. Fable keeps the judgment, tiered subagents on Opus, Sonnet and Haiku do the labor. Install once and every new session in every repo starts this way.
專為繁體中文使用者設計的 Claude Code 插件集合,提供開發、生產力、安全與學習等工具。
AI-native task management for Claude Code. Track tasks in a MASTER_PLAN.md file, pick what to work on, save progress, and ship — all through agent skills.
秒悟(Meoo)官方命令行工具,让 Claude Code、Codex、Cursor、Qoder 等本地 AI 助手在帮你写完前端代码后,能直接接管「数据库、用户登录、文件存储、部署上线」的所有云端工作——你只需要在终端跑一条命令,剩下的交给 AI。 完整文档索引 获取所有可用文档页面的完整列表。
A Claude Code plugin that runs config-driven development workflows as a state machine. You declare stages, transitions, and inputs in a single workflow.json; the plugin's hooks and scripts drive the loop.
Local AI skills central library + scoped symlink enablement. One AISkills directory holds every skill source; symlink what you need into a project, the shared user-level Agents directory, or Hermes on demand.
🇰🇷 한국어로 읽으시려면 → README.ko.md · 🇬🇧 English continues below. The kind little buddy that says "this already exists" before you write it again. Your repo's companion for vibe-coding sessions.
A collection of open-source Agent Skills for OpenClaw, focused on content creation — images, audio, and video — with zero API key management. We handle all the service integrations so you can focus on creating.
通用需求分析到开发实施工作流 — 26 个独立可组合 skill、3 个完整行业示例、13 个 CI workflow、26 个自动化脚本、15 个 pytest 测试。
穷理证澈 Academic Research Skills: Plan the work, search the literature, draft and review manuscripts, run research code, and keep the evidence trail in one place.
Dex is the agent-native analytics engineering toolkit. Point it at your warehouse and your dbt project. It learns the landscape, authors your transformations, and tells you exactly what to fix when the schema drifts. Built for analytics engineers and data engineers who want more out of their coding agent.
Structured frameworks for AI product managers — covering daily workflows, product thinking, and technical depth.
From "I want a board that does X" to a wired .kicad_pcb EasyEDA can auto-route and JLCPCB can build — in a single Claude Code conversation. kicad-jlcpcb is a Claude Code plugin + MCP server that automates the tedious half of going from idea to fab.
Great music in your Claude Code sessions, with an AI DJ that understands your vibes
Bootstrap a fully personalized Obsidian vault with a single command. Obsidian AI Setup is an open-source onboarding system that transforms an empty Obsidian vault into a structured AI-ready knowledge base.
The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.
A file-based memory and prompt bridge that connects claude.ai (where you think) ↔ Claude Code (where you build) ↔ Obsidian (shared long-term memory). -lightgrey.svg)
AI-powered whitebox penetration testing plugin for Claude Code. 9 languages, 22 skills, 7 autonomous agents. STRIDE threat modeling, OWASP 2025 coverage, polyglot monorepo support.
A skill for AI coding assistants that generates and modifies Metin2 client UI code.
Ore in, steel out. A blacksmith doesn't blame the ore. It smelts, shapes, tempers, and quenches — until what comes out holds an edge.
Agent skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of "97 Things Every Programmer Should Know"
Your AI agent adds Sentry instrumentation — metrics and tracing — the right way on the first try, so a year from now, when someone asks "is the app actually working?", you have an answer that isn't a guess.
An opinionated library of Flows. Free. Open source. V1.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic