bun
Skills for contributors to the Bun JavaScript runtime codebase. They cover implementing JavaScript classes in C++ and Rust with JavaScriptCore, garbage collector pitfalls, Rust system calls via bun_sys, and finding slow CI tests.
Flowy lists 95 plugins for Redis work in Claude Code. Each one bundles skills a Claude Code agent can load while you work. Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
Skills for contributors to the Bun JavaScript runtime codebase. They cover implementing JavaScript classes in C++ and Rust with JavaScriptCore, garbage collector pitfalls, Rust system calls via bun_sys, and finding slow CI tests.
Creates branded editorial diagrams such as architecture charts, flowcharts, sequence diagrams, ER models, timelines and swimlanes as self-contained HTML and SVG files. Suited to writers and designers who want polished visuals for Claude Code.
Builds and tracks job-search materials for Claude Code users: a complete resume as importable Reactive Resume JSON, mock and prep interviews, a job application pipeline, and offer negotiation help.
Draw and edit draw.io diagrams by chatting with an AI. Describe a diagram in a sentence and the AI draws it on a real draw.io canvas. Edit it by hand like any draw.io file, or select a few shapes and tell the AI what to change.
A lightweight framework for building multi-agent workflows that works with OpenAI's Responses and Chat Completions APIs as well as many other LLM providers.
Gives AI coding agents persistent memory across sessions, capturing observations automatically and offering recall, session history, hybrid search, and a knowledge graph through skills, commands, and MCP tools.
Lets Claude Code inspect DBX-managed database connections, explore schemas, run bounded read-only queries, generate DBML or schema docs, and open tables in DBX Desktop.
A multi-agent orchestration system that coordinates specialized AI agents through a real-time Kanban dashboard, with workflow approval, model configuration and full audit trails.
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Gives Claude Code users network observability for Kubernetes clusters, with skills for installing Kubeshark, writing its filter language, root cause analysis of past incidents, and security audits, backed by an MCP server for AI agents.
Skills and agents for working on Redpanda Connect, a stream processor that moves data between sources and sinks with hydration, enrichment, and transformation. Includes a schema.Common metadata audit and a code review for pull requests.
Gives Claude Code skills for using Honcho as persistent memory of the user, covering the recall and record loop, sessions and peers, integrating Honcho into Python or TypeScript code, and debugging Honcho workspaces.
Gives a machine learning team one place to define features and serve them consistently, so training data and live predictions use the same values. Covers the offline store, online store and feature server.
Runs a math modeling contest from start to finish: it analyzes the problem, builds and solves the model, produces the code and charts, and drafts the paper in Typst or LaTeX, so you get a complete submission-ready paper instead of assembling each stage by hand.
Authors, validates, and troubleshoots Dagu workflow definitions in YAML and runs Dagu CLI operations. Useful for creating or debugging DAG files, choosing commands, and managing DAGs and run history.
Gives Claude Code a bash-style interface to files and directories mounted from cloud storage, databases, and APIs in one virtual filesystem. Includes skills for working with mounted data and for building custom adapters for new data sources.
Lets an AI assistant read and change your Gmail, Drive, Calendar, Docs, Sheets and other Google Workspace apps in plain language, so you stop clicking through each app by hand. Works from Claude Code via MCP tools or a command line interface.
Open-source meeting bots and real-time transcription, cloud or fully self-hosted.
A persistent memory layer shared across AI agents such as Claude Code, stored as Markdown and searched by semantic recall. It offers skills to recall past sessions, configure memory behavior, and turn past workflows into reusable skills.
Skills, agents, commands and MCP servers that help developers build Stripe integrations in Claude Code. They cover payments and API choices, Stripe Connect onboarding and verification, Stripe Apps and dashboard extensions, and Metronome usage-based billing.
Gives Claude Code users Stripe-focused skills, agents, commands and MCP servers for payment integration, Stripe Connect onboarding and verification, Stripe Apps development, and usage-based billing with Metronome.
Lets AI coding agents such as Claude Code control locally connected Android phones through screenshots and allowlisted actions. It can run natural-language mobile tasks, list online devices, and install or update the OpenGUI backend.
A Go-Spring development skill that takes a plain request, plans it, and builds it in a Go-Spring project by scaffolding code, adding interfaces, regenerating code, wiring components, and writing tests.
An open-source API gateway that sits between your applications and multiple LLM providers, routing requests to providers such as OpenAI, Anthropic and Google Vertex AI through one middleware layer.
Arkon gives Claude Code users skills to query a self-hosted organizational knowledge base, edit wiki pages through drafts for review, and review pending edits as an editor.
Runs your implementation plan from a terminal without you watching each step. Each task gets a fresh Claude Code or codex session, then the work is reviewed and committed, so long features stay sharp instead of degrading as context fills up.
A Claude Code plugin with skills for API design safety, proxy and WAF keyword matching, async task patterns for long-running jobs, Bash style, and modular code quality review. It is meant as a maintainable AI collaboration configuration, not a prompt collection.
An enterprise platform for managing AI resources through a unified AI gateway and token scheduling. It covers models such as OpenAI, Azure, Claude and DeepSeek, plus cost attribution, budget control and centralized MCP tool registration.
An HTTP and REST based Redis client for TypeScript, built on the Upstash REST API. It suits serverless functions such as AWS Lambda, where persistent connections are impractical.
Multi-agent AI analysis for China A-share stocks. Specialized agents cover technical, sentiment, capital flow and macro factors, debate bull and bear cases, and produce structured trading advice with risk assessment. Accepts stock codes or Chinese names.
Skills for Claude Code that help add custom domains with automatic SSL, error tracking, Node.js SDK access, React analytics, and session recording to apps deployed on Temps, a self-hosted platform.
Turns a software change into a guided pipeline of written steps: a change proposal, a technical design comparing options, test-driven development, and architecture decision records. Each stage leaves an auditable document, so AI-assisted coding follows a repeatable process you can review.
Agentic Skills for Azure Development Supercharge your AI coding assistant with curated, production-ready skills for Microsoft Azure.
Lets Claude Code validate FOFA search syntax, query and profile internet assets, and export bounded results. Scan plans are generated first and run through Nuclei only after one-time human approval of targets, templates and severity.
An open source AI application development guide for backend, frontend, testing and architecture engineers, covering LLMs, agents, RAG, MCP, prompts, evaluation and Claude Code. It also includes skills for drawing draw.io diagrams and applying Java and Spring Boot coding standards.
Skills for operating the Pilot daemon, which turns tickets into pull requests, along with a branch audit tool for safe local git branch cleanup and debugging help for stuck executor runs.
An agent harness and toolkit for building AI agents and agentic applications, with a CLI and SDKs. It supports sub-agent spawning, MCP integration, session memory and human-in-the-loop control.
High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.
A set of Claude Code skills for operating Kurtosis, covering cleaning up enclaves, switching between Docker and Kubernetes backends, managing contexts, building the CLI locally, and debugging Docker engine and service issues.
Persistent long-term memory for AI agents, shared across a fleet under access control. Agents recall prior decisions at the start of a task, with trust tiers, audit trails, and a knowledge graph.
Refines product specification documents by having multiple LLMs such as GPT, Gemini and Grok debate the draft until they reach consensus. Useful when a single model would miss gaps in a spec.
Persistent, governed long-term memory for AI agent fleets, shared across agents under access control, with audit trails and a knowledge graph. Agents recall prior decisions at the start of tasks and reuse what earlier work established.
An MCP server that gives Claude Code and other AI agents persistent memory, with fact retrieval, checkpointing and memory consolidation to help cut token use.
Gives coding agents ready-made skills for generating SVG algorithmic art, optimizing code performance with benchmarks, uploading and downloading files to TOS object storage, managing AgentKit skill hubs, and building text-to-video workflows.
A tutorial and reference for building AI agents with LangGraph, covering ReAct agents, state graphs, tool integrations, retrieval patterns, and human in the loop workflows.
A Chinese-language bidding assistant for Claude Code that interprets tender documents, generates bid text, checks bids for compliance, and formats the final Word document.
Vigil is an open source, agentic AI SOC released under Apache 2.0. Your playbooks are plain-text Markdown files, your agent logic is readable code, and your integrations use an open standard (MCP). It is a capability you own, not a black box you rent.
Coordinates multiple Claude Code agents to run tasks in parallel, with automated quality gates, a simulated expert board for major decisions, and planning and code-review workflows. Aimed at developers building larger multi-step projects.
Gives AI coding agents like Claude Code and Cursor your team's shared engineering rules and architecture context, so they stop guessing from a few open files. The instructions are versioned in Git and can run inside your own perimeter.
Gives Claude Code access to a Buddhist digital text platform for searching scripture and commentary across Chinese, Pali and Tibetan canons. Its sutra-commentary skill compares how classical commentators explained a passage.
Gives Claude Code and Codex the Spring Boot conventions your project uses, such as constructor injection, your own response wrapper and exception hierarchy, and Flyway migrations. The agent reads them before it writes code, so it stops inventing patterns that do not fit your app.
Makes Claude's replies terse to cut token use, with skills for short commit messages, one-line PR review comments, compressing memory files like CLAUDE.md, and delegating to small subagents. Japanese and English supported.
A red team skill for authorized penetration testing that works through hypothesis-driven attack techniques, loading one focused technique file at a time. For security professionals running sanctioned offensive assessments.
23 Components of the Claude Code Architecture.
A plugin of agent skills for Claude Code covering Anki via AnkiConnect, Mermaid diagram rendering, Context7 library documentation lookup, GitHub Copilot SDK work, and the gog CLI for Google Workspace.
An autonomous, looping, multi-altitude security vulnerability hunt for a codebase, packaged as a Claude Code skill.
An autonomous work mode that lets Claude Code keep working while you are away. It runs a pre-flight risk check, asks approval before dangerous operations, and applies a framework for handling blockers. Start it with /nonstop.
A plugin for Claude Code that gives coding agents Symfony expertise, covering API Platform resources, DTO mapping, filters, security and serialization for REST and GraphQL APIs.
Lets you query, browse and explore data in PostgreSQL, MySQL, MariaDB, Oracle, SQLite and Redis from one desktop editor. Adds skills for database tuning and schema design.
Website: Hosted Hub: Detailed reference: docs/reference.md ไธญๆ็ๆฌ: README.zh.md Git for the AI era. Mainline lets agents save developer intent and decisions to Git alongside the code. Git already records the history of the code.
Diagrams that move. A Claude skill for animated technical diagrams, from plain English or Mermaid, as one self-contained HTML/SVG file.
Helps Claude write and review Frappe and ERPNext code by bundling skills for architecture, debugging, migrations, validation and turning vague requests into concrete tasks. Aimed at developers working on Frappe apps who want fewer errors and less time lost to log reading.
Context-efficient development knowledge via progressive skill discovery.
Gets a second opinion on plans, code and designs from other AI models such as GPT, Gemini and Grok, so you can compare their verdicts before you act. Works in Claude Code and other coding agents, with local and OpenRouter models also available.
Delegate development tsk tasks to YOLO mode AI agents running in sandbox containers. tsk auto-detects your toolchain and builds container images for you, so most projects require very little setup.
A Claude Code plugin that maintains FILETREE.md, a one-line description per file with content hashes for staleness detection. Lets the LLM grasp repo layout in a few hundred tokens before touching code.
Writes git commit messages that record intent, decisions, and constraints alongside code changes, extending Conventional Commits. Includes a recall skill that rebuilds development context from those commits at session start or when resuming work.
A comprehensive technical diagramming toolkit for solutions architects, presales engineers, and developers. Generate professional diagrams for proposals, documentation, and architecture reviews. Professional architecture diagram generated in seconds.
Orchestrate Claude Code sessions as managed background processes from any OpenClaw channel.
Communication for AI agents. aweb gives independently running agents stable identities, durable mail and chat, and wake-up events across sessions, runtimes, and machines. Agents can use it through the aw CLI, HTTP API, MCP tools, or event stream.
Claude Lane Stack is a self-hosted toolkit for coordinating coding agents through CLI processes, task contracts, Git workspaces, and verification receipts (bin/run-controller:117-159, schemas/task-v2.schema.json:1-60).
Private distribution for Agent Skills. Publish once; install, update, and roll back across Cursor, Claude Code, Codex, OpenClaw, and similar assistants, one small server, one CLI (skb).
Essential skills for teams and developers building software with best engineering practices and 10x productivity. Compatible with AdaL CLI, the automation-first agent harness, and Claude Code.
Blog posts: Building /deep-plan - The story behind this plugin The Deep Trilogy - How the three plugins work together What I Learned - Technical lessons from plugin development /deep-plan transforms vague feature requests into detailed, production-ready.
Gives Claude Code tools and guidance for building interactive Python desktop, web, and notebook UIs with native webview rendering, Plotly and TradingView charts, grids, and chat widgets, instead of Flask, Streamlit, Dash, or Electron.
Coordinates a team of Claude Code agents that plan, build, and review code changes, producing a reviewed pull request from a plain description of the task. Includes context auditing and validation rubric skills.
Gives your AI coding agent memory that carries decisions, fixes and project context across sessions, so you do not re-explain a project each time. Works with Claude Code and Codex, runs locally by default, and lets you inspect what was recalled.
Keeps the specs, decisions, rules and plans of a repo in Git and feeds the right project context to your coding agent, so it stops guessing and changes code that fits your architecture and past choices. Plan before you build, document as you go, and review a branch against its records before merge.
Takes a rough idea and walks it through specs, task planning, test-driven coding and review until it lands as committed code on its own branch. Also traces runtime bugs back to missing requirements so the gaps get fixed in the spec.
Stops an AI coding assistant from charging ahead on vague requests, picking the first obvious option, or making claims without checking sources. Its skills ask clarifying questions, test plans for failure, look for alternatives, verify research and review work before you rely on it.
Persistent project memory for Claude Code that loads at session start and is organized by a schema in hot and cold layers. A memory-loop skill writes structured entries after tasks, decisions, and gotchas.
Gives Claude Code memory across sessions. It pulls durable lessons such as decisions, conventions and bug fixes out of each conversation and surfaces the relevant ones next time, so you stop re-explaining your project. Everything is stored locally as plain markdown.
Gives Claude Code expert guidance for the tools in your stack, from React and Prisma to Redis and AI model APIs, so you stop looking up each SDK's patterns by hand. Install only the ones that fit your project.
A Claude Code plugin of offensive security skills, agents and commands for penetration testers. It covers API testing, network reconnaissance, cloud lateral movement, password attacks and payment security.
A Claude Code plugin set for Java developers, with skills for architecture decision records, REST API review, Clean and Hexagonal Architecture, Conventional Commits messages, and concurrency and thread-safety review.
A curated collection of Claude Code plugins for Drupal development, security, and deployment. Each plugin covers one topic, Drupal itself, DDEV, Docker, CI/CD, git workflows, and security verification, so you install only what you need.
Runs a Planner, Dev, Test, Learn workflow for feature development in Claude Code, with automatic bug-fix loops and state checkpointing so work can resume from saved progress.
A portable CLAUDE.md and documentation set for Claude Code that adds guardrails for Angular, Go, debugging, and session auditing, plus a health check for the installed kit.
Keeps planning and building apart: you argue a multi-session task in chat, then freeze the result into a file that any session can implement and have reviewed, with each finding checked before it is fixed. Built for longer work, not quick fixes.
magento-claude-skills is a free, open-source Claude Code plugin that gives Claude (and the Claude Agent SDK) expert, current knowledge of Magento 2, Mage-OS, and Adobe Commerce development.
Keeps a project's decisions, dead ends and current state in files, so a new session picks up where the last one stopped instead of re-reading the whole codebase. Works with Claude Code and other agents that read SKILL.md files.
Archives every Claude Code session locally in a searchable SQLite store and saves durable facts into persistent memory. Adds skills to flush and review memory at session start or before clearing a conversation.