a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UIโฆ
11,438 subagents in 989 plugins. Each works in Claude Code and Cursor.
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UIโฆ
Analyzes how a specific topic affects a group of compiler passes. Used by the /plan-update skill to parallelize research acrossโฆ
Agent for managing AI prompts on prompts.chat - search, save, improve, and organize your prompt library.
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", orโฆ
Expert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when theโฆ
- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such asโฆ
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hardโฆ
Senior code reviewer that evaluates changes across five dimensions โ correctness, readability, architecture, security, andโฆ
Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css. Use for Phase 2โฆ
Dynamic topology switching coordinator with self-organizing swarm patterns and real-time optimization
Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.
Kubernetes-native AI automation platform for intelligent agentic sessions.
Open source platform for AI-native products. Pre-built AI agents with real tools and 1000+ integrations, in a Rust engine + Tauri desktop app. Free forever.
AI agents that triage infrastructure alerts, investigate root causes, and propose fixes, while a solo operator sleeps. For the complete technical reference, see README.extensive.md.
Private AI on a bootable USB drive. Your secure, offline-first AI assistant, carry it anywhere, leave no trace. A complete computer. In your pocket. PAI is an entire operating system, lean enough to fit on a USB stick, powerful enough to run local AI.
A Model Context Protocol server that stores, searches and serves prompt templates and agent configurations to any MCP client (Claude Desktop, Claude Code, Cursor and others), plus a script that uses those templates to orchestrate Claude CLI agents over a.
Portable, source-controlled configuration for AI coding assistants. my-ai-tools installs one consistent set of agent guidelines, skills, commands, hooks, MCP servers, and tool settings across supported AI coding assistants.
Documentation A ZoneMinder client for web, desktop, iOS, and Android. It shows live camera feeds, a montage of many cameras at once, and events on a timeline, and has an AI chat agent you can ask about your cameras.
Runs eleven specialist agents that review code, analyze issues, and verify waves, plus commit and release-note commands. Fires when you plan an issue, orchestrate a swarm of agents, or cut a release.
Make Your Ideas Real. Build Apps, Websites and AI Agents with Plain English with Astro, React, Shadcn and Cloudflare.
An operating system built for AI agents, talk to your NixOS server instead of SSH-ing in. Typed, audited tool access with atomic rollback on every change. Research-grade; run it on a disposable box, not production.
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.
Runs analyzer, comparator, and grader agents over multi-tenant agent sandboxes and task pipelines. Fires when you audit agent runs, compare backend outputs, or score task results.
Auto-invokedPlugins that fire their skills as you need them. You prompt as usual, and a Flowy hook picks the right skill, so you never have to invoke it by hand.How it works
Gives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
Walks a software change from a written spec through design, testing, code review, CI/CD, and release, applying the matching engineering skill at each stage. Useful for developers using Claude Code on full development workflows.
Turns a codebase into an interactive knowledge graph you can explore, search, and ask questions about, with skills for diff impact analysis, explanations, and business domain mapping.
Turns the sources you read, such as papers, articles and transcripts, into a linked wiki of Markdown notes in Obsidian. Claude keeps sources and citations so every summary can be traced back to its origin.
Gives you skills for pulling answers and prep from Circleback meeting notes, and for triaging failing GitHub Actions runs and GitHub issues. Use it to find what was decided, build meeting briefs, and sort CI failures and issues without digging through logs by hand.
Audits paid ad accounts across platforms such as Google, Meta, Amazon, and Apple, plus budget planning and attribution checks. Built for agencies, consultants, and in-house marketing teams using Claude Code.
A Claude Code plugin for long-running web novels that keeps settings, plot threads and outlines consistent across many chapters. It covers project setup, volume and chapter planning, writing-pattern memory, a project health check, and a read-only dashboard.
Turns a rough feature idea into a written spec through guided questions, then has the agent build it and checks the result against that spec. Instead of hand-checking whether the work is finished, you get an automatic evaluation gate that runs in your coding agent.
A research assistant plugin for Claude Code that supports literature review, paper writing, citation verification, Zotero and Obsidian integration, and code review and debugging for academic and software work.
Keeps an AI coding agent working in a loop, checking its output against tests and lint, until a task is actually finished. It also helps turn rough ideas into design documents and code task files, and it reviews pull requests.
A Claude Code plugin of skills for writing, scoring, auditing, and localizing blog posts. It covers SEO and E-E-A-T checks, site-wide audits for orphan pages and stale content, brand and voice guides, content briefs, and optional paid text-to-speech audio.
/plugin marketplace add owner/repoRun it once for the repository that lists the plugin. The listing page links that repository.
/plugin install plugin-name@marketplace-nameClaude Code opens the plugin panel on that plugin. Read it before you choose a scope, because a plugin can run hooks and MCP servers.
@agent-plugin-name:agent-namePlugin subagents load automatically and appear in the @-mention list under their scoped name. Claude can also delegate to one on its own.
No plugin needed for one subagent: save its Markdown file in ~/.claude/agents/ for every project, or in .claude/agents/ for one repository.
These steps are the pattern for a plugin listed in a marketplace. Each Flowy listing shows the install its own repository documents. A subagent loaded from a plugin ignores the hooks, mcpServers and permissionMode fields in its header.
A subagent is a specialist that Claude Code hands a task to, with its own instructions, tools and context. Custom subagents are Markdown files in .claude/agents/, and a plugin can ship several. Flowy lists each beside its plugin, so you can see the whole bundle first.
Subagent files are Markdown with a short header, so you can read one in full before it runs.
Install the plugin that ships it and it loads automatically, or copy its Markdown file into ~/.claude/agents/ or .claude/agents/. A running session may need a restart to see a newly created agents folder.
Claude can delegate a task to a subagent on its own, and you can ask for one by name with an @-mention. The description in the subagent file is what tells Claude when it fits.
A skill is instructions Claude loads into the current conversation. A subagent is a separate specialist with its own tools and context that works on a task and reports back.
By the GitHub stars of the plugin that ships the subagent, one per plugin. A subagent has no stars of its own, and the card says which plugin the number belongs to.
Not when it loads from a plugin. For security reasons Claude Code ignores the hooks, mcpServers and permissionMode fields on a plugin subagent. Copy the file into .claude/agents/ if you need them.
Save a Markdown file in .claude/agents/ for one repository, or in ~/.claude/agents/ for every project. Its header holds a name and a description, and the body is the instructions. The /agents command in Claude Code can walk you through it.
By default a subagent inherits the tools of the main conversation, including MCP tools. A tools field in its header limits it to the list you name.
Cursor documents reading subagent files from .claude/agents/, so a file saved there can be used in Cursor too. A plugin install is a Claude Code step, so copy the file instead. Flowy has not tested subagents in Cursor.
Publish it on GitHub and the crawler finds it. Or send the repository yourself.
Submit a plugin