1password
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi,โฆ
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, orโฆ
Ask which skill or flow fits your situation. A router over the skills in this repo.
Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android โ semantic ARIA roles and labels,โฆ
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commitsโฆ
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoidโฆ
Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, andโฆ
Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submitโฆ
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product โ it recommendsโฆ
Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use onโฆ
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.
Gives an OpenCode setup 45 skills for TDD, debugging, browser automation, and Python or bash scripting. Fires when you start a feature, hit a bug, or need a tool wired in.
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.
A lightweight Node.js proxy (~150 lines, zero dependencies) that wraps Anthropic API requests with the Claude Code envelope, routing billing through your Claude Code subscription instead of direct API credits.
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.
Ears for coding agents. Watch the 22 s launch film - every sound in it was made in code by earshot forge; no recordings, no music track. AI coding agents can now write the code that renders a film, a product demo or a game.
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
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
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.
A Claude Code plugin with skills for auditing a whole repo, reviewing a change, listing deferred shortcut comments, and showing measured savings and a quick command reference.
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.
Gives your AI agent the marketing know-how to plan A/B tests, write ad creative, set up analytics tracking, optimize for AI search answers, and run paid ad campaigns, so you can work through these tasks without starting from scratch.
Gives Claude Code skills for debugging and automating Chrome through DevTools, covering browser inspection, performance and LCP analysis, accessibility audits, cookie debugging, and shell scripting of browser tasks.
Gives an AI agent a persistent place to store and retrieve its memory, knowledge and skills as files it can browse, search and edit. You can open any directory to see and correct what the agent has stored, and find or update skills and kanban tasks there as well.
/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.
/plugin-name:skill-nameA skill from a plugin runs as /plugin-name:skill-name. Claude also loads a skill on its own when the task fits its description.
No plugin needed for a single skill: save its folder as ~/.claude/skills/skill-name/SKILL.md for every project, or .claude/skills/skill-name/SKILL.md 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 skill, also called an Agent Skill, is a folder with a SKILL.md file that teaches Claude Code how to do one job, such as writing a failing test first. Claude loads a skill when it fits the task, or you run it by name. This Claude skills list shows each under its plugin.
Reading a skill costs nothing and needs no account. Open any listing to read its instructions before you install.
Install the plugin that ships the skill, or copy the skill folder into ~/.claude/skills/ yourself. Each listing links the repository so you can see which of the two its authors document.
Claude loads a skill when it fits the task, or you run it by name. Whether the right one fires is not guaranteed. Flowy marks plugins that add a hook to keep routing every prompt as auto-invoked.
A plugin skill sits at skills/skill-name/SKILL.md inside the plugin and runs as /plugin-name:skill-name. A personal skill sits under ~/.claude/skills/ and a project skill under .claude/skills/.
By the GitHub stars of the plugin that ships the skill, one skill per plugin, so one popular plugin cannot fill the row. A skill has no stars of its own.
Yes. Every skill page shows the skill as written and links the repository it comes from. Nothing on Flowy needs an account to read.
Those agents, and GitHub Copilot, OpenCode and Windsurf, each document support for SKILL.md skills. Skill pages on Flowy print the install command for each of them when the source is on GitHub. A skill that leans on Claude Code features may behave differently, and Flowy has not tested skills in other agents.
Front matter with a name and a description, then Markdown instructions. The description tells Claude when the skill fits. Scripts and reference files can sit in the same folder.
They do different jobs. A skill teaches Claude a procedure in plain Markdown. An MCP server gives Claude a tool that reaches outside the conversation, such as an API. Many plugins ship both.
Publish it on GitHub and the crawler finds it. Or send the repository yourself.
Submit a plugin