I built Skill Flow — manage and deploy AI coding skills across every major agent
Hey there, little explorer! 🚀
Imagine you have many robot friends, like a drawing robot, a building robot, and a singing robot! Each robot needs special little tools to do its job, right? Like a crayon for the drawing robot, or blocks for the building robot.
Sometimes, a grown-up has to put the same tool in each robot's hand, one by one. That's a lot of work! 😩
But now, a clever person made a magic toolbox called "Skill Flow"! ✨ You put the tool in the magic toolbox once. Then, the toolbox knows exactly which robot needs which tool, and it gives it to all your robot friends super fast! It even remembers which tools they have and if they need new, shiny ones!
So, all your robot friends can play and work together easily! Yay! 🎉
<p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fzff1vukid600uejgom2a.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fzff1vukid600uejgom2a.png" alt=" " width="800" height="574"></a></p> <p>I got tired of installing skills one by one across Claude Code, Cursor, Copilot, and whatever new agent showed up next.</p> <p>The real problem isn't installation — it's that there's no coherent way to manage them:</p> <ul> <li>Skill repos are grouped by design, but you install them separately</li> <li>
I got tired of installing skills one by one across Claude Code, Cursor, Copilot, and whatever new agent showed up next.
The real problem isn't installation — it's that there's no coherent way to manage them:
-
Skill repos are grouped by design, but you install them separately
-
Every agent expects files in a different location
-
Updates drift silently
-
Nobody tracks what's actually deployed
So I built skill-flow.
What it does
Import a skill source once — from GitHub, skills.sh, or a local path — and deploy to multiple agents in one step. It tracks what's installed, keeps everything in sync, and tells you when something's out of date.
Supported agents: Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Windsurf, and more.
How it works
One source stays one cohesive unit. You inspect it, select the skills you need, and deploy — without manually copying files or remembering which agent lives where.
State is explicit: a manifest.json stores your intent, a lock.json tracks what's resolved and deployed.
Try it
GitHub: skill-flow
Would love feedback — especially from anyone managing skills across more than two agents.
DEV Community
https://dev.to/vintlin/i-built-skill-flow-manage-and-deploy-ai-coding-skills-across-every-major-agent-3306Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
claudegeminiupdate
How to Build a Voice Agent With AssemblyAI
This tutorial shows you how to build a complete voice agent that can have natural conversations with users. You'll create an application that listens to speech, processes it with AI, and responds back with voice—handling the full conversation loop in real-time. Read All
Paper close reading: "Why Language Models Hallucinate"
People often talk about paper reading as a skill, but there aren’t that many examples of people walking through how they do it. Part of this is a problem of supply: it’s expensive to document one’s thought process for any significant length of time, and there’s the additional cost of probably looking quite foolish when doing so. Part of this is simply a question of demand: far more people will read a short paragraph or tweet thread summarizing a paper and offering some pithy comments, than a thousand-word post of someone’s train of thought as they look through a paper. Thankfully, I’m willing to risk looking a bit foolish, and I’m pretty unresponsive to demand at this present moment, so I’ll try and write down my thought processes as I read through as much of a a paper I can in 1-2 hours.
OpenClaw Changed How We Use AI. KiloClaw Made It Effortless to Get Started
OpenClaw is a powerful open-source AI agent, but self-hosting it is a pain. KiloClaw is OpenClaw fully hosted and managed by Kilo — sign up, connect your chat apps, and your agent is running in about a minute. No Docker, no YAML, no server babysitting. People are using it for personalized morning briefs, inbox digests, auto-building CRMs, browser automation, GitHub triage, and more. Hosting is $8/month with a 7-day free trial, inference runs through Kilo Gateway at zero markup across 500+ models, and it's free for open-source maintainers. Read All
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in AI Tools
Free MCP Server: Real-Time Crypto Data for Claude Code and Cursor
Free MCP Server: Real-Time Crypto Data for Claude Code and Cursor If you do any crypto trading, DeFi research, or blockchain development, this is useful. I built an MCP server that gives Claude Code, Cursor, and any MCP-compatible AI tool direct access to real-time cryptocurrency data — powered by CoinGecko. It is free. No API key required. What It Does Five tools: get_price Real-time prices for any token by ID or symbol. Get me the current price of ETH and BTC → ETH: $3,847.22 | BTC: $94,221.55 get_market_data Full market data: price, volume, market cap, 24h change. What is SOL market cap and 24h volume? → Market cap: $89.4B | 24h volume: $4.2B | Change: +2.3% search_tokens Search by name or symbol across 70+ tokens. Find tokens related to "layer 2" → ARB, OP, MATIC, IMX, METIS, ZK... get
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!