{"slug": "state-of-agent-skills", "title": "State of agent skills", "summary": "The skills.sh registry reached one million agent skills and nearly 280 million installs in seven months, according to an analysis of aggregate registry data, after Anthropic introduced Agent Skills in October 2025 and Vercel launched the skills.sh registry three months later. Software engineering accounts for about a quarter of listings but 18% of installs, while business operations skills draw 74% more installs per listing than average, writing and documents 50% more, and cloud and infrastructure 42% more. The report attributes the growth to skills being faster to create than conventional software, noting GitHub took 27 months, the App Store just over five years, and npm more than nine years to reach one million repositories, apps, and packages respectively.", "body_md": "In seven months, the [skills.sh](https://www.skills.sh/) registry grew to one million agent skills and recorded nearly 280 million installs.\n\nA skill gives an AI agent reusable instructions for a particular job. Agents are capable but generic; they can do many jobs, but they don't know how a specific person, team, or company does them. A skill supplies that missing context and can be as simple as a file written in ordinary language.\n\nAnthropic introduced [Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) in October 2025, and Vercel launched the [skills.sh](http://skills.sh) registry three months later.\n\nUsing aggregate data from the registry, this report follows a new market through its first million skills: what people teach agents, what gets installed, and where the value is heading.\n\nTo write a skill, some of the judgment behind a job has to be made explicit, like the steps to follow, what good looks like, and how to evaluate the result. The agent and its tools already supply much of the underlying capability, so the skill only has to provide the judgment and instructions specific to a job.\n\nThis makes skills faster and easier to create than conventional software.\n\nskills.sh reached one million skills in seven months. GitHub took 27 months to reach one million repositories. Apple's App Store took just over five years to get to one million apps. npm took more than nine years to reach one million packages.\n\nFar more people can describe how work should be done than program a computer to do it. And once a skill is written, it can be distributed and installed without being rewritten for each agent. Skills pair a much larger pool of creators with software’s capacity for reuse, driving the explosive growth of the ecosystem.\n\nWe classified the registry's most-installed skills by the kind of work they help agents do. Together, these skills account for more than four-fifths of all installs. Published listings show supply: what authors have made available to agents. Installs show demand: what people want their agents to learn.\n\nSupply leans technical. More than half of listings teach software engineering, agent workflows, data, infrastructure, or security, with software engineering alone accounting for about a quarter.\n\nDemand is more distributed. No category draws more than a fifth of installs. Software engineering remains the largest at 18%, followed by agent workflows at 15%, then business operations and writing at nearly 11% each.\n\nTo see how each category performs for its size, we also compared its installs per listing with the average.\n\nBusiness operations, writing and documents, and cloud and infrastructure get the most installs per listing. Demand for that work is split across fewer skills, so each one carries more of it. The average business operations skill draws 74% more installs than the average, writing and documents 50% more, cloud and infrastructure 42% more.\n\nSoftware engineering, education and productivity, and research run the opposite way. The average software engineering skill draws about 30% fewer installs than average, education and productivity 39% fewer, research 55% fewer.\n\nTo write a skill, you need to understand a job. To install one, you need only want the job done. Most skills are technical because they began in developer tools. Installs cover a much broader range of work because agents are useful in every part of a company.\n\nAgent workflows and automation account for 14.8% of installs in the classified dataset, second only to software engineering. Among listings with at least 100,000 installs, agent workflows are the largest category.\n\nAgent workflow and automation skills teach agents how to plan, route work, use tools, and automate browsers, abilities that apply across many jobs. A contract-review skill applies to contracts, but a planning skill applies to any job the agent takes on, contracts included.\n\nPeople are using agents to improve agents. And because agents also help write skills, the catalog grows by improving the very machinery used to build it.\n\nInstall activity is highly concentrated. Nearly half of all skills were installed exactly once. At the other end, 375 skills, or 0.04% of the registry, account for 62% of installs, and the top 1.2% account for 94% of installs.\n\nFor all that concentration, there's no single winner. Even the most-installed skill accounts for less than 1% of all installs.\n\nSkills compete within jobs and accumulate across them. Once a team chooses an expense-report skill, it has little reason to install another expense-report skill. But it can use that skill alongside others for spreadsheets, research, and presentations. Each job crowns its own winner, and the winners together carry most of the installs.\n\nWe also classified each skill by whether its work was shared across industries or specific to one. Tasks such as cleaning up a spreadsheet or deploying a website recur at banks and hospitals, law firms and restaurants. These cross-industry skills account for 66% of classified skills and 87.5% of installs. On average, they receive 3.6 times as many installs per listing as industry-specific skills.\n\nThe advantage is portability, whether a skill reaches across jobs, like agent workflows, or across industries. The skills installed most are the ones the most people can use.\n\nThe first million skills taught agents what everyone knows. The next million will teach your agents what only you know.\n\nPublic skills and better models are making general expertise available to every team, which will turn it into the baseline rather than any kind of advantage. More of the differentiating value will move to company-specific judgment. For example, when a customer gets a refund or what can ship without another review.\n\nThe measure of a skill will also shift from popularity to effectiveness. Today, the best signal of a skill's quality is its install count. As models improve, the bar rises, because a skill justifies itself only if the agent does the job better with it than without it. Skills will get tests and benchmarks that measure exactly that.\n\nThe first generation of skills turned expertise into software. The next generation will see the public catalog continue to grow as supply catches up to demand. And organizations will build on top of it, writing down the knowledge only they have and maintaining it the same way they now maintain code.\n\nExplore the first million, or add to the next, at [skills.sh](http://skills.sh/).\n\nThis report uses aggregate [skills.sh](http://skills.sh/) data. A few notes on measurement:\n\nCatalog totals count unique registry listings.\n\nInstall figures use aggregate registry counters. They do not represent unique people or necessarily independent choices.\n\nFunction and industry findings describe a classified sample rather than the full catalog.\n\nEach analysis uses the latest complete data available. Figures may be revised as the underlying data and methodology improve.", "url": "https://wpnews.pro/news/state-of-agent-skills", "canonical_source": "https://vercel.com/blog/state-of-agent-skills", "published_at": "2026-09-25 06:00:00+00:00", "updated_at": "2026-09-25 17:03:12.536225+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-products", "artificial-intelligence"], "entities": ["Anthropic", "Vercel", "Agent Skills", "GitHub", "Apple App Store", "npm"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/state-of-agent-skills", "markdown": "https://wpnews.pro/news/state-of-agent-skills.md", "text": "https://wpnews.pro/news/state-of-agent-skills.txt", "jsonld": "https://wpnews.pro/news/state-of-agent-skills.jsonld"}}