GenAI PMskills.sh
A marketplace for agent skills, indicating a growing ecosystem of reusable capabilities for AI agents. For AI PMs, it signals an emerging distribution layer for agent behaviors and automations.
Key Highlights
- skills.sh emerged as a fast-growing marketplace for reusable AI agent capabilities, scaling from 20,000 to 40,000+ skills within weeks.
- The platform signals an emerging distribution layer for agent behaviors, where teams can source and adapt modular capabilities instead of building everything from scratch.
- Newsletter coverage tied skills.sh closely to Vercel and v0, emphasizing Git-native workflows with branches, sandboxes, previews, and pull requests.
- For AI PMs, the key product questions are discoverability, trust, governance, and when to buy, adapt, or build agent functionality.
- Rapid submission volume—reported at hundreds of new skills per hour—highlights both ecosystem momentum and the need for strong curation systems.
Overview
skills.sh is a marketplace for reusable AI agent skills: installable capabilities, automations, and behaviors that can be shared across agents and workflows. Based on newsletter coverage, it emerged as a fast-growing hub in the Vercel ecosystem, with community contributions scaling from tens of thousands of listed skills to hundreds of new submissions per hour in early 2026.
For AI Product Managers, skills.sh matters because it suggests a new distribution layer for agent functionality. Instead of treating every agent behavior as custom-built product logic, teams can increasingly source, test, adapt, and deploy modular skills from an ecosystem. That has implications for product velocity, integration strategy, quality control, discoverability, and governance. It also signals a shift toward Git-native, marketplace-driven agent development, where reusable capabilities can move from prototype to production through branches, sandboxes, previews, and pull requests.
Key Developments
- 2026-01-25 — skills.sh was reported to have reached 20,000 agent skills, highlighting rapid ecosystem growth and rising interest in reusable agent capabilities.
- 2026-01-28 — Guillermo Rauch reported that skills.sh was adding 550+ skills per hour. The v1.1.1 release also brought enhanced CLI tools and improved search/discoverability, including command patterns such as `reforge@shell` to explore capabilities.
- 2026-02-04 — skills.sh, described as a Vercel-hosted hub built entirely in v0/VZero, surpassed 34,000 community-submitted AI skills and was receiving up to 500 new submissions per hour. Coverage emphasized a Git-centric workflow: one-click branch creation, sandboxed VS Code environments, dependency installation, preview deployments, and auto-generated PRs.
- 2026-02-05 — In a live How I AI episode in San Francisco, Guillermo Rauch demonstrated v0 by Vercel and noted that skills.sh had grown to 40,000+ installable AI skills. The demo framed skills.sh as part of a broader code-to-production pipeline powered by Git repositories and pull requests.
Relevance to AI PMs
- Evaluate marketplace vs. in-house capability strategy. skills.sh is a useful signal that agent behaviors may become modular and externally sourced. AI PMs can assess which capabilities should be built internally versus assembled from reusable skills to reduce time-to-value.
- Design for discoverability, trust, and governance. A marketplace with tens of thousands of skills creates product problems around ranking, quality assurance, compatibility, provenance, and safety. PMs building agent platforms should think about metadata, review systems, evals, permissioning, and lifecycle management.
- Operationalize faster iteration loops. The reported workflow around branches, sandboxes, previews, and PRs points to a practical model for shipping agent features. PMs can use this pattern to shorten experimentation cycles, standardize contribution flows, and connect prototyping directly to production deployment.
Related
- v0 — Vercel’s AI-driven development environment featured prominently in demos tied to skills.sh; it appears to be a key creation and iteration layer for building and publishing skills.
- Vercel — The hosting and platform layer behind the marketplace, positioning skills.sh within a broader ecosystem of deployment, previews, and Git-based workflows.
- Guillermo Rauch — Vercel’s CEO and the most visible public source for growth updates, demos, and framing around skills.sh’s product direction.
- dzero — Related by association in the source graph; likely adjacent to the same emerging workflow or product ecosystem around agent creation and deployment.
- v111 — Referenced in connection with release evolution, likely tied to versioning and product updates around the skills ecosystem.
- agent-skills — A directly related concept/entity representing the broader category of reusable agent capabilities that skills.sh helps package, distribute, and discover.
Newsletter Mentions (4)
“How I AI episode in SF featuring Guillermo Rauch demonstrating v0 by Vercel, which spun up skills.sh hosting 40k+ installable AI skills and introduced a code→production pipeline powered by git repos and PRs.”
#1 in Claire Vo recorded the first live How I AI episode in SF featuring Guillermo Rauch demonstrating v0 by Vercel, which spun up skills.sh hosting 40k+ installable AI skills and introduced a code→production pipeline powered by git repos and PRs.
“skills.sh, a Vercel-hosted hub built entirely in VZero, now contains over 34 000 community-submitted AI skills and is receiving up to 500 new skill submissions per hour.”
#8 ▶️ “Anyone can cook”: How v0 is bringing git workflows to vibe-coding | Guillermo Rauch (Vercel CEO) How I AI Podcast Guillermo Rauch demonstrates how VZero, Vercel’s AI-driven IDE, makes full Git workflows—branch creation, VS Code sandboxed dev environment, preview deployments and PR generation—first-class for evolving skills.sh from prototype to production. skills.sh, a Vercel-hosted hub built entirely in VZero, now contains over 34 000 community-submitted AI skills and is receiving up to 500 new skill submissions per hour. In VZero a single button click creates a branch named “project/feature” (e.g. v0/rouchg), spins up a sandbox VM with Next.js dev server and full VS Code editor, auto-installs dependencies, and auto-generates a PR with an instant production-grade preview on Vercel’s CDN.
“As reported by Guillermo Rauch , skills.sh is now adding over 550 skills every hour.”
From LinkedIn • Deeper Insights AI Product Launches & Updates As reported by Guillermo Rauch , skills.sh is now adding over 550 skills every hour. The latest v1.1.1 release (vercel.fyi/skills-v1.1.1) brings enhanced CLI tools and improved search and discoverability, with users able to run commands like ‘reforge@shell’ to explore new capabilities.
“Skills.sh marketplace hits 20,000 agent skills”
GenAI PM Daily January 25, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's curated insights on AI product management from X, LinkedIn, and YouTube. Skills.sh marketplace hits 20,000 agent skills From X AI Product Launches & Updates Qwen3-TTS update with streaming, voice design & Instruct-style control : Qwen @Alibaba_Qwen announced streaming inference support in collaboration with vLLM , explained using Voice Design plus the Base model’s clone feature for consistent voice tone , and confirmed the upcoming 25Hz open-source model will enable Instruct-style control . Vercel AI Dashboard powered by Opus 4.5, Sandbox & Gateway : Guillermo Rauch @rauchg highlighted that the new dashboard’s “Jarvis of data” enables querying product and business metrics (e.g., “How many users opted in…?”) using Opus 4.5 , Sandbox , and Gateway , emphasizing there’s “ no going back .” AI Tools & Applications Context engineering for long-horizon agents podcast : Harrison Chase @hwchase17 hosted a discussion with Sonya and Grady on agent harnesses , coding agents , and using traces as a source of truth to build robust, long-horizon agents . Claude Code vs. Claude Cowork use cases : George from 🕹prodmgmt.world @nurijanian contrasted Claude Code for multi-file debugging and refactoring with Claude Cowork for admin tasks like PDF form filling, DOCX editing, and file management. Streamlined agent tooling by removing 80% of tools : Guillermo Rauch @rauchg pointed to a Vercel blog post detailing how they removed 80% of agent tools to streamline and focus their agent tooling . Product Management Insights & Strategies AI-powered interview practice with ChatGPT : George from 🕹prodmgmt.world @nurijanian outlined using ChatGPT as a mock interviewer to practice product design questions, set timers, and get feedback on user segmentation , success metrics , technical constraints , and prioritization . Compounding productivity with portable scripts & workflows : George from 🕹prodmgmt.world @nurijanian suggested encapsulating skills in scripts and workflows using markdown and custom tools so you can contribute immediately at new roles instead of starting from scratch. Aligning prioritization frameworks to uncertainty : George from 🕹prodmgmt.world @nurijanian advised choosing RICE , ICE , Opportunity Solution Trees , or WSJF based on data maturity , stage , and risk type , noting most issues stem from clarity rather than the framework itself . AI Industry Developments & News Skills.sh marketplace hits 20,000 agent skills : Guillermo Rauch @rauchg updated that the skills.sh marketplace now hosts 20,000 agent skills , underscoring rapid ecosystem expansion. AI talent move to Google DeepMind : Logan Kilpatrick @OfficialLoganK welcomed Alan Cowen following his move from Hume AI to Google DeepMind , highlighting ongoing voice AI advancements and infrastructure sharing. From LinkedIn • Deeper Insights AI Tools & Applications Rapid prototyping with Google AI Studio: Peter Yang sat down with Google AI Studio PM lead Logan Kilpatrick to uncover a clever prototyping hack: instead of building multiple prototypes, ask the AI to embed a toggle button that flips between five or six design variations in a single UI. This approach streamlines iterations and makes the PM workflow more engaging. End-to-end deployments with AI coding agents on Render: Tal Raviv highlights how Render, billed as “what Heroku was supposed to be for coding agents,” lets PMs delegate both code fixes and deployment tasks to an AI agent. By defining stack and infra in a single configuration file and linking GitHub, the agent handles outages, testing, and communication—mirroring the roles of dev and ops teams. Product Management Insights & Strategies Bringing rigor to AI agent prompts with Intent Engineering: Karthick Nethaji Kaleeswaran shares Pawel Huryn’s Intent Engineering framework, which treats AI agent capabilities like feature specs—defining clear constraints, decision autonomy, and success criteria. This shift from “vague prompting” to structured intent definitions helps teams avoid unpredictable agent behavior and align AI actions with product goals. Staying on the cutting edge and addressing governance gaps: Henry Finkelstein lists top resources—Dan Shipper, Every Inc., and livecasts featuring recursive Git workflows and cloud-based agent flows—that have boosted his personal productivity. He also calls out persistent gaps in governance, evaluation, and alignment when scaling from solo AI “agents” to team-based implementations, urging PMs to build robust oversight and collaboration frameworks.
Related
The founder of Vercel, cited for arguing that the CLI is the core interface for coding agents. Relevant to AI PMs for platform strategy and agent UX.
A developer platform company behind Sandbox at Vercel. Relevant to AI PMs because it is positioning infrastructure for agentic workflows and automation.
An AI app-building tool referenced here as highlighting a prompt directory for faster shipping. Relevant to PMs exploring rapid prototyping and app creation workflows.
Reusable capabilities or task-specific skills added to AI agents to extend what they can do. Here they are mentioned as part of Claude's healthcare and life sciences expansion.
Stay updated on skills.sh
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free