The Agent Skills Explosion: 9 Open-Source Repos Reshaping Agentic AI (2026)

Why Agent Skills Are the Hottest Layer in the Agentic AI Stack Right Now

In early September 2026, something unusual happened on GitHub Trending. For three consecutive days — September 4, 5, and 6 — the trending list was dominated not by new AI models, not by another coding agent, but by agent skills: reusable capability packages that teach AI agents how to perform specialized tasks. Anthropic’s public skills repo gained 475 stars in a single day. NVIDIA shipped a security scanner specifically for vetting skills before installation. Google launched an official skills repository at Cloud Next 2026. A startup called OpenAgentSkill raised its hand as “npm for AI Agent Skills.”

The pattern is clear: the agentic AI ecosystem has bifurcated into three distinct layers — runtimes (agents that run), skills (what agents know how to do), and meta-tools (security scanners, context managers, registries) that sit on top of both. If you are an Agentic AI Architect, an RPA developer evaluating agent-augmented automation, or an engineering leader planning your 2027 agent platform strategy, the skills layer is where the action is — and where the risk is hiding.

This roundup covers the nine most significant open-source agent skill repositories, registries, and security tools trending right now, with star counts, license details, what each actually does, and who should care.

What Exactly Are Agent Skills?

Agent skills are self-contained instruction packages — typically a folder containing a SKILL.md file plus optional scripts, templates, and resources — that an AI coding agent loads dynamically to gain specialized knowledge about a task. Think of them as the difference between a generalist developer and a domain expert: the base agent can write code, but a skill teaches it how to write a UiPath workflow, or audit a Kubernetes deployment, or generate a compliant patent disclosure document.

The format originated at Anthropic and was released as an open standard that has since been adopted by Claude Code, OpenAI Codex, Gemini CLI, Cursor, Windsurf, and dozens of other agent products. Unlike MCP servers (which expose tools — callable functions), skills expose knowledge — instructions, best practices, and decision frameworks that shape how the agent reasons about a domain.

This distinction matters for enterprise adoption. An MCP server gives an agent access to your Jira API. A skill teaches the agent your team’s sprint planning conventions, your definition-of-done checklist, and when to escalate versus auto-assign. Skills are the connective tissue between raw capability and production-grade reliability.

The Nine Repos You Need to Know

Below is a quick-reference comparison table, followed by deep dives on each project.

1. anthropics/skills — The Format Origin and Quality Bar

Stars: ~149,000 | License: Source-available | GitHub: anthropics/skills

More Read

AI Agent Control Planes: The 2026 Enterprise Governance Guide

UiPath vs Automation Anywhere vs SS&C Blue Prism: The 2026 Agentic Platform Showdown

Personal Agent Protocol (Poppy): The Complete Guide to Agentic Commerce’s Missing Identity Layer for RPA and Agentic AI Architects (2026)

This is the repository that started it all. Anthropic open-sourced their internal agent skills format — originally developed for Claude Code — and published their production skills as a reference implementation. The repo includes the ./spec/ folder containing the Agent Skills specification itself, a ./template/ for creating new skills, a skill-creator skill (a meta-skill that helps you build new skills), and the production document-generation skills (docx, pdf, pptx, xlsx) that Anthropic uses in its own products.

The skills range from creative applications (algorithmic art, canvas design) to technical tasks (MCP server generation, web app testing) to enterprise workflows (internal communications, brand guidelines). Each skill follows a consistent structure: a SKILL.md with instructions, optional scripts for complex operations, and resource files.

Why it matters for Agentic AI Architects: This isn’t just a library — it’s the specification. If you’re building skills for your organization’s agent fleet, this repo defines the format that Google, NVIDIA, and the broader ecosystem have converged on. Start here to understand the contract your skills need to fulfill.

2. google/skills — First-Party Vendor Skills at Scale

Stars: ~15,000+ | License: Apache 2.0 | GitHub: google/skills

Announced at Cloud Next 2026, Google’s official skills repository ships thirteen skills out of the gate: seven product-specific skills covering AlloyDB, BigQuery, Cloud Run, Cloud SQL, Firebase, the Gemini API, and GKE; three Well-Architected Pillar skills for Security, Reliability, and Cost Optimization; and three “recipe” skills for Google Cloud Onboarding, Authentication, and Network Observability.

The installation story is clean: npx skills install github.com/google/skills drops them into any compatible agent — Gemini CLI, Antigravity, Claude Code, Codex, or custom runtimes. Google published a behind-the-scenes blog detailing how they build, test, and scale these skills internally, which is itself a useful reference for teams building their own.

Why it matters: Google publishing vendor-specific skills under Apache 2.0 signals that the skills format has achieved the kind of cross-vendor adoption that MCP achieved for tool integration. When the two largest AI labs (Anthropic, Google) and the largest GPU vendor (NVIDIA) all ship skills in the same format within weeks of each other, the format war is effectively over. If your team uses Google Cloud, these skills are free, production-tested knowledge that your agents should already have installed.

3. NVIDIA/SkillSpector — Security Scanner for the Skills Supply Chain

Version: 2.0.0 | License: Open source | GitHub: NVIDIA/SkillSpector

This is arguably the most important project on this list, and the reason is a single statistic: 26.1 percent of skills on major marketplaces contain at least one vulnerability, and 5.2 percent show likely malicious intent. That finding comes from NVIDIA’s own research, which scanned 42,447 skills from major marketplaces and registries.

SkillSpector runs two passes. The first is static and takes seconds: an AST walk flags exec, eval, subprocess, and dynamic imports, while a taint tracker follows environment variables and file contents to network sinks. The second pass is optional and uses an LLM to read flagged code in context, drop false positives, and write human-readable explanations — achieving roughly 87% precision. The output is a 0–100 risk score, a list of findings, and recommendations.

You can point it at a directory, a zip file, a single SKILL.md, or a Git URL. It covers Claude Code, Codex, and MCP skills — essentially the full agent skills ecosystem.

Why it matters: The agent skills supply chain is following the exact trajectory of npm packages circa 2018 — rapid growth, minimal vetting, and inevitable exploitation. Security firm AIR demonstrated this in August 2026 by building a fake skill, pushing it through a popular marketplace with an Instagram ad, and reaching approximately 26,000 agents — including some on corporate accounts. Every skill security scanner tested marked it as safe. SkillSpector isn’t perfect (no scanner is), but it’s the most rigorous open-source option available, and running it before any skill installation should be a non-negotiable step in your agent governance playbook.

For teams already running UiPath Autopilot as a coding agent or deploying agents via Microsoft Agent Framework 1.0, integrating SkillSpector into your CI/CD pipeline for skill vetting is the single highest-impact security action you can take today.

4. OpenAgentSkill — npm for AI Agent Skills

Website: openagentskill.com | GitHub: Leon-Drq/openagentskill

If individual skill repos are packages, OpenAgentSkill is the registry. It positions itself as “npm for AI Agent Skills” — a central discovery, comparison, trust-scoring, and installation layer for the entire skills ecosystem. The platform indexes over 5,400 skills from multiple sources and provides a composite quality signal that factors in GitHub adoption, freshness, metadata quality, trust checks, audit signals, use-case fit, and install readiness.

OpenAgentSkill also published a remarkably transparent “State of Agent Skills 2026” report that examines what’s actually inside the registry: which records are genuine reusable skills versus documentation or wrappers, which are maintained, which declare a license, and — critically — how little real outcome evidence the ecosystem still has. That intellectual honesty is rare in a space prone to hype.

Why it matters: The npm analogy is apt in both the positive and negative sense. npm made JavaScript’s package ecosystem discoverable and installable, but it also introduced dependency hell and supply-chain attacks. OpenAgentSkill’s trust layer is an attempt to get ahead of that — every skill gets a quality score, license check, and install safety assessment before you run install. If you’re managing an enterprise agent fleet, having a registry that pre-filters is more sustainable than manually vetting GitHub repos.

5. humanlayer/skills — Community-Curated Skills Library

Trending: +442 stars/day | License: Open source | GitHub: humanlayer/skills

HumanLayer — known for their human-in-the-loop agent approval framework — has released a community skills library that complements the vendor-published repos from Anthropic and Google. Where those repos focus on their own products, HumanLayer’s collection covers cross-cutting concerns: workflow patterns, approval chains, escalation logic, and the kind of glue-logic skills that emerge from actual production agent deployments.

Why it matters: Not every skill needs to come from a Fortune 500 vendor. Some of the most valuable skills are the ones that encode your team’s operational patterns — “how we do code review,” “how we triage support tickets,” “how we handle on-call escalation.” HumanLayer’s library provides templates for exactly these patterns, and the human-in-the-loop focus aligns with the governance requirements that enterprise RPA platforms like UiPath and Automation Anywhere already enforce.

6. K-Dense-AI/scientific-agent-skills — 165 Validated Domain Skills

Trending: +1,980 stars/week | License: Open source

This repository stands out because of its specificity and rigor. It contains 165 validated agent skills covering biology, chemistry, medicine, and drug discovery — each skill designed for a specific scientific workflow: literature review, experimental design, data analysis pipelines, regulatory compliance checks, and compound interaction prediction.

The validation angle is what separates this from a generic skills dump. Each skill has been tested against real scientific workflows and includes documented accuracy benchmarks, making it one of the first skills libraries that provides genuine outcome evidence rather than just “it runs without errors.”

Why it matters: Scientific research is one of the highest-value domains for agentic AI, and also one of the most error-sensitive. If you’re in pharma, biotech, or academic research, this library is directly useful. For everyone else, it’s a template for what a serious domain-specific skills library looks like — validated, benchmarked, and documented.

7. Imbad0202/academic-research-skills — Research-to-Publish Pipeline

Trending: +496 stars/week | License: Open source

A skill set that packages the complete academic research lifecycle — from literature discovery through writing, peer-review preparation, revision, and finalization — into composable agent skills. It is specifically designed for Claude Code but portable to other skill-compatible agents.

The interesting architectural pattern here is composability: rather than one monolithic “write a research paper” skill, the pipeline is broken into discrete stages that can be chained, skipped, or replaced. This mirrors the modular composable agent architecture that Pydantic AI v2 introduced — the principle is the same whether you’re composing code-level agents or knowledge-level skills.

Why it matters: The composability pattern is the real takeaway. If you’re building enterprise skills for your RPA or agentic automation team, don’t build monolithic mega-skills. Build small, testable, chainable units — the same way you build reusable automation components in UiPath or Power Automate.

8. blader/humanizer — The Most Controversial Trending Skill

Trending: +1,208 stars/week | License: Open source

This agent skill does one thing: it strips markers of AI-generated writing from text. It gained over 1,200 stars in a single week, making it one of the fastest-rising skills on GitHub Trending.

The ethical implications are immediately obvious and worth addressing directly. While there are legitimate use cases — a professional writer using AI as a drafting assistant who wants to polish the output to match their voice, or a non-native English speaker refining translated text — the project also enables academic dishonesty and content fraud. Its viral popularity says less about the tool and more about a market gap: people want AI-assisted writing that doesn’t read like AI-assisted writing.

Why it matters for this roundup: Controversial or not, a skill gaining 1,200 stars in a week demonstrates the distribution power of the skills format. Skills that solve a genuine pain point (whether you agree with the use case or not) spread virally through the agent ecosystem in a way that standalone tools never did. This is the skills supply chain in action — and it’s exactly why security and governance tooling like SkillSpector exists.

9. qufei1993/skills-hub — The Skills Management Layer

Trending: Growing | License: Open source

As the number of available skills crosses the thousands, a new problem emerges: management. Skills Hub is a cross-platform desktop application that manages and syncs agent skills across 50+ coding tools — Claude Code, Codex, Cursor, Windsurf, Gemini CLI, and more. It provides a single pane of glass for installing, updating, removing, and auditing the skills loaded into each agent in your toolchain.

A sibling project, xingkongliang/skills-manager, tackles the same problem with a lighter footprint. The fact that two independent projects targeting skills management are trending simultaneously confirms that skills sprawl is already a pain point in production environments.

Why it matters: Enterprise teams running multiple agent products — and most do, given the fragmentation between coding agents, workflow agents, and domain-specific agents — need a way to enforce consistent skill versions, audit what’s installed, and push updates. Skills Hub is early but directionally correct. Pair it with SkillSpector for vetting and OpenAgentSkill for discovery, and you have the beginnings of a governed skills supply chain.

The Security Elephant in the Room

The agent skills ecosystem is growing faster than its security infrastructure can keep up. The numbers are sobering:

• 26.1% of skills on major marketplaces contain at least one vulnerability (NVIDIA research, August 2026).
• 5.2% show likely malicious intent — not accidental bugs, but deliberate data exfiltration or prompt injection.
• 341 malicious skills were found on ClawHub by security researchers at Koi Security, who audited all 2,857 skills on the marketplace (February 2026).
• Security firm AIR demonstrated a fake skill reaching ~26,000 agents — including corporate accounts — with every scanner marking it safe.
• Manifold Security disclosed eight security flaws across seven CLI coding agents where a repository’s Git configuration can execute arbitrary commands via the agent without an approval prompt (September 2026).

The parallel to the npm supply chain crisis is almost exact. In 2018, a malicious npm package (event-stream) compromised a Bitcoin wallet library with 2 million weekly downloads. The agent skills ecosystem is at the same inflection point — growing fast enough to be valuable, but not yet mature enough to be safe by default.

For Agentic AI Architects, the minimum viable governance stack for skills today is:

1. Vet before install — Run SkillSpector (or equivalent) on every skill before it touches your agents.
2. Pin versions — Never pull skills from main in production. Pin to a specific commit hash.
3. Audit the registry — If you use OpenAgentSkill or any registry, check the trust score, license, and maintenance status. A skill with no license declaration is a legal liability.
4. Isolate execution — Skills that include executable scripts should run in sandboxed environments, not with your agent’s full permissions.
5. Monitor behavior — Skills that phone home, exfiltrate environment variables, or dynamically import code at runtime are red flags. SkillSpector’s taint tracker catches the common patterns, but novel attacks will get through.

What This Means for the RPA and Automation Community

If you’ve spent years building reusable components in UiPath (custom activities, libraries, templates), Power Automate (solution components, custom connectors), or Automation Anywhere (packages, bot templates), the agent skills pattern should feel familiar — because it is familiar. Skills are to AI agents what reusable components are to RPA platforms: encapsulated domain knowledge that makes the next deployment faster and more reliable.

The difference is scope and portability. A UiPath custom activity works in UiPath. An agent skill works in Claude Code, Codex, Gemini CLI, Cursor, and any MCP-compatible agent. The A2A protocol joining MCP at the Agentic AI Foundation further accelerates this convergence — skills that encode your organization’s process knowledge become portable across the entire agent ecosystem.

For RPA teams evaluating the transition to agentic architectures, the actionable insight is this: start building skills now, even before your agent strategy is finalized. The skills you build today — encoding your team’s domain expertise in invoice processing, compliance checks, customer onboarding, data reconciliation — will be usable across whatever agent platform you adopt. The format is standardized. The portability is real. The knowledge is yours.

FAQ

What is the difference between an agent skill and an MCP server?

An MCP server exposes tools — callable functions that let an agent interact with external systems (APIs, databases, file systems). A skill exposes knowledge — instructions, decision frameworks, and best practices that shape how an agent reasons about a domain. In practice, they work together: a skill might tell an agent how to design a BigQuery schema, while an MCP server gives it the ability to execute queries against BigQuery.

Are agent skills safe to install from public repositories?

Not by default. NVIDIA’s research found that 26.1% of skills on major marketplaces contain vulnerabilities and 5.2% show malicious intent. Always run a security scanner like SkillSpector before installing any skill, pin to specific versions, and audit the skill’s code — especially any executable scripts.

Can I use agent skills with UiPath, Automation Anywhere, or Power Automate?

Agent skills work directly with AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, etc.) and any MCP-compatible runtime. They don’t natively integrate with traditional RPA platforms, but they can be used alongside them — for example, using a skill-equipped coding agent to generate UiPath workflows, write Power Automate flows, or scaffold Automation Anywhere bot code.

How do I create my own agent skill?

Start with the template in anthropics/skills. A minimal skill is a folder containing a SKILL.md file with structured instructions. For more complex skills, add scripts, resource files, and sub-skills. The skill-creator meta-skill in the same repo can bootstrap new skills interactively.

Which agent skills registry should I use?

OpenAgentSkill is the most comprehensive registry with trust scoring and quality signals. For vendor-specific skills, go directly to the source: anthropics/skills for Anthropic’s production skills, google/skills for Google Cloud and Workspace. For security vetting, always run NVIDIA’s SkillSpector regardless of which registry you discover skills through.

Key Takeaways

• The agent skills ecosystem has emerged as the fastest-growing layer in the agentic AI stack, with multiple repos trending simultaneously on GitHub in September 2026.
• Anthropic, Google, and NVIDIA all shipping skills-related repos in the same format confirms the Agent Skills specification as a de facto standard — the format war is over.
• Security is the critical gap: 26.1% of skills contain vulnerabilities, and proven attacks have bypassed every existing scanner. Run NVIDIA SkillSpector before any installation.
• Domain-specific skills (scientific, academic, enterprise workflows) are where the highest production value lies — general-purpose skills are table stakes.
• For RPA teams: agent skills are the cross-platform equivalent of reusable automation components. Start encoding your domain knowledge as skills now — the format is standardized and portable.
• The “npm for skills” infrastructure (registries, managers, security scanners) is forming in real time. Early adopters who establish governed skills pipelines will have a structural advantage.

References

1. Anthropic, “Public repository for Agent Skills,” GitHub, 2025-2026. github.com/anthropics/skills
2. Google Cloud Blog, “Level Up Your Agents: Announcing Google’s Official Skills Repository,” Cloud Next 2026. cloud.google.com
3. NVIDIA, “SkillSpector: Security scanner for AI agent skills,” GitHub, 2026. github.com/nvidia/skillspector
4. Help Net Security, “SkillSpector: NVIDIA’s open-source security scanner for AI agent skills,” August 2026. helpnetsecurity.com
5. OpenAgentSkill, “State of Agent Skills 2026,” 2026. openagentskill.com
6. StartupCorners, “GitHub Trending September 4-6, 2026: AI Agents Dominate,” September 2026. startupcorners.com
7. Socket, “How AI Agents Expand the Software Supply Chain Attack Surface,” 2026. socket.dev
8. PurpleBox, “AI Agent Skills: The New Supply Chain Risk,” 2026. prplbx.com
9. InfoQ, “The Open-Sourcing of DeepSeek Harness Opens the Door to Modular, Unbundled AI Agent Infrastructure,” August 2026. infoq.com
10. The Hacker News, “Why Agentic AI Is Security’s Next Blind Spot,” May 2026. thehackernews.com