explainx / blog
Google open-sourced Agent Skills for Google products on GitHub—install with npx skills add, Apache 2.0, bundles for Gemini API, BigQuery, Cloud Run, Firebase, GKE, and Well-Architected tracks. Field summary plus how it fits next to Chrome Skills.
Jul 11, 2026
@OfficialLoganK rolls out pretty URLs for AI Studio deployed apps — free subdomains, free deploys, code stays private. explainx.ai breaks down the launch.
Jul 3, 2026
Google renamed much of its enterprise AI stack in 2025–2026, and the exam guide lags behind. Here is the definitive old-name → new-name mapping, with the traps each rename creates.
Jul 3, 2026
A non-technical, business-level Google Cloud certification: 50–60 questions in four weighted domains, six business scenario frames, $99 per attempt, 3-year validity. Here is the competency map, the Gemini Enterprise naming maze, common traps—and our mock test bank.
Google’s google/skills repository is a vendor-maintained drop-in for teams that want coding agents to follow Google-flavored playbooks: Gemini, Google Cloud primitives, and Well-Architected guardrails—without rewriting the same onboarding docs in every repo.
This post is a field summary: what’s in the box, how installation works, license posture, and how it sits next to other “skills” terminology across Google’s product surface.
Primary source: github.com/google/skills
| Topic | Detail |
|---|---|
| What | Agent Skills for Google products and technologies (heavy Google Cloud emphasis) |
| License | Apache 2.0 |
| Install | npx skills add google/skills (per upstream README; interactive skill selection) |
| Status | Active development—expect churn |
| Signals | The repo had on the order of 5.5k stars and 374 forks in public listings around launch visibility—verify live numbers on GitHub |
Most enterprises already standardize on Google Cloud for data, compute, and identity. The hard part in agent-assisted development is not “can the model write Terraform-ish YAML”—it is whether procedures match internal best practice (networking, security baselines, cost patterns).
A skills monorepo from the vendor compresses that work into reusable agent context: onboarding recipes, service “basics,” and framework-aligned checklists that stay closer to what Google documents than ad-hoc chat instructions.
The README enumerates these packages (names may evolve—check the repo):
That mix is deliberately breadth-first: core managed services plus cross-cutting “how we expect you to operate GCP” material.
Upstream documents installation through the skills CLI:
npx skills add google/skills
Practical guidance:
Google also ships Skills in Chrome—saved Gemini prompts for browser workflows. That is not the same artifact as google/skills on GitHub.
| Layer | google/skills (GitHub) | Skills in Chrome |
|---|---|---|
| Audience | Developers using coding agents | General browser users |
| Artifact | Installable skill packages | Saved prompts |
| Runtime | Agent tooling / IDE / CLI | Gemini in Chrome |
We compared the Chrome feature in Skills in Chrome—worth reading if your team is confused by shared naming.
For the cross-tool mental model (metadata, progressive disclosure, MCP pairing), start with What are agent skills?.
For discovery beyond Google:
google/skills is Google’s open, Apache-licensed contribution to the agent skills pattern: packaged operational knowledge for Gemini and Google Cloud that installs with npx skills add google/skills. It complements—not replaces—your org’s security review, MCP integrations, and internal standards.
If you standardize agents across vendors, keep vendor skills (Google) and community skills (explainx.ai registry) in separate namespaces so updates and trust boundaries stay clear.
Repository stats and the exact skill list can change; always verify on GitHub. explainx.ai is not affiliated with Google.