GitHub organization
Agent skills by google
- skills
- 185
- official
- 185
- repositories
- 6
Repositories by google
- skillsOfficialAgent Skills for Google products and technologies21k stars · 145 skills
- adk-pythonOfficialAn open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.22k stars · 13 skills
- adk-recipesOfficialA collection of agent recipes, reference patterns, and vertical plugins built with Agent Development Kit (ADK)10k stars · 14 skills
- meridianOfficialMeridian is an MMM framework that enables advertisers to set up and run their own in-house models.1.6k stars · 5 skills
- crosvmOfficialThe Chrome OS Virtual Machine Monitor - Mirror of https://chromium.googlesource.com/crosvm/crosvm/1.3k stars · 4 skills
- heirOfficialThe compiler for homomorphic encryption929 stars · 4 skills
Skills by google, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail… | google/ | 22k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use. | google/ | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Writes a hands-on developer guide for one ADK code unit — a minimal runnable example, how it works, a configuration-option table, advanced uses, limitations, and links to related samples — to… | google/ | 22k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and… | google/ | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Skill to assist with the contribution workflow for crosvm. An agent skill from google/crosvm. | google/ | 1.3k | — | ~1.5k | Automated safety check: Pass | BSD-3-Clause | today |
| 6 | Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test… | google/ | 22k | — | ~993 | Automated safety check: Notes | Apache-2.0 | today |
| 7 | Reopens a fitted Meridian MMM from a saved file and runs budget allocation scenarios, producing an HTML report and a Python script that repeats the run. | google/ | 1.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Converts MLIR lit test files to bazel run commands. An agent skill from google/heir. | google/ | 929 | — | ~447 | Automated safety check: Pass | Apache-2.0 | today |
| 9 | Builds a retail product search agent on Google Cloud, from catalog ingestion into BigQuery and Vector Search to ADK scaffolding, evaluation and Cloud Run deployment. | google/ | 10k | — | ~3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | Manages Google Cloud Privileged Access Manager entitlements and grants: create and edit entitlements, request temporary access, and approve or deny pending grants. | google/ | 21k | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Finds and reads the right Meridian marketing-mix-modeling documentation file to answer a concept or parameter question, instead of guessing. | google/ | 1.6k | — | ~896 | Automated safety check: Pass | Apache-2.0 | today |
| 12 | Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between… | google/ | 22k | — | ~879 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Skill to assist with using the ./tools/cl tool for managing and uploading Gerrit CLs in the crosvm repository. | google/ | 1.3k | — | ~647 | Automated safety check: Pass | BSD-3-Clause | today |
| 14 | Takes a user through building a Meridian marketing mix model, from loading CSV data and mapping columns to running EDA, fitting and saving the model. | google/ | 1.6k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | Converts end-to-end (e2e) test targets or paths to bazel run commands for heir-opt. | google/ | 929 | — | ~394 | Automated safety check: Pass | Apache-2.0 | today |
| 16 | Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud. | google/ | 21k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. | google/ | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Brings a Python recipe's pyproject.toml in line with the repo's CI rules, either as a read-only dry run or by rewriting the file while keeping comments. | google/ | 10k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 19 | Skill to assist with running tests and managing test VMs in the crosvm repository. | google/ | 1.3k | — | ~847 | Automated safety check: Pass | BSD-3-Clause | today |
| 20 | Loads a saved Meridian MMM model and produces an HTML results summary, with optional health checks and approval checkpoints at each step. | google/ | 1.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 21 | Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cleans up endpoints, confirming before any change. | google/ | 21k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | today |
| 22 | Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. | google/ | 22k | — | ~837 | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Augments a bazel run CLI command for heir-opt with additional flags that dump the IR before each compiler pass, allowing the agent to inspect intermediate IR during compilation, identify a… | google/ | 929 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Generates a minimal tests/test_runnability.py for a Python agent recipe that imports the agent module and checks root_agent, adding only the mocks and env vars it needs. | google/ | 10k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 25 | Generates Scenario Planner data from a fitted Meridian marketing mix model and prepares it for a Looker Studio dashboard through a Colab handoff. | google/ | 1.6k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | Searches, manages and scaffolds skills in the Gemini Enterprise Agent Platform Skill Registry using bundled Python scripts and Google Cloud credentials. | google/ | 21k | — | ~584 | Automated safety check: Pass | Apache-2.0 | today |
| 27 | Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file… | google/ | 22k | — | ~748 | Automated safety check: Pass | Apache-2.0 | today |
| 28 | Describes a decision tree of steps and skills to utilize when, starting from a test failure or the failure of bazel run command using heir-opt, you would like to produce a reproducing input IR that… | google/ | 929 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 29 | Sets up a virtual try-on agent on Google Cloud that generates image and catwalk-video try-ons with Gemini, from first setup through local testing. | google/ | 10k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 30 | Skill to assist with using the devcontainer tool for running builds, tests, and other tools in a consistent containerized environment. | google/ | 1.3k | — | ~345 | Automated safety check: Pass | BSD-3-Clause | today |
| 31 | Designs GCP infrastructure as local Terraform, validates and scans it against best practices, then imports it to Application Design Center for deployment and troubleshooting. | google/ | 21k | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | today |
| 32 | Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to… | google/ | 22k | — | ~759 | Automated safety check: Pass | Apache-2.0 | today |
| 33 | Creates a new Python recipe for the ADK recipes repository by running a scaffold script that copies template files, after confirming the output directory and recipe name. | google/ | 10k | — | ~931 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 34 | Analyzes BigQuery slot use, query costs and execution bottlenecks from INFORMATION_SCHEMA to diagnose slow queries, slot contention and unpartitioned scans. | google/ | 21k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | today |
| 35 | Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. | google/ | 22k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 36 | Interviews you about data model, workload and scale, then recommends one Google Cloud database from a decision matrix and drafts starter provisioning code for review. | google/ | 21k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 37 | Reviews a GitHub pull request and drafts a small set of inline comments in a human reviewing voice, each checkable from the line it points at, then posts them after approval. | google/ | 10k | — | ~8.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 38 | Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them… | google/ | 22k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 39 | Generates valid PromQL queries for Cloud Monitoring metrics from metric descriptors and resource parameters, with a validator script and error-recovery notes. | google/ | 21k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 40 | Makes an existing Python recipe deployable: generates the serving files a container needs (Dockerfile, .dockerignore, fastapiapp.py, apputils/a2a.py, apputils/services.py… | google/ | 10k | — | ~6.9k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 41 | Translates Snowflake dbt SQL models into standardized BigQuery SQL, keeping Jinja constructs and tracking progress in a migration tasks file. | google/ | 21k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 42 | Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. | google/ | 22k | — | ~592 | Automated safety check: Pass | Apache-2.0 | today |
| 43 | A skill your agent uses when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. | google/ | 21k | 3 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 44 | Searches skills.sh for agent skills you do not have yet, checks their quality, presents the option and installs only after you confirm. | google/ | 10k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 45 | Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). | google/ | 21k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 46 | Scan an ADK recipe directory and generate a manifest.yaml for it based on the schema at .github/schemas/manifest-schema.json. | google/ | 10k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 47 | Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. | google/ | 21k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 48 | Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the gws CLI. | google/ | 10k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill by google?
Adk Verify Snippets (official) from google/adk-python ranks first of the 185 skills by google listed here, with the highest score: its repository has 22k GitHub stars, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Adk Sample Creator and Adk Unit Guide.
Are google's skills official?
185 of the 185 skills by google are official, published by the vendor's own GitHub organization: Adk Verify Snippets, Adk Sample Creator, Adk Unit Guide, Adk Git, Crosvm Contribution Workflow and 180 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.