Guides setup of the Race Condition project from clone to running simulation.

Custom licenceAuto-check: notesDevelopment

Install Getting Started

skills CLI
$ npx skills add GoogleCloudPlatform/race-condition --skill getting-started -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GoogleCloudPlatform/race-condition getting-started --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/getting-started .claude/skills/getting-started && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
getting-started
GitHub stars
234
Token cost
~1k tokens
SKILL.md length
399 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Custom licence

At a glance

Guides setup of the Race Condition project from clone to running simulation.

  • Works in 7 steps: Clone the repo (AUTO) → GCP authentication (MANUAL) → Enable required APIs (AUTO) → …
  • The developer wants to get the project running locally
  • SKILL.md covers Prerequisites Check, Setup Workflow, Troubleshooting and Next Steps
  • Calls make, gcloud and uv; needs GOOGLE_MAPS_API_KEY

What it does

Getting Started is an agent skill from GoogleCloudPlatform/race-condition. Guides setup of the Race Condition project from clone to running simulation. Use when the developer wants to get the project running locally, install dependencies, configure GCP credentials, or troubleshoot startup issues.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Async programming. It works with Google Cloud, Google Maps Platform, Docker and Python. The repository describes itself as: The open source multi-agent simulation from the Developer Keynote at Google Cloud Next '26. A deployable reference architecture for autonomous AI agents using Gemini and ADK.

When your agent uses it

  • The developer wants to get the project running locally
  • Install dependencies
  • Configure GCP credentials
  • Troubleshoot startup issues

Example prompts

  • “Use the getting-started skill to guide setup of the Race Condition project from clone to running simulation”
  • “/getting-started”

Requirements

  • Python 3
  • Node.js
  • Docker
  • A credential in GOOGLE_MAPS_API_KEY

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Clone the repo (AUTO)
  2. GCP authentication (MANUAL)
  3. Enable required APIs (AUTO)
  4. Initialize the project (AUTO)
  5. Configure .env (AUTO)
  6. Start the simulation (AUTO)
  7. Google Maps API key (MANUAL, optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 26efc1b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make
    • gcloud
    • uv
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • go.dev
    • docs.astral.sh
    • nodejs.org
    • docs.docker.com
    • cloud.google.com
    • console.cloud.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GOOGLE_MAPS_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Getting Started loads about 1k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 399 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:75
    This checks prerequisites, creates `.env` from `.env.example`, installs Python
  • NoteMentions a .env fileSKILL.md:79
    ### Step 5: Configure .env (AUTO)
  • NoteMentions a .env fileSKILL.md:85
    your-gcp-project-id/ACTUAL_PROJECT_ID/g' .env
  • NoteMentions a .env fileSKILL.md:88
    your-gcp-project-id/ACTUAL_PROJECT_ID/g' .env
  • NoteMentions a .env fileSKILL.md:119
    3. Add to `.env`: `GOOGLE_MAPS_API_KEY=AIza...`
  • NoteMentions a .env fileSKILL.md:131
    RUNNER_MODEL=ollama_chat/gemma4:e2b` in `.env` for free local inference |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 399 words (~1,037 tokens).

“This skill walks through setting up Race Condition for local development. Some steps are fully automatable (installing dependencies, building code). Others require the developer to act in a browser or terminal (GCP auth, API key creation). Each step is marked…”

— opening of SKILL.md by GoogleCloudPlatform, Custom licence
name
getting-started

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/getting-started of GoogleCloudPlatform/race-condition.

Open the folder on GitHubat commit 26efc1b

Compare with similar skills

Getting Started next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Getting Started compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Getting Started this skillGoogleCloudPlatform/race-condition234—~1kAutomated safety check: NotesCustom licence
Burla Parallel Dev ClustersBurla-Cloud/burla263—~1.6kAutomated safety check: PassCustom licence
Zizkadb Dev SetupZIZKA-AI-SL/ZizkaDB124—~535Automated safety check: NotesCustom licence
AzureML Project ScaffoldingKilo-Org/kilo-marketplace189—~3.1kAutomated safety check: NotesMIT
Flowfile Build and Environment SetupEdwardvaneechoud/Flowfile370—~7.3kAutomated safety check: NotesMIT
Flowfile Config and Flags CatalogEdwardvaneechoud/Flowfile370—~12kAutomated safety check: NotesMIT

Similar skills

  • Sets up an isolated Burla dev cluster per git worktree so several agents can work in parallel, and explains when to use local-dev or remote-dev.

    263 GitHub stars~1.6k tokensUpdated 15 days ago
    DevelopmentAuto-check passed
  • Zizkadb Dev Setup

    ZIZKA-AI-SL/ZizkaDB

    Set up and start the local ZizkaDB development stack. An agent skill from ZIZKA-AI-SL/ZizkaDB.

    124 GitHub stars~535 tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • AzureML Project Scaffolding

    Kilo-Org/kilo-marketplace

    Sets up and maintains AzureML-ready Python projects as uv workspaces with devcontainers, a Makefile and job YAML, so local runs match cloud jobs and experiments stay reproducible.

    189 GitHub stars~3.1k tokensUpdated 8 days ago
    DevelopmentAuto-check: notes
  • Flowfile Build and Environment Setup

    Edwardvaneechoud/Flowfile

    Recreates every Flowfile development and build environment from scratch, with exact version pins and an explanation of what each Makefile target really does.

    370 GitHub stars~7.3k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Flowfile Config and Flags Catalog

    Edwardvaneechoud/Flowfile

    Catalog of Flowfile's environment variables and runtime flags: what each does, where the code reads it, its default, and where the docs disagree with the code.

    370 GitHub stars~12k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Temporal Python Pro

    aiskillstore/marketplace

    Master Temporal workflow orchestration with Python SDK. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 6 repos~2.8k tokens
    DevelopmentAuto-check passed

More from GoogleCloudPlatform/race-condition

All 16 skills in this repo
  • Gis Spatial Engineering

    GoogleCloudPlatform/race-condition

    A skill your agent uses when the marathon plan needs a 26.2-mile physical route generated from road-network GeoJSON, or when the request mentions traffic impact, route variety via seed, finishing…

    234 GitHub stars~672 tokensUpdated 2 days ago
    Auto-check passed
  • A2ui Rendering

    GoogleCloudPlatform/race-condition

    A skill your agent uses when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol.

    234 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Contributing

    GoogleCloudPlatform/race-condition

    Guides the developer workflow for contributing to Race Condition.

    234 GitHub stars~930 tokensUpdated 2 days ago
    Auto-check passed
  • Deploying

    GoogleCloudPlatform/race-condition

    Guides deployment of Race Condition to a GCP project. An agent skill from GoogleCloudPlatform/race-condition.

    234 GitHub stars~3k tokensUpdated 2 days ago
    Auto-check passed
  • Exploring The Codebase

    GoogleCloudPlatform/race-condition

    Explains the Race Condition architecture, the design decisions behind it, and where to read code first.

    234 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed
  • Preparing The Race

    GoogleCloudPlatform/race-condition

    A skill your agent uses when the simulator receives a validated plan from the planner and must initialize the race: parsing the plan, spawning runner agents, starting the telemetry collector, and…

    234 GitHub stars~563 tokensUpdated 2 days ago
    Auto-check passed

Questions about Getting Started

What does Getting Started do?

Guides setup of the Race Condition project from clone to running simulation. Getting Started is an agent skill from GoogleCloudPlatform/race-condition. Guides setup of the Race Condition project from clone to running simulation.

When should I use Getting Started?

Getting Started fits situations like: the developer wants to get the project running locally; install dependencies; configure GCP credentials; troubleshoot startup issues.

How do I install Getting Started in Claude Code?

Run `npx skills add GoogleCloudPlatform/race-condition --skill getting-started -a claude-code`. Or copy the skill folder (.claude/skills/getting-started in GoogleCloudPlatform/race-condition) into .claude/skills/getting-started in your project. Claude Code loads it when a task matches its description.

How do I install Getting Started in Codex?

Run `npx skills add GoogleCloudPlatform/race-condition --skill getting-started -a codex`. Or copy the skill folder (.claude/skills/getting-started in GoogleCloudPlatform/race-condition) into .agents/skills/getting-started in your project. Codex loads it when a task matches its description.

Can I use Getting Started in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleCloudPlatform/race-condition --skill getting-started -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/getting-started, .gemini/skills/getting-started, .github/skills/getting-started and .opencode/skills/getting-started in your project.

What does Getting Started need to run?

Going by SKILL.md and its folder, Getting Started needs the command-line tools its instructions call (make, gcloud, uv and git) and credentials named GOOGLE_MAPS_API_KEY. Our summary lists: Python 3; Node.js; Docker; A credential in GOOGLE_MAPS_API_KEY.

Does Getting Started access the network?

SKILL.md names 6 domains. As links in the text: go.dev, docs.astral.sh, nodejs.org, docs.docker.com, cloud.google.com and console.cloud.google.com. This is read from the text; nothing was executed.

Is Getting Started safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Getting Started use?

Getting Started has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Getting Started use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Getting Started?

Skills that share tags, products or a category with Getting Started: Burla Parallel Dev Clusters (Burla-Cloud/burla, 263 stars), Zizkadb Dev Setup (ZIZKA-AI-SL/ZizkaDB, 124 stars), AzureML Project Scaffolding (Kilo-Org/kilo-marketplace, 189 stars) and Flowfile Build and Environment Setup (Edwardvaneechoud/Flowfile, 370 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Getting Started?

GoogleCloudPlatform (a GitHub organization) maintains it in GoogleCloudPlatform/race-condition, which has 234 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.

Source: GoogleCloudPlatform/race-condition on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.