How do I install the Gcs Setup skill?

Run npx skillmds@latest add datus-ai/gcs-setup in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Gcs Setup safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gcs Setup?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gcs Setup free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Gcs Setup?

datus-ai (@datus-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gcs Setup by datus-ai — Agent Skill

Name: Gcs Setup
Author: datus-ai

File contents

GCS Setup

Add profiles under agent.plugins.gcs.<profile> in the active Datus config. Prefer Application Default Credentials (ADC).

Collect and configure

Collect the profile name, GCP project, authentication mode, and optional default bucket.

agent:
  plugins:
    gcs:
      prod:
        default: true
        project: data-prod
        bucket: data-lake

        # Authentication: omit for ADC.
        # credentials_file: ${GOOGLE_APPLICATION_CREDENTIALS}
        # impersonate_service_account: datus@data-prod.iam.gserviceaccount.com
        # quota_project: billing-project
        # scopes: https://www.googleapis.com/auth/cloud-platform

        # api_endpoint: https://storage.googleapis.com
        timeout: "60"
        max_attempts: "3"

bucket enables bare-key arguments such as reports/today.csv; otherwise use gs://bucket/key. Use only ${ENV_VAR} references for credential-file paths, require the variable in the Datus process environment, and never copy the JSON credential into YAML or chat. credentials_file replaces default ADC; impersonate_service_account wraps the source credential, quota_project controls quota attribution, and scopes accepts comma-separated OAuth scopes. Use api_endpoint only for a custom Storage endpoint or emulator.

Prefer workload identity, an attached service account, or local ADC. Grant object read/list for browsing; add create/update for cp/sync; add delete for mv/rm; add bucket update for lifecycle replacement. Service-account impersonation requires Token Creator on the target. Signed URLs require a signing-capable identity in addition to access for the intended operation.

Verify

datus gcs --profile prod buckets list -o json
datus gcs --profile prod ls gs://data-lake/ --limit 5 -o json

If bucket listing is intentionally forbidden, verify a known allowed prefix directly. For failures, distinguish missing ADC/environment variables, service account impersonation denial, object-vs-bucket IAM denial, and custom endpoint connectivity. A configured default bucket does not grant access by itself.

If this environment cannot edit the active config, ask the deployment administrator to make the change.

---name: gcs-setupdescription: Configure or troubleshoot a Google Cloud Storage profile for datus gcs, including ADC, credential files, service-account impersonation, default bucket, scopes, custom endpoints, retries, permissions, and verification.---# GCS SetupAdd profiles under `agent.plugins.gcs.<profile>` in the active Datus config.Prefer Application Default Credentials (ADC).## Collect and configureCollect the profile name, GCP `project`, authentication mode, and optionaldefault `bucket`.```yamlagent: plugins: gcs: prod: default: true project: data-prod bucket: data-lake # Authentication: omit for ADC. # credentials_file: ${GOOGLE_APPLICATION_CREDENTIALS} # impersonate_service_account: datus@data-prod.iam.gserviceaccount.com # quota_project: billing-project # scopes: https://www.googleapis.com/auth/cloud-platform # api_endpoint: https://storage.googleapis.com timeout: "60" max_attempts: "3"````bucket` enables bare-key arguments such as `reports/today.csv`; otherwise use`gs://bucket/key`. Use only `${ENV_VAR}` references for credential-file paths,require the variable in the Datus process environment, and never copy the JSONcredential into YAML or chat. `credentials_file` replaces default ADC;`impersonate_service_account` wraps the source credential, `quota_project`controls quota attribution, and `scopes` accepts comma-separated OAuth scopes.Use `api_endpoint` only for a custom Storage endpoint or emulator.Prefer workload identity, an attached service account, or local ADC. Grantobject read/list for browsing; add create/update for `cp`/`sync`; add delete for`mv`/`rm`; add bucket update for lifecycle replacement. Service-accountimpersonation requires Token Creator on the target. Signed URLs require asigning-capable identity in addition to access for the intended operation.## Verify```bashdatus gcs --profile prod buckets list -o jsondatus gcs --profile prod ls gs://data-lake/ --limit 5 -o json```If bucket listing is intentionally forbidden, verify a known allowed prefixdirectly. For failures, distinguish missing ADC/environment variables, serviceaccount impersonation denial, object-vs-bucket IAM denial, and custom endpointconnectivity. A configured default bucket does not grant access by itself.If this environment cannot edit the active config, ask the deploymentadministrator to make the change.

Frequently asked questions

Gcs Setup