Skip to main content
skill CX Codex

using-cloud-cli — Claude Code skill: what it does, how to install

The using-cloud-cli skill sets patterns for bq, gcloud, and aws. Use it for BigQuery queries, cloud resource commands, and AWS or GCP service decisions.

MIT 108 installs ★ 17 updated 2026-10-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add julianobarbosa/claude-code-skills --skill using-cloud-cli -a claude-code
Open on GitHub

What using-cloud-cli does

using-cloud-cli gives an agent practical patterns for AWS and GCP command-line work. For BigQuery, it puts a dry run before query execution so scanned bytes can be estimated. It also covers table listings, schema inspection, Compute Engine resources, EC2, and S3.

The skill allows Read, Bash, Grep, and Glob. Its references include GCP.md and AWS.md, while scripts/ contains helper scripts for common operations. Examples use JSON output, explicit projects or regions, JMESPath filtering, and --quiet for automated commands.

BigQuery charges by bytes scanned, so skipping --dry_run can turn an unreviewed query into a paid one. The notes also separate gcloud auth login from application-default credentials, compare AWS CLI v1 and v2 configuration, and explain precedence between AWS_PROFILE, --profile, and environment credentials.

What it helps with

  • estimate a BigQuery query before running it
  • inspect a table schema with bq
  • list GCP or AWS resources as JSON
  • verify the AWS identity in use
  • run gcloud commands in automation

Example prompts for the agent

  • Estimate the cost of this BigQuery query with bq --dry_run, then run it as JSON.
  • List the Compute Engine instances as JSON and set the project explicitly.
  • Check which AWS credentials are active, then return EC2 instance IDs with JMESPath.

How to install using-cloud-cli

1Skills CLI (Vercel)

npx skills add julianobarbosa/claude-code-skills --skill using-cloud-cli -a claude-code

2Manually: put the files in place

~/.claude/skills/using-cloud-cli/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/using-cloud-cli/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about using-cloud-cli

How do I install using-cloud-cli in Claude Code?

Run npx skills add julianobarbosa/claude-code-skills --skill using-cloud-cli -a claude-code, then check ~/.claude/skills/using-cloud-cli/SKILL.md.

What does using-cloud-cli do?

It provides patterns for bq, gcloud, and aws, including BigQuery cost checks, cloud resource inspection, explicit project or region selection, and credential verification.

Why should a BigQuery query use --dry_run first?

BigQuery charges for scanned bytes. --dry_run lets the agent estimate the query before execution.

Source text

SKILL.md · MIT
---
name: using-cloud-cli
description: Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.
allowed-tools: Read, Bash, Grep, Glob
---

# Cloud CLI Patterns

Credentials are pre-configured. Use `--help` or Context7 for syntax.

## BigQuery

```bash
# Always estimate cost first
bq query --dry_run --use_legacy_sql=false 'SELECT ...'

# Run query
bq query --use_legacy_sql=false --format=json 'SELECT ...'

# List tables
bq ls project:dataset

# Get table schema
bq show --schema --format=json project:dataset.table
```

**Cost awareness**: Charged per bytes scanned. Use `--dry_run`, partition tables, specify columns.

## GCP (gcloud)

```bash
# List resources
gcloud compute instances list --format=json

# Describe resource
gcloud compute instances describe INSTANCE --zone=ZONE --format=json

# Create with explicit project
gcloud compute instances create NAME --project=PROJECT --zone=ZONE

# Use --quiet for automation
gcloud compute instances delete NAME --quiet
```

## AWS

```bash
# List resources
aws ec2 describe-instances --output json

# With JMESPath filtering
aws ec2 describe-instances --query 'Reservations[].Instances[].InstanceId' --output text

# Explicit region
aws s3 ls s3://bucket --region us-west-2

# Dry run where available
aws ec2 run-instances --dry-run ...
```

## References

- [GCP.md](GCP.md) - GCP service patterns and common commands
- [AWS.md](AWS.md) - AWS service patterns and common commands
- [scripts/](scripts/) - Helper scripts for common operations

---

## Gotchas

- **`gcloud auth login` and `gcloud auth application-default login` are DIFFERENT credentials** — a script working for the user can 401 in CI because CI only has the latter.
- **AWS CLI v1 vs v2 have different config formats** — both may be installed; `aws --version` reveals which is the default `aws` binary.
- **BigQuery cost estimation requires `--dry_run`** — without it, you can run a $100 query thinking it's free. Always estimate first.
- **Precedence**: `AWS_PROFILE` vs `--profile` flag vs `AWS_ACCESS_KEY_ID` direct env — three-way precedence is order-dependent and rarely documented.
- **gcloud impersonation chains via `--impersonate-service-account` need IAM token-creator on EACH hop** — missing one hop returns 403 with vague "permission denied".
- **`aws sts get-caller-identity` is the cheapest way to verify which credential you're actually using** — always check first.

© julianobarbosa · MIT · julianobarbosa/claude-code-skills

Similar skills

All skills for Cloud: AWS, Azure, GCP →
database-cloud-optimization-cost-optimize sickn33 The database-cloud-optimization-cost-optimize skill reviews AWS, Azure, and GCP spending, spots waste, and proposes cost changes with risk checks. Use it for cloud databases and infrastructure budgets. CX Codex +1 ★ 50,109repo stars cloud-devops davila7 cloud-devops is a Claude Code skill for cloud infrastructure and DevOps work. It lays out tasks for Kubernetes deployments, CI/CD, monitoring, security, cost management, and disaster recovery. CX Codex +1 107installs cloud-infrastructure Seth Hobson cloud-infrastructure designs AWS, GCP, and Azure setups, prepares reusable Terraform modules, and optimizes cloud spending using six specialized subagents. ★ 126repo stars cloud-security Alireza Rezvani cloud-security flags exploitable misconfigurations across AWS, Azure and GCP: IAM privilege escalation paths, public buckets, open security group ports. Useful before an audit or when reviewing IaC. CX Codex +1 643installs google-cloud-solution-agentic-ai-borderless-data-lakehouse official google The google-cloud-solution-agentic-ai-borderless-data-lakehouse is a Claude Code and Gemini CLI skill that designs multi-cloud data lakehouses with Apache Iceberg, BigQuery data agents, and Gemini Enterprise Agent Platform. CX Codex +1 5,100installs cloud-architect https://github.com/Jeffallan A skill for designing cloud architectures on AWS, Azure and GCP: redundant topology, migration plan, cost model and a disaster recovery strategy. CX Codex +1 5,100installs

From the same set37

The whole set →

Project sponsors

Companies that keep this analytics open