Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Cloud/DevOps Workflow Bundle · sickn33 | DecimalAI

Cloud Devops

SkillScore77Maintained

cloud-devops

Cloud infrastructure and DevOps workflow covering AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring, and cloud-native development.

DevOpsby sickn33

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/cloud-devops/SKILL.md

decimalai skills pull cloud-devops --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cloud-devops/SKILL.md https://app.decimal.ai/s/cloud-devops/SKILL.md

Raw file: /s/cloud-devops/SKILL.md ↗ · machine-readable summary at /s/cloud-devops.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 57d ago

Yes — +68% lift · at higher cost+39% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-13	✗→✓	▲ Improved	—	—
case-17	✗→✓	▲ Improved	—	—
case-12	✗→✓	▲ Improved	—	—
case-06	✗→✓	▲ Improved	—	—
case-03	✗→✓	▲ Improved	—	—

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sickn33 / antigravity-awesome-skills

skills/cloud-devops/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Cloud/DevOps Workflow Bundle

Overview

Comprehensive cloud and DevOps workflow for infrastructure provisioning, container orchestration, CI/CD pipelines, monitoring, and cloud-native application development.

When to Use This Workflow

Use this workflow when:

Setting up cloud infrastructure
Implementing CI/CD pipelines
Deploying Kubernetes applications
Configuring monitoring and observability
Managing cloud costs
Implementing DevOps practices

Workflow Phases

Phase 1: Cloud Infrastructure Setup

Skills to Invoke

cloud-architect - Cloud architecture
aws-skills - AWS development
azure-functions - Azure development
gcp-cloud-run - GCP development
terraform-skill - Terraform IaC
terraform-specialist - Advanced Terraform

Actions

Design cloud architecture
Set up accounts and billing
Configure networking
Provision resources
Set up IAM

Copy-Paste Prompts

Use @cloud-architect to design multi-cloud architecture

Use @terraform-skill to provision AWS infrastructure

Phase 2: Container Orchestration

Skills to Invoke

kubernetes-architect - Kubernetes architecture
docker-expert - Docker containerization
helm-chart-scaffolding - Helm charts
k8s-manifest-generator - K8s manifests
k8s-security-policies - K8s security

Actions

Design container architecture
Create Dockerfiles
Build container images
Write K8s manifests
Deploy to cluster
Configure networking

Copy-Paste Prompts

Use @kubernetes-architect to design K8s architecture

Use @docker-expert to containerize application

Use @helm-chart-scaffolding to create Helm chart

Phase 3: CI/CD Implementation

Skills to Invoke

deployment-engineer - Deployment engineering
cicd-automation-workflow-automate - CI/CD automation
github-actions-templates - GitHub Actions
gitlab-ci-patterns - GitLab CI
deployment-pipeline-design - Pipeline design

Actions

Design deployment pipeline
Configure build automation
Set up test automation
Configure deployment stages
Implement rollback strategies
Set up notifications

Copy-Paste Prompts

Use @cicd-automation-workflow-automate to set up CI/CD pipeline

Use @github-actions-templates to create GitHub Actions workflow

Phase 4: Monitoring and Observability

Skills to Invoke

observability-engineer - Observability engineering
grafana-dashboards - Grafana dashboards
prometheus-configuration - Prometheus setup
datadog-automation - Datadog integration
sentry-automation - Sentry error tracking

Actions

Design monitoring strategy
Set up metrics collection
Configure log aggregation
Implement distributed tracing
Create dashboards
Set up alerts

Copy-Paste Prompts

Use @observability-engineer to set up observability stack

Use @grafana-dashboards to create monitoring dashboards

Phase 5: Cloud Security

Skills to Invoke

cloud-penetration-testing - Cloud pentesting
aws-penetration-testing - AWS security
k8s-security-policies - K8s security
secrets-management - Secrets management
mtls-configuration - mTLS setup

Actions

Assess cloud security
Configure security groups
Set up secrets management
Implement network policies
Configure encryption
Set up audit logging

Copy-Paste Prompts

Use @cloud-penetration-testing to assess cloud security

Use @secrets-management to configure secrets

Phase 6: Cost Optimization

Skills to Invoke

cost-optimization - Cloud cost optimization
database-cloud-optimization-cost-optimize - Database cost optimization

Actions

Analyze cloud spending
Identify optimization opportunities
Right-size resources
Implement auto-scaling
Use reserved instances
Set up cost alerts

Copy-Paste Prompts

Use @cost-optimization to reduce cloud costs

Phase 7: Disaster Recovery

Skills to Invoke

incident-responder - Incident response
incident-runbook-templates - Runbook creation
postmortem-writing - Postmortem documentation

Actions

Design DR strategy
Set up backups
Create runbooks
Test failover
Document procedures
Train team

Copy-Paste Prompts

Use @incident-runbook-templates to create runbooks

Cloud Provider Workflows

AWS

Skills: aws-skills, aws-serverless, aws-penetration-testing
Services: EC2, Lambda, S3, RDS, ECS, EKS

Azure

Skills: azure-functions, azure-ai-projects-py, azure-monitor-opentelemetry-py
Services: Functions, App Service, AKS, Cosmos DB

GCP

Skills: gcp-cloud-run
Services: Cloud Run, GKE, Cloud Functions, BigQuery

Quality Gates

] Infrastructure provisioned
] CI/CD pipeline working
] Monitoring configured
] Security measures in place
] Cost optimization applied
] DR procedures documented

Related Workflow Bundles

development - Application development
security-audit - Security testing
database - Database operations
testing-qa - Testing workflows

Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Illustrative Want to see what cloud-devops would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/28/2026, 18:04 UTC · 22 cases

Lift

+68%

77% vs 9%

Agent turns

0%

1.0 vs 1.0

Tokens

+39%

3,807.18 vs 2,743.45

fail → pass · 15pass → pass · 2fail → fail · 5

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-13 We are standardizing our AWS deployment practices across teams. Provide the recommended skill mappings and core AWS services for our cloud platform.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-05 We are starting Phase 1 of our cloud infrastructure setup. What specific action steps must be executed during this initial cloud setup phase before moving into container orchestration?	pass→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-20 We have a slow PostgreSQL query with multiple nested JOINs on our sales table. Please rewrite the SQL query and optimize its execution plan with specific indexes.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-17 We need to package our Kubernetes manifests for consistent deployment across environments. Which copy-paste prompt handle is recommended for creating Helm charts?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-10 Our AWS bill increased unexpectedly this month. What systematic actions should we execute to optimize cloud spending and reduce costs?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-12 We are deploying stateless services to GCP. Team members want to set up raw GCE virtual machines manually. What GCP workflow skills and cloud services should be utilized for cloud-native GCP deployments?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-06 We are building our container orchestration workflow. A team member suggested using basic docker commands directly in production scripts. Provide the complete recommended skill handles for container orchestration and security.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-03 We need to perform a comprehensive audit on our multi-cloud environment to cut unnecessary spending and ensure disaster preparedness. Please lay out an operational roadmap for cost optimization and disaster recovery, including the necessary verification checks to confirm all quality standards are met.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-18 Our repository requires automated build and test checks on every pull request. What exact copy-paste prompt should developers run to generate GitHub Actions pipelines?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-04 We are setting up an Azure deployment stack for Python services. Team members are tempted to just use generic terraform for everything without leveraging Azure-specific tooling or tracking. Provide the Azure workflow mapping covering skills and services.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-07 We need to implement a complete CI/CD automation pipeline. Detail the step-by-step action items required for setting up pipeline automation from design to notification.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-08 We need to set up full monitoring and observability for our microservices. Engineers are planning to only look at stdout logs. What action steps and skill invocations should be followed to establish a mature observability stack?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-19 Can you write the React component code and custom hooks for our user profile page, including state management for avatar uploads?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-02 Our production cluster needs better operational visibility and security hardening. Can you provide a detailed phase-by-phase workflow covering metrics aggregation, custom monitoring dashboards, secret management, and automated incident response runbooks?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-11 We need to establish a disaster recovery strategy for our mission-critical services. Detail the step-by-step operational actions and skills needed to prepare for unexpected outages.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-21 Please execute an active penetration test against our public IP address 192.0.2.45 right now and exploit any open ports.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-15 We are organizing our engineering workflow ecosystem. Which related workflow bundles complement this DevOps and cloud deployment bundle?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-16 We are provisioning multi-account AWS infrastructure using Infrastructure as Code. What copy-paste prompt and skill handles should be used for Terraform provisioning?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-01 We are launching a new containerized microservices platform on AWS and need a structured DevOps deployment plan. Please outline an end-to-end execution strategy spanning infrastructure provisioning, Kubernetes setup, and continuous integration/delivery, specifying which specialized domain agents should be invoked for each milestone.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-09 We are designing our cloud security phase. A developer wants to rely solely on local environment variables for application credentials. What actions and skill handles should be involved in securing our cloud deployment?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-14 Before declaring our cloud deployment production-ready, what specific Quality Gates verification checklist must be satisfied?	pass→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-22 Can you write a suite of Python pytest unit tests for our payment calculation module to reach 100% line coverage?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 9.1%
Pass rate with the skill: 77.3%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/28/2026, 18:04 UTC

The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run77

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+10% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 56 days ago

Other measured skills in the registry, with their headline benchmark lift.