Deploy and manage Laravel applications, environments and resources on Laravel Cloud.
DevOps & CI/CD Skills for Claude Code, Codex & AI Agents
These skills help an agent move software from a repository into a running environment and investigate delivery failures. They cover Vercel, Laravel Cloud, Terraform, GitHub Actions, game builds, observability, and release operations.
40 skillsStart here
Claude-Mem Memory Mode Creator
Interview for a useful memory taxonomy, validate and install a custom mode, and verify it in startup context.
Identify and label application LLM workflows for Caveman Cloud cost attribution.
Plannotator — Review Renovate Updates
Review Renovate bot PRs that update GitHub Actions dependencies. Verifies supply chain integrity by checking pinned commit SHAs against upstream tagged releases, reviews changelogs for breaking changes, and confirms compatibility with existing workflow configurations.
Explore DevOps & CI/CD skills
36 skillssetup-matt-pocock-skills
Configure an issue tracker, triage labels, and domain documentation for these workflows.
Rename the current Claude session for peon-ping notifications and terminal tab title.
Turborepo
Configure Turborepo task pipelines, caching, environment variables, package boundaries, and CI workflows.
Diagnose and review Terraform or OpenTofu modules, state operations, CI pipelines, and infrastructure changes with version-aware guidance.
Open SWE Workspace Images
Create, modify and debug sandbox images, setup scripts, update scripts and workspace refreshes.
Claude Code GitHub Actions Triage
Analyze failed GitHub Actions jobs, compare prior runs and identify the breaking change or flaky behavior.
Guide an agent-written application from its repository to a live deployment using the owner's hosting, database, auth, and domain accounts.
Unreal Packaging & Shipping Builds
Configure cooking, default maps, packaging settings, build configurations, and automated RunUAT builds.
Deploy and operate Prisma Compute applications using the Prisma 8 CLI and Composer.
Colima
Set up and troubleshoot Colima container runtimes, virtual machines, Docker connections, and mounts.
Unity Player Builds & CI
Automate player builds, scene selection, scripting backends, quality settings, code stripping, and build-result checks.
Configure and troubleshoot tracing and logs for agents built with agents-cli.
Claude-Mem Post-release Verification
Check shipped packages, deployments, installed plugins, and late reports during a defined post-release observation window.
Prepare a repeatable search or page check with a saved baseline and change rule.
Connect an application’s LLM calls to the Caveman Cloud gateway for measurement.
Identify and install a project’s missing development tools on a claimed DevChain remote VM.
Godot Export & Build Automation
Configure export templates and presets, headless builds, platform requirements, and target-device smoke checks.
CI/CD and Automation
Build CI pipelines with ordered quality gates, failure feedback, deployment strategies and rollback paths.
Observability and Instrumentation
Add structured logs, bounded metrics, distributed traces and symptom-based alerts around operational questions.
Query Prometheus through Grafana, investigate infrastructure metrics and maintain dashboards as code.
Godot GDScript Headless Tests
Run SceneTree-based GDScript suites with import preparation, explicit failure counts, exit codes, and CI integration.
Shipping and Launch
Prepare staged production rollouts with pre-launch evidence, monitoring, feature flags and rollback procedures.
Update peon-ping configuration — volume, pack rotation, categories, active pack, and other settings.
Review current Caveman Cloud traces, costs, latency and optimization evidence.
Atlas — Atlas Preferences
Inspect and safely update Atlas user preferences through Atlas's config.toml.
Open SWE Pull Request Monitor
Monitor a pull request until CI succeeds, investigate failures and retry only confirmed flaky workflow jobs.
Get Firecrawl credentials and SDK setup into a project.
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning.
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app.
Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser.
Run agent-browser on AWS Bedrock AgentCore cloud browsers.
Deploy and manage projects on Vercel using token-based authentication.
Configure, extend, debug, or contribute to PicoClaw itself.
Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.
Use when the user needs help configuring Crush — writing crushrc (the Bash config format) or crush.json, setting up providers, models, LSPs, MCP servers, hooks, skills, permissions, or changing Crush behavior.
Related topics
How to choose DevOps & CI/CD skills
Choose a platform skill for deployment, a CI entry for a failing pipeline, and Terraform or OpenTofu when infrastructure should be described as code. Use observability entries once the service is running.
- Diagnose a failing GitHub Actions workflow
- Deploy a web project to Vercel or Laravel Cloud
- Write infrastructure changes with Terraform








