Generates cost optimization guidance for Google Cloud workloads based on the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate a workload, identify cost requirements and constraints, and provide actionable recommendations for build, deploy, and manage the workload cost-efficiently in Google Cloud.

Use when creating Helm charts, packaging Kubernetes applications, managing multi-environment deployments, or asking about "Helm", "Helm chart", "values.yaml", "chart templating", "Helm dependencies"

Learn how to set up Xcode Cloud to build and deploy your Flutter application to TestFlight and the App Store with this step-by-step guide.

Best practices for using browser-use's open-source browser-harness with Kernel cloud browsers over CDP. Use when driving a Kernel browser from browser-harness, extracting a CDP URL from `kernel browsers create`, or running multi-step or parallel harness sessions against Kernel.

Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.

Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.

Run integration tests that require Linux (full loopback range 127.x.x.x) via Docker. Use when a test fails on macOS with "Can't assign requested address" or when the user says "/linux-test".

Execute mcloud projects commands to list, get, or delete Cloud projects. Use when discovering projects, resolving project handles by name, or retrieving project details including linked environments.

Execute mcloud variables commands to list and get environment variables for a Cloud environment. Use when inspecting, reading, or exporting environment variables. Never pass --reveal unless the user explicitly requests secret values.

Use when "Modal", "serverless GPU", "cloud GPU", "deploy ML model", or asking about "serverless containers", "GPU compute", "batch processing", "scheduled jobs", "autoscaling ML"

Terraform module development patterns and best practices. Provides structure, versioning, and output scaffolds. Use when creating reusable modules.

Optimizes CI pipelines for monorepos by detecting affected packages/apps and running only necessary builds and tests. Includes Turborepo/Nx strategies, caching, and parallel execution. Use for "monorepo CI", "affected detection", "incremental builds", or "workspace optimization".

Secure OpenClaw deployments with preflight hardening checks, CI/CD guardrails, container runtime restrictions, and post-deploy verification. Use when shipping OpenClaw with Docker, Kubernetes, or automated release pipelines.

Optimize CI/CD pipelines by caching Playwright browser binaries and dependencies to speed up test execution. Use when setting up Playwright in CI/CD pipelines, reducing build times by caching browser binaries, or configuring GitHub Actions or Azure DevOps for Playwright tests.

Reference for the /create-dashboard and /deploy-dashboard orchestrated AI workflow

Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches

Enforces minimum quality thresholds in CI including code coverage, linting, type checking, and security scanning. Provides required checks, PR rules, and automated enforcement. Use for "quality gates", "CI checks", "code quality", or "PR requirements".

Reference documentation for docker-local architecture, commands, and configuration

Analyze and fix CI check failures on a PR. Use when CI checks fail, build errors occur, or tests fail in CI. Invoked automatically by the SDLC workflow (Step 7.4) when checks fail, or manually via 'resolve CI failures', 'fix CI', 'fix failing checks'.

Rstest best practices for config, CLI workflow, test writing, mocking, snapshot testing, DOM testing, coverage, multi-project setup, CI integration, performance and debugging. Use when writing, reviewing, or troubleshooting Rstest test projects.

Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network, and process access.

Use when asked to shepherd, babysit, monitor, or poll open pull requests or merge requests — including triaging review comments, detecting CI failures, fixing trivial CI issues, and keeping PRs/MRs moving without manual intervention.

Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or "resolve comments". Handles comment triage (resolve false positives, fix trivial issues, flag complex ones), build/lint/type errors, and e2e snapshot updates.

Ship a PR end-to-end: local verify (build, test, lint), push, create or update PR, watch CI to green, address review bot feedback, merge with auto-delete. NEVER uses --admin merge. Triggers: 'ship', 'ship it', 'push and merge', 'land this PR'. SKIP if user just wants to open a PR without merging — use `create-pr` instead.

SRE / Observability Engineer (/sre) — reliability engineering: SLOs/SLIs & error budgets, monitoring & alerting (Prometheus, Grafana, OpenTelemetry), incident response & runbooks, on-call, capacity & load, chaos/resilience, and post-incident reviews. Use when defining reliability targets, instrumenting observability, setting up alerting, writing runbooks, doing incident response, or reviewing a change for production readiness. Invoke alongside /arch for reliability NFRs and devops-engineer for the underlying infra/CI-CD. NOT for provisioning infra or pipelines (that's devops-engineer) — /sre owns reliability, not the cluster.

Terraform infrastructure as code patterns and best practices. Use when writing Terraform configurations, creating modules, managing state, or designing IaC architectures.

Update GitHub Actions versions in workflow files, focusing only on major version changes. Use when the user wants to update action versions, check for outdated GitHub Actions, or upgrade workflow dependencies to their latest major versions.

Vercel Functions and Edge Runtime, including cron jobs and routing middleware. Use when building APIs, serverless workloads, or scheduled tasks on Vercel.

Vercel account, team, and billing management including plans and spend controls. Use when managing teams, accounts, or cost governance on Vercel.

Mid-review entry point: fetch PR comments and CI failures, address them, validate, push. Use when jumping into an existing PR. /dev handles this automatically.

Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-tuning`), deploying models to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).

Pull a Fusion BICC bulk extract into a Spark DataFrame from an AIDP notebook. Use when the user mentions BICC, Fusion bulk extract, BI Cloud Connector, PVO, or needs >50k rows from Fusion. The recommended path uses AIDP's built-in `spark.read.format("aidataplatform")` connector (matches the official Oracle AIDP sample). HTTP Basic auth.

Addresses all PR review comments, resolves merge conflicts, and fixes failing CI checks to get the PR ready to merge. Use when the user wants to make their PR "all green" or ready for merge.

AWS cloud infrastructure patterns and best practices. Use when designing AWS architectures, creating Lambda functions, configuring S3 buckets, setting up EC2 instances, designing VPCs, or implementing any AWS services.

Work with Azure DevOps Product Backlog Items using az boards CLI

Configure Biome to respect .gitignore via VCS integration so that untracked and ignored files are skipped during format and lint. Use when the user encounters Biome errors on .gitignore'd files, CI failures from local-only files, or asks how to exclude files from Biome. Trigger on keywords: "biome gitignore", "biome ignore files", "biome vcs", "biome skip untracked", "biome CI failure local file", "biome settings.local.json", "useIgnoreFile", "clientKind".

Use when bootstrapping a new repo's CI, setting up deploy workflows, deciding what branch a feature PR should target, or whenever someone proposes "auto-deploy prod on every main merge". Captures the feat → dev → main promotion model with separate Deploy Dev (push to dev) and Deploy Prod (push to main), and links the templates that implement it.

Build and deploy Xcode projects to Mac or iOS devices in one step. Use when user says "build and deploy", "deploy to iPad", "rebuild server", "install on device", or wants to test changes on a physical device. Handles xcodegen → xcodebuild → install → launch automatically.

Cloudflare Durable Objects: stateful workflows, WebSockets, coordination, rate limiting, alarm scheduling. Use when building stateful services on Cloudflare.

Cloudflare KV storage: caching, key-value operations, TTL, namespace management. Use when implementing caching or edge storage on Cloudflare Workers.

Check repository compliance with Brockhoff Cloud spec-driven development standards

Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.

Identifies which object-storage provider an S3-compatible target actually hits, from endpoint URLs, env vars, or Terraform provider blocks. Prevents AWS-default assumptions on GCS/DO Spaces/R2/Hetzner/B2/MinIO. Use when working with boto3, `aws_s3_bucket`, rclone, s3cmd, or S3-compatible storage.

Deploy and release wipnote — run quality gates, bump version, tag, push, and trigger GitHub release pipeline. Use when asked to deploy, release, publish, ship, or push a new version.

Automatically discover CI/CD and automation skills when working with GitHub Actions, Jenkins, GitLab CI, pipelines, continuous integration, continuous deployment, or automated testing. Activates for CI/CD development tasks.

Docker Compose generation, optimization, and troubleshooting assistance.

Define and run Eve pipelines and workflows via manifest and CLI. Use when wiring build, release, deploy flows or invoking workflow jobs.

Use when the user wants to spin up, run, start, or self-host a local Excalidraw whiteboard server from the official open-source repo (clone + Vite dev server, no Docker). Handles cloning, the yarn-classic toolchain, a configurable port, port-collision detection, and readiness verification.

Guidelines for identifying and resolving missing Google Cloud authentication and Application Default Credentials (ADC). Use this skill if `gcloud`, `bq`, `dataform`, or Python libraries return authentication errors.

Orchestrate CI/CD pipelines with GitHub Actions for Flutter apps. Use when setting up quality gates, automated builds, semantic versioning, code signing, or deployment workflows.

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

Guides Claude through deploying Gleam applications to production on Fly.io, Docker, or other platforms. Use when setting up deployment pipelines, configuring environments, or troubleshooting production issues.

Create and manage Hetzner Cloud servers. Use when creating VPS/cloud servers, managing Hetzner infrastructure, or setting up dev/remote servers. Requires hcloud CLI.

Learn how to deploy PocketBase on Google Cloud Run using the new volume mounting feature, enabling scale-to-zero, infinite storage, and easy backups.

Kubernetes and Helm patterns - use for deployment configs, service definitions, ConfigMaps, Secrets, and Helm chart management

Provides production-ready Kubernetes manifest guidance including resource management, security, high availability, and configuration best practices. This skill should be used when working with Kubernetes YAML files, deployments, pods, services, or when users mention k8s, container orchestration, or cloud-native applications.

Implement Kubernetes security contexts, Pod Security Standards, and network policies. Secure cluster components and workloads. Use when hardening Kubernetes deployments or meeting security compliance.

Kubernetes deployment patterns and best practices. Use when creating Kubernetes manifests, Helm charts, configuring pods, services, deployments, or troubleshooting K8s clusters.

Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper that bridges Lighthouse CI accessibility audit data with the agent ecosystem. Parses Lighthouse reports, normalizes accessibility findings, tracks score regressions, and deduplicates against local scans.

Execute mcloud organizations commands to list or get Cloud organizations. Use when discovering organizations, resolving organization IDs by name, or retrieving organization details including members and subscription.

Merge a reviewed PR (hv-managed or standalone) after confirming it is genuinely ready — approved, green CI, up to date with base, no unresolved blocking feedback. Use once /hv:review-pr approves a feature's PR. Refuses to merge on red checks or missing review.

Fastlane, GitHub Actions for mobile, code signing (iOS provisioning, Android keystores), beta distribution (TestFlight, Firebase App Distribution), and app store submissions. Use when setting up mobile build pipelines, automating releases, or managing signing.

Curated bundle for managing monorepos with containerized deployment pipelines. Includes monorepo management, Docker containerization, CI/CD deployment, and coding standards. Use when setting up or improving multi-package repository infrastructure.

This skill should be used when the user asks to "watch this PR", "monitor the PR", "keep an eye on CI", "watch for reviews", "babysit this PR", or wants autonomous PR monitoring that detects and responds to CI failures, review comments, and merge conflicts on the current branch's PR.

Hardening Dockerfiles to reach Docker Hub Health Score grade A: enforcing a non-root USER, minimal/distroless multi-stage base images, no fixable critical/high CVEs, no AGPL-3.0 deps, and SBOM+provenance attestations. Use when creating a new Dockerfile, auditing one for security, or preparing images for Docker Hub publication. Skip when the project has no Dockerfile, changes are app-code-only, or you consume pre-built images.

Use when deploying Salesforce metadata — package.xml, source-format/metadata-format, validate, deploy, diff, rollback, scratch orgs, sandboxes, production.

Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.

Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.

Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.

Audit AWS security groups for overly permissive rules and security vulnerabilities. Use when reviewing AWS security, auditing security groups, or improving network security posture.

Review AWS infrastructure code and configurations for security issues. Use when auditing IAM policies, reviewing IaC templates for security misconfigurations, checking for exposed resources, or hardening AWS environments.

Guide for setup arXiv paper search MCP server using Docker MCP

CLI tool for querying AWS Knowledge MCP Server

Manage agent skills using the npx skills CLI. Use when the user asks to "install a skill", "add a skill", "remove a skill", "list skills", "update skills", "find skills", "search for skills", or mentions "npx skills", skill management, or agent skill installation. Also trigger when the user mentions skills.sh, agent-skills, vercel skills, or wants to discover available skills for their environment. Boundary: not for creating new skills (use skill-creator) or managing plugins (/plugin commands).

Deploy Slidev presentations to the web. Use this skill for GitHub Pages, Netlify, Vercel, and Docker deployments.

Encrypt files and configs with Mozilla SOPS. Integrate with AWS KMS, GCP KMS, or PGP for key management. Use when encrypting configuration files, Kubernetes secrets, or implementing GitOps with encrypted secrets.

Safely removes all AWS resources created by this plugin. Permanently deletes cloud resources.

PR workflow Skill for Terraform/Terragrunt repos: branch naming, PR hygiene, read-only CI gates, and versioning expectations for interface changes.

Manages Terraform state operations including importing existing resources, moving resources between states, removing resources from state, and migrating state backends. This skill should be used when users need to import infrastructure into Terraform, refactor resource addresses, fix state issues, or migrate state storage locations.

Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.

Update outdated GitHub Actions in workflow files and pin them to commit hashes for supply-chain security.

Create, amend, remove, and rebase patches for Terraform provider submodules using `./scripts/upstream.sh`. Use when `upgrade-provider` or manual patch work needs owning-patch lookup, patch conflict fixes, patch/hunk removal, or upstream rebase.

Deploy and manage applications on Vercel, including preview deployments and deployment protection. Use when working with Vercel-hosted projects or configuring Vercel deployments.

Your Own AI Personal Assistant, Set Up in 24 Hours. Managed OpenClaw hosting and setup service.

Read and write AWS S3 (`s3a://`) from an AIDP notebook. Use when the user mentions S3, AWS S3 bucket, s3a, or has AWS access keys. Auth is access key + secret key via the Hadoop S3A connector. boto3 is also available for non-Spark management operations (list, copy).

Build AI agents with AWS Bedrock AgentCore. Use when developing agents on AWS infrastructure, creating tool-use patterns, implementing agent orchestration, or integrating with Bedrock models. Triggers on keywords like AgentCore, Bedrock Agent, AWS agent, Lambda tools.

Manage AWS resources using the AWS CLI v2 (EC2, Lambda, ECS, CloudWatch, IAM, and more).

AWS cloud infrastructure patterns and best practices. Use when designing or implementing AWS solutions including EC2, Lambda, S3, RDS, and infrastructure as code with Terraform or CloudFormation.

Manage AWS ECS clusters, services, tasks, and task definitions.

Manage AWS Lambda functions -- deploy, invoke, view logs, and configure.

Backup files to Backblaze B2 using rclone. Use when the user wants to back up files, sync files to the cloud, or mentions rclone/B2 backups.

Check CI status for the current branch, analyze failures, distinguish failures caused by our changes from pre-existing flakes, and propose specific fixes. Use when the user asks about CI, build status, failing checks, failing jobs, test failures in CI, or whether the branch is ready after a push.

AWS, Azure, and GCP cloud services and best practices

Use when making source code changes to cloud-setup, creating branches, pushing changes, or creating merge requests for infrastructure and ArgoCD manifests.