Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Cloud & infra
2,227 results · page 69 of 75
- View details
datarobot-model-monitoringSkillCloud & infra
Tools and guidance for monitoring model performance, tracking data drift, managing model health, and detecting prediction anomalies. Use when monitoring deployed models, tracking drift, or investigating prediction anomalies.
Ready to connect
- View details
datarobot-workload-apiSkillCloud & infra
Use when the user wants to create, configure, scale, debug, observe, or roll out container workloads on DataRobot's Workload API. Triggers include: deploying a container as a managed service, listing/starting/stopping workloads, changing replica counts or autoscaling, picking CPU/GPU compute bundles
Ready to connect
- View details
deployment-claims-auditSkillCloud & infra
PetSwipe workflow for checking whether deployment, production-readiness, or enterprise-grade claims are actually supported by repo evidence. Use when editing deployment docs, infra summaries, or any task that makes strong statements about readiness.
Ready to connect
- View details
deployment-engineerSkillCloud & infra
Use when a task needs deployment workflow changes, release strategy updates, or rollout and rollback safety analysis.
Ready to connect
- View details
deployment-proceduresSkillCloud & infra
Guides your agent through safe production deployment steps, rollback planning, and verification decisions.
Ready to connect
- View details
devops-incident-responderSkillCloud & infra
Use when a task needs rapid operational triage across CI, deployments, infrastructure automation, and service delivery failures.
Ready to connect
- View details
dotnet-core-expertSkillCloud & infra
Use when a task needs modern .NET and ASP.NET Core expertise for APIs, hosting, middleware, or cross-platform application behavior.
Ready to connect
- View details
expo-react-native-expertSkillCloud & infra
Use when a task needs Expo / React Native mobile work — navigation, native modules, performance, EAS builds, or store deployment.
Ready to connect
- View details
fastapi-developerSkillCloud & infra
Use when a task needs FastAPI implementation — async endpoints, Pydantic v2 contracts, dependency injection, or ASGI deployment behavior.
Ready to connect
- View details
golden-path-designerSkillCloud & infra
Use when a task needs an opinionated, low-friction golden path for service creation, deployment, or operations.
Ready to connect
- View details
infra-release-readinessSkillCloud & infra
PetSwipe infrastructure and deployment workflow for Kubernetes, Terraform, production Docker Compose, release bundle, and preflight validation. Use when the task is explicitly about deployability, production readiness, operator workflow, or infra/devops changes.
Ready to connect
- View details
infrahub-auditing-repoSkillCloud & infra
Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, queryin
Ready to connect
- View details
k8s-hardening-and-renderSkillCloud & infra
Kubernetes-local workflow for manifest hardening, renderability, overlays, quotas, network policies, and rollout safety in PetSwipe. Use when working inside k8s and the task is specifically about manifest correctness or production posture.
Ready to connect
- View details
kubernetes-specialistSkillCloud & infra
Use when a task needs Kubernetes manifest review, rollout safety analysis, or cluster workload debugging.
Ready to connect
- View details
mlops-engineerSkillCloud & infra
Use when a task needs model deployment, registry, pipeline, monitoring, or environment orchestration for machine learning systems.
Ready to connect
- View details
product-and-deploy-doc-syncSkillCloud & infra
Docs-local workflow for keeping PetSwipe product pages, deployment docs, architecture docs, and operational claims aligned with the current repository. Use when working inside docs or when multiple docs need to be updated together.
Ready to connect
- View details
prompt-engineeringSkillCloud & infra
Use when designing, optimizing, testing, or deploying robust prompt systems for AI agents. This skill provides frameworks for structured prompt engineering, meta-prompting, and automated optimization workflows.
Ready to connect
- View details
reinforcement-learning-engineerSkillCloud & infra
Use when a task needs RL environment design, policy training, reward engineering, or deployment of decision-making agents.
Ready to connect
- View details
reviewSkillCloud & infra
Bug-focused PetSwipe review workflow emphasizing regressions, deployment risk, missing validation, stale docs, and user-visible breakage. Use when the user asks for a review or when a risky change needs structured scrutiny.
Ready to connect
- View details
swagger-health-contractsSkillCloud & infra
Backend-local workflow for health endpoints, readiness behavior, Swagger/OpenAPI exposure, and runtime contract changes in PetSwipe. Use when backend work touches backend/src/app.ts, startup behavior, docs endpoints, or deployment-sensitive runtime behavior.
Ready to connect
- View details
app-templateSkillCloud & infra
Deploy applications using bjw-s/app-template Helm chart - a flexible chart for helmifying container images without dedicated charts.
Ready to connect
- View details
dockerfile-optimizerSkillCloud & infra
Audits Dockerfiles for multi-stage build efficiency, layer caching, non-root security, and minimal base image footprint.
Ready to connect
- View details
flux-gitopsSkillCloud & infra
Flux GitOps patterns for the homelab Kubernetes platform using ResourceSets.
Ready to connect
- View details
gateway-routingSkillCloud & infra
Gateway API routing, TLS certificates, and WAF configuration for the homelab Kubernetes platform.
Ready to connect
- View details
helm-k8s-manifest-reviewerSkillCloud & infra
Checks Kubernetes manifests and Helm charts for resource limits, readiness probes, and security contexts.
Ready to connect
- View details
lokiSkillCloud & infra
Query Loki API for cluster logs and debugging. Use when searching logs for errors or patterns, investigating pod or service issues, querying Kubernetes events, debugging Flux reconciliation, or running LogQL queries.
Ready to connect
- View details
pre-mortem-facilitatorSkillCloud & infra
Runs prospective failure simulations by assuming a project or deployment has failed and working backward to identify vulnerabilities.
Ready to connect
- View details
promotion-pipelineSkillCloud & infra
Direct build-to-live OCI artifact pipeline from PR merge to cluster deployment.
Ready to connect
- View details
secretsSkillCloud & infra
Secret management patterns for the Kubernetes homelab platform. Covers secret-generator, ExternalSecret, app-secrets Terragrunt module, and cross-namespace replication via kubernetes-replicator.
Ready to connect
- View details
security-testingSkillCloud & infra
Adversarial security testing methodology for the Kubernetes homelab. Covers network policy evasion, authentication bypass, privilege escalation, credential theft, and supply chain attacks.
Ready to connect
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,462 of the 53,895 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.