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
2,232 results · page 74 of 75
- View details
ghostingSkillCloud & infra
Ghosting-free dating for AI agents — no ghosting, no disappearing, no silence. Anti-ghosting connections with presence tracking, ghosting-proof conversations, and agents who actually respond on inbed.ai. 消失不回、幽灵。Anti-ghosting, sin fantasmas.
Ready to connect
- View details
post-deploy-canary-monitorSkillCloud & infra
Monitors production after the deploy closes, comparing metrics and screenshots against the pre-deploy baseline. Detects silent regressions (console errors, perf drop, broken pages) within the first hours/days. Unlike skill 43 (canary-deployment), which performs gradual promotion during the deploy: t
Ready to connect
- View details
sota-cloud-infrastructureSkillCloud & infra
State-of-the-art cloud infrastructure architecture (2026). Applies when designing, building, or auditing cloud environments on AWS, GCP, or Azure — account/project structure and landing zones, IAM and workload identity, VPC/network design, DNS/TLS/CDN, compute selection (serverless vs containers vs
Ready to connect
- View details
sota-confidential-computingSkillCloud & infra
State-of-the-art confidential computing and cryptographic PETs (2026) for BUILDING and AUDITING systems that protect workloads and data in use from the infrastructure they run on — the inverse of sandboxing. Covers TEE selection (AMD SEV-SNP, Intel TDX, ARM CCA realms, SGX enclaves, AWS Nitro Enclav
Ready to connect
- View details
sota-kubernetesSkillCloud & infra
State-of-the-art Kubernetes platform security and operations (2026) for cloud-managed (EKS/GKE/AKS) and self-hosted clusters (kubeadm, k3s/k0s, Talos). Use when building, operating, hardening, or auditing the cluster PLATFORM layer: control plane and etcd, API server/kubelet, RBAC, admission control
Ready to connect
- View details
sota-network-securitySkillCloud & infra
State-of-the-art network security as a discipline (2026) for BOTH designing/building secure networks AND auditing segmentation and exposure. Use for zero-trust architecture, network segmentation and blast-radius control, Kubernetes NetworkPolicy/CiliumNetworkPolicy depth, service mesh and mTLS, edge
Ready to connect
- View details
static-analysisSkillCloud & infra
Automated code scanning skill for vulnerabilities, bugs, and code smells via Semgrep and CodeQL. Use before every release, on large PRs, or when you suspect a recurring class of bug. Triggers: "semgrep", "codeql", "static analysis", "security scan", "SAST", "sweep", "pre-deploy.
Ready to connect
- View details
yolo-exportSkillCloud & infra
Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, Core AI, OpenVINO, LiteRT, NCNN, ExecuTorch, and NPUs (RKNN, QNN, Hailo, Ascend, IMX, Axelera, DeepX), FP16/INT8 quantization, benchmarking
Ready to connect
- View details
yolo-inferenceSkillCloud & infra
Use when testing, running, or deploying Ultralytics YOLO inference in Platform or code on images, video, webcams, or streams — Platform Predict and dedicated endpoints, model.predict()/yolo predict, Results API boxes/masks/keypoints, persistent tracking, annotated video, and Solutions such as counti
Ready to connect
- View details
architect-diagramSkillCloud & infra
Use when the user asks for a diagram of a system, integration, flow, state, data model, deployment topology, roadmap, prioritization matrix, or decomposition. Triggers on "show me", "draw", "diagram of", or artifact-shaped nouns like "sequence", "C4 Container view", "state machine", "roadmap", "2×2"
Ready to connect
- View details
base-cn-registry-mirror-strategySkillCloud & infra
Domestic registry mirrors and tiered proxy strategy (Docker / Debian / Alpine / Node / Python / Maven / Gradle / Go) for maintainable acceleration in Dockerfiles and CI.
Ready to connect
- View details
br-network-securitySkillCloud & infra
Configure Better Route 1.1 trusted-proxy client IP resolution and CIDR allowlists. Use behind Cloudflare, nginx, load balancers, or reverse proxies when authorization, rate limiting, or audit data depends on the real client IP.
Ready to connect
- View details
ck-initSkillCloud & infra
Initialize Context King in the current repository, or migrate a repo from a legacy per-repo deployment to the global install.
Ready to connect
- View details
contract-acquisitionSkillCloud & infra
Acquire a platform's or library's real contract from its own toolchain oracles before authoring against an unfamiliar one — infrastructure, a CLI invocation, code on a managed runtime, or code against an unfamiliar framework or third-party library whose contract you don't hold. Triggers on "deploy t
Ready to connect
- View details
devlab-integration-fullstackSkillCloud & infra
Full-stack integration testing expert skill. Supports multi-service Docker Compose deployment scenarios, using Testcontainers + Mock Server for end-to-end integration testing.
Ready to connect
- View details
docker-via-wslSkillCloud & infra
Use when YOU (the AI agent) are running on Windows OUTSIDE WSL (Git Bash/MSYS/PowerShell shell) and need to run ANY docker / docker compose command. Docker Desktop runs on the WSL2 engine, so commands must be re-issued INSIDE WSL via wsl.exe -- running them from the Windows shell on a network/SMB dr
Ready to connect
- View details
flags-sdkSkillCloud & infra
Guide for feature flags and A/B tests with the Flags SDK (`flags` npm package) and Vercel Flags. Use when: declaring flags with `flag()`, using `vercelAdapter` or `vercel flags` CLI (add, list, enable, disable, inspect, archive, rm, sdk-keys), setting up providers/adapters (Vercel, Statsig, LaunchDa
Ready to connect
- View details
forge-app-reviewSkillCloud & infra
Performs a lightweight pre-release readiness review of Atlassian Forge apps across manifest/module wiring, architecture, runtime compatibility, dependency posture, tests, deploy readiness, and obvious security, cost, or reliability smells. Use when the user asks "review my Forge app", "pre-deploy ch
Ready to connect
- View details
forge-debuggerSkillCloud & infra
Diagnoses and fixes issues in Atlassian Forge apps. Use this skill whenever a Forge app has errors, crashes, shows blank UI, fails to deploy, doesn't appear after installation, has permission issues, or produces unexpected output. Trigger on any mention of forge logs, forge deploy errors, resolver e
Ready to connect
- View details
gemini-blogSkillCloud & infra
Configure or debug LLM blog post generation using Vercel AI SDK and Google Gemini. Use when updating blog generation prompts, fixing AI integration issues, modifying content generation logic, or working with structured output schemas.
Ready to connect
- View details
infra-system-env-opsSkillCloud & infra
Infrastructure system and environment operations skill. Covers port mapping/forwarding, iptables, firewalld, portproxy, and SSH tunnel (formerly the net-ops capabilities), as well as enterprise-grade system reliability practices such as unified Monit watchdog deployment, automatic recovery from serv
Ready to connect
- View details
infra-woodpecker-pipeline-opsSkillCloud & infra
Design, inspect and operate portable Woodpecker CI pipelines with explicit repository and deployment boundaries.
Ready to connect
- View details
ml-experiment-standardsSkillCloud & infra
Always invoke for training, validating, tuning, benchmarking, or claiming readiness of a predictive model. Covers leakage audits, spatial and grouped splits, metrics, reproducibility, and honest reporting. Invoke especially when spatial dependence, split design, or deployment geography is unknown; u
Ready to connect
- View details
monitoringSkillCloud & infra
Monitor Vercel deployments, debug production issues, check logs, and understand logging patterns. Use when investigating errors, checking deployment logs, debugging failures, or improving observability.
Ready to connect
- View details
release-checkSkillCloud & infra
Pre-release checklist for Forge — verify, version bump, changelog, docs, docker build, smoke test. Run before tagging v*.
Ready to connect
- View details
serverless-securitySkillCloud & infra
What a function-as-a-service platform changes: an execution environment reused between invocations so /tmp and module globals outlive a request, an event envelope that is attacker-influenced whichever trigger delivered it, encrypted-at-rest configuration that the control-plane API still returns in c
Ready to connect
- View details
sonarqube-checkSkillCloud & infra
SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read the real gate + issues, fix by rule id, re-scan and diff. A linter's green build is a pre-check, never the gate.
Ready to connect
- View details
workflow-managementSkillCloud & infra
Create, debug, or modify Vercel WDK workflows for data updates and social media posting in the web application. Use when adding new automated jobs, fixing workflow errors, or updating scheduling logic.
Ready to connect
- View details
asset-specSkillCloud & infra
Generate artifact specifications from CDDs and related docs. Game: visual/audio/VFX asset specs and AI prompts. Product: API schema, CLI help, docs asset, config sample, migration, deployment, or package artifact specs.
Ready to connect
- View details
launch-checklistSkillCloud & infra
Complete launch readiness validation. Game: platform certification, store metadata, content, community. Product: deployment strategy, rollback plan, on-call, monitoring.
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.
53,585 of the 54,017 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.