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 67 of 75
- View details
openocd-jlink-stlink-debugSkillCloud & infra
Use when debugging OpenOCD, J-Link, ST-Link, CMSIS-DAP, probe connection, reset scripts, flash algorithms, GDB attach, semihosting, RTT, or SWD/JTAG failures
Ready to connect
- View details
container-operationsSkillCloud & infra
Build, inspect, debug, and validate Docker or Podman images, containers, networks, volumes, and Compose stacks.
Ready to connect
- View details
tryworld-paperSkillCloud & infra
Create branded 试界TryWorld AI-knowledge videos in the fixed "Paper Algorithm" (纸上算法) style with HyperFrames. Input is a Chinese voiceover script and optional images; output is a 16:9 horizontal video with Azure YunxiNeural (真·云希) voiceover, word-synced captions, ink/paper animations and unified trans
Ready to connect
- View details
agentclash-agent-deployment-setupSkillCloud & infra
Use when creating, selecting, or diagnosing AgentClash agent deployments for runs, including ready build versions, runtime profiles, provider/model wiring, deployment IDs, workspace context, and run compatibility.
Ready to connect
- View details
agentclash-eval-runnerSkillCloud & infra
Use when starting, following, inspecting, or reporting AgentClash eval runs with the CLI, especially eval start, run create, deployment selection, input set selection, suite-only scopes, repetitions, events, rankings, failures, and scorecards.
Ready to connect
- View details
agentclash-runtime-resources-setupSkillCloud & infra
Use when configuring AgentClash workspace secrets, provider accounts, provider models, runtime profiles, workspace tools, and readiness checks required before agent builds, deployments, evals, or runs.
Ready to connect
- View details
ci-performanceSkillCloud & infra
Nightly CI and deploy optimizer - measure the real push-to-green-production critical path from GitHub Actions and production deploy timestamps, then land every ranked, evidence-backed optimization that passes the rails on the dated PR branch (one commit per experiment so each stays attributable) wit
Ready to connect
- View details
domain-cloud-nativeSkillCloud & infra
Use when building cloud-native apps. Keywords: kubernetes, k8s, docker, container, grpc, tonic, microservice, service mesh, observability, tracing, metrics, health check, cloud, deployment, 云原生, 微服务, 容器
Ready to connect
- View details
security-nightlySkillCloud & infra
Nightly security auditor and authorized local penetration tester - daily audit that scans the source delta since the last audited SHA with pinned deterministic tools plus (when operator-bootstrapped) Vercel DeepSec and the official Claude Security plugin, independently verifies every candidate again
Ready to connect
- View details
suno-api-clientSkillCloud & infra
Deploy and operate the unofficial gcui-art/suno-api service locally, then call its music-generation endpoints from scripts or agent workflows. Use when a user wants to self-host a Suno-compatible API with Docker, check quota/health, generate music or lyrics, poll song status, extend clips, or debug
Ready to connect
- View details
byof-onboardSkillCloud & infra
Use when onboarding an OSS repo via BYOF — containerize on Ubuntu or Isaac Lab, push to an operator-controlled or authorized GHCR registry, and smoke on live Kubernetes.
Ready to connect
- View details
cosmosSkillCloud & infra
Use when working on Cosmos world model serving, inference, serverless training smoke validation, backend selection, or rendering limitations.
Ready to connect
- View details
detection-trainingSkillCloud & infra
Use to train and evaluate Faster R-CNN detectors from LanceDB materialized views (BDD100K failure-mode slices) — direct versus deployed-service execution, the mandatory label map for string categories, and checkpoint discovery at eval time.
Ready to connect
- View details
dsa-notice-actionSkillCloud & infra
Prüfung und Gestaltung des Melde- und Abhilfeverfahrens (Notice-and-Action) nach Art. 16 DSA samt Begründungspflicht Art. 17 DSA und Haftungsprivileg des Hosting-Anbieters Art. 6 DSA – Meldewege, Kenntniserlangung, Reaktionsfristen, Folgen für die Haftung. Use when ein Hosting-Anbieter oder eine Onl
Ready to connect
- View details
fleetSkillCloud & infra
Use to deploy or operate a fleet of Nebius Managed Kubernetes (k8s-training) clusters across one or many projects in a tenant from an npa.fleet/v0.0.1 spec — including strict capacity-block-backed GPU pools, identical and/or custom clusters, create-on-demand projects, and a k8s-training recipe sourc
Ready to connect
- View details
genesisSkillCloud & infra
Use when working on Genesis simulation, RL teacher training, visual demo generation, or related serverless/EGL behavior.
Ready to connect
- View details
golden-evalSkillCloud & infra
Use to prove a workbench container image actually works — the per-container hello-world manifest, dry-run/local/serverless execution tiers, batch runs across every image, and the offline manifest validation that gates CI.
Ready to connect
- View details
gpu-cluster-provisioningSkillCloud & infra
Use when creating or repairing a GPU Kubernetes cluster for npa — the managed-image vs GPU-Operator driver decision, why operator mode is unsafe on NVSwitch, the post-apply health gates (fabric, CUDA vectorAdd, stability window), and triage for nodes that come up without working GPUs.
Ready to connect
- View details
grootSkillCloud & infra
Use when working on NVIDIA GR00T deployment, model download, finetuning, evaluation, serving, inference, conversion, status checks, validation, routing, or CUDA alignment.
Ready to connect
- View details
health-preflightSkillCloud & infra
Use before any deploy, image build, or GPU submit to prove credentials and gated-model access up front with `npa workbench health preflight` and `npa workbench health access`, instead of discovering a missing token mid-run.
Ready to connect
- View details
isaac-labSkillCloud & infra
Use when working on Isaac Lab RL simulation, deployment, SkyPilot workflows, or customer custom-fork support.
Ready to connect
- View details
npa-agentSkillCloud & infra
Use when operating the NPA agent VM, chat UX, API grounding, bootstrap deployment, or verify-live checks.
Ready to connect
- View details
provider liabilitySkillCloud & infra
Examination of the liability of service providers for third-party/user-generated content: limited liability (§ 7 DDG in conjunction with Art. 4–8 DSA), hosting (Art. 6 DSA), no general monitoring obligation (Art. 8 DSA), right to block (§ 8 DDG), information (§ 10 DDGA), disturber liability and noti
Ready to connect
- View details
soperatorSkillCloud & infra
Use to deploy or operate a Nebius soperator (Slurm-on-Kubernetes) cluster from npa — the npa.soperator/v0.0.1 spec, multi-preset worker pools, per-pool Docker/Enroot image cache, quota preflight, and post-deploy fixes.
Ready to connect
- View details
verbotene-ki-praktikenSkillCloud & infra
Examination of prohibited AI practices under Art. 5 AI Act – manipulative and exploitative systems, social scoring, biometric real-time remote identification, exceptions and fine risk under Art. 99 AI Act. Use when a company or authority needs to check whether a planned or deployed AI system is unt
Ready to connect
- View details
workbench-toolSkillCloud & infra
Use when adding, changing, deploying, or calling any NPA workbench tool; captures the API/CLI/SDK/container architecture and data-flow contract.
Ready to connect
- View details
add-hub-templateSkillCloud & infra
Add or update a Blaxel Sandbox Hub image/template under hub/. Use when adding a new hub image, sandbox image, runtime image, template.json, Dockerfile, hidden/internal image, or workflow-dispatch build option in the blaxel-ai/sandbox repository.
Ready to connect
- View details
aks-deployment-troubleshooterSkillCloud & infra
Diagnose and fix Kubernetes deployment failures, especially ImagePullBackOff, CrashLoopBackOff, and architecture mismatches. Battle-tested from 4-hour AKS debugging session with 10+ failure modes resolved.
Ready to connect
- View details
blueprint-skill-creatorSkillCloud & infra
Creates blueprint-driven skills for infrastructure and deployment tasks. This skill should be used when creating new skills that require templates, patterns, or reference configurations (e.g., Dockerfiles, Helm charts, Kubernetes manifests, CI/CD pipelines). It enforces impact analysis before contai
Ready to connect
- View details
check-deploySkillCloud & infra
Watch CI until the "Build and Push Sandbox" workflow completes. For dev deployments, watches the develop branch. For prod deployments, watches the latest tag. Use after merging into develop or pushing a release tag.
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.