inventory-operations
Stock, capacity, and availability monitoring, acting on low-stock and slow-mover alerts, triaging order exceptions such as delays, return spikes, and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Deployment & operations
12,753 results
observability
Full-stack observability architect for Prometheus, Grafana, OpenTelemetry, distributed tracing (Jaeger/Tempo), SLIs/SLOs, error budgets, and alerting. Use for…
paperclip-coolify-deployer
Deploy and self-host Paperclip — the open-source AI agent orchestration dashboard — on Coolify v4. Use this skill immediately whenever the user mentions…
ios-build-sign
Takes an iOS source tree to a signed .ipa ready to upload. Covers macOS and Xcode host checks, workspace vs project discovery with xcodebuild -list -json and…
release-automation
The automate/human split for a mobile release — which release steps an agent can do unattended, which need a named credential first, and which are permanently…
external-gitcode-ascend-fault_diagnose
Ascend fault diagnosis tool, providing the full process of log collection, cleaning, and diagnosis. Supports cluster/standalone/super-node fault diagnosis, invoked when users need to troubleshoot NPU training and inference faults or performance degradation issues.
external-gitcode-ascend-large_scale_deploy
Automated large-scale cluster installation and deployment tool for batch deployment of ascend-deployer components. Invoke when users need to deploy components across clusters or perform batch installation operations.
ascend-mmcv-install
Compile and install mmcv-full in an Ascend NPU container, with NPU operator support. This serves as a prerequisite step before installing other OpenMMLab libraries that require mmcv as a dependency.
ascend-mmdet3d-install
Install mmdetection3d (including the mmsegmentation dependency) in an Ascend NPU container. Suitable for development of 3D object detection models.
ascend-mmlab-install-suite
Install the OpenMMLab series library suite (mmcv/mmdet/mmdet3d/detectron2) in the Ascend NPU environment, supporting a local + remote hybrid development mode
atb-nnal-installer
Ascend NPU NNAL (ATB acceleration library) installation skill. Depends on cann-operator-env-config to provide the Toolkit+Kernels environment; this skill is only responsible for installing the NNAL package, configuring environment variables, and verification.
model-training
Model training on Ascend NPU. Invoke when user wants to launch training script and monitor training progress.
ssh-dev-suite
SSH remote development suite: connection management, command execution, file transfer, deployment, tunneling, debugging
amplify-lambda-node24-upgrade
Upgrade an AWS Amplify backend Lambda function from the Node.js 20 runtime (nodejs20.x) to Node.js 24 (nodejs24.x), including the runtime config change AND the…
provider-setup
Reports which delegation CLIs are installed and authenticated, installs missing ones, and stores the result. Use before delegating or when a provider errors.
monitoring-darkweb-sources
Monitors dark web forums, marketplaces, paste sites, and ransomware leak sites for mentions of organizational assets, leaked credentials, threatened attacks,…
auvik-performance
Auvik time-series performance stats for devices, interfaces, services, and hardware components — plus SNMP poller history for custom OID values. Use when…
eve-lab-topology-discovery
Gather missing requirements for EVE-NG topology design. Use when the request is vague or incomplete, when you need discovery questions, defaults, trade-off…
eve-lab-topology-validation
Validate EVE-NG topology designs and enforce final delivery structure. Use when reviewing a design, checking build readiness, producing the final design…
eve-ng-lab-management
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives,…
halo-asset-context
Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only. Use when investigating a Halo asset, checking a…
halo-change-request
Open a change request in HaloPSA / HaloITSM through a discover-preview-confirm-submit workflow, with the confirmed change ticket type cached in Memory. Use…
multivendor-device-query
Query normalized device facts across mixed vendors or platforms without a dedicated NetClaw server. Use pyATS or Junos skills for their platform-specific…
prisma-sdwan-status
Monitor Prisma SD-WAN element health, software versions, events, and alarms