dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-22 00:14
Deployment & operations
12,150 results
dynamo-troubleshoot
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use…
tao-run-on-kubernetes
Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem…
aws-cloud-security-essentials-lab
Educational lab repository for AWS cloud computing security fundamentals including IAM, VPC, encryption, monitoring, and incident detection
initialise-skills
Scan the host repo a set of agent skills is installed into and reconcile every installed skill's config.json with detected facts — base branch, monorepo…
devops-troubleshooter
Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing,…
container-native-deployment
Use when packaging a Spring Boot 3 application as an OCI image or GraalVM native executable. Covers buildpacks, layered images, JVM containers, AOT hints,…
observability-cost-governance-review
Design and audit observability cost governance across logs, metrics, traces, events, profiling, session replay, analytics, retention, sampling, cardinality,…
reliability-incident-learning-review
Design and audit reliability incident learning, postmortems, incident timelines, contributing factors, action items, recurrence prevention, customer impact,…
pipeline-plugin-development
Used when developing BK-CI pipeline plugins, for example adding an Atom, writing `task.json`, defining inputs and outputs, handling multilingual runtimes, debugging, and publishing plugins. Prefer this when the user wants to work on the plugin itself rather than the executor or pipeline model.
worker-module-architecture
Used when handling the BK-CI Worker executor, such as task claiming and execution, plugin running, log reporting, environment variable passing, and artifact archiving. Prefer this when the user wants to change the Worker execution pipeline rather than plugin definitions or scheduling policies.
terraform-state
Use when managing Terraform state files, remote backends, and state locking for infrastructure coordination.
routeros-netinstall
MikroTik netinstall-cli for automated RouterOS device flashing. Use when: automating netinstall, writing scripts that invoke netinstall-cli, building…
defending-kubernetes
Harden and monitor a Kubernetes cluster against the attacks that actually happen — RBAC least privilege and escalation paths, Pod Security Admission…
gpc-vitals-monitoring
Use when monitoring Android app health metrics from Google Play. Make sure to use this skill whenever the user mentions gpc vitals, gpc watch, gpc status,…
chinese-git-workflow
Domestic Git platform configuration reference — differences in SSH/HTTPS/credentials/CI integration and mirror sync configuration for Gitee, Coding.net, JiHu GitLab, and CNB. Only invoked when the user explicitly uses /chinese-git-workflow; do not trigger automatically based on context.
developer-experience
Developer Experience specialist for tooling, setup, and workflow optimization. Use when setting up projects, reducing friction, improving development…
performance
Comprehensive performance specialist covering analysis, optimization, load testing, and framework-specific performance. Use when identifying bottlenecks,…
gitlab-automation
Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for…
hodlmm-move-liquidity
HODLMM Move-Liquidity & Auto-Rebalancer — withdraw from drifted bins, re-deposit around the current active bin. Includes autonomous monitoring loop.
alibabacloud-rds-mysql-inspection
Batch health inspection for Alibaba Cloud RDS MySQL instances. Supports single, multiple, or all-instance global scan with configurable time window (default 7…
iot-cloud
Cloud IoT platforms: AWS IoT Core, GCP IoT Core, Azure IoT Hub, fleet management
whale-tracking
Monitor whale trades on Polymarket and crypto chains (Solana, ETH, Polygon, ARB, Base, OP)
gpc-app-recovery
Create, deploy, and manage app recovery actions for Google Play using gpc. Use when responding to critical app issues that require user-facing recovery.