AGENT SKILLS · 任务装备

值得安装的 Agent Skills

汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。

目录范围: 已验证
Skills: 22,403
仓库: 3432
最近同步: 2026年10月27日

22,403 Skills

helm-charts

Create, manage, and deploy Helm charts for Kubernetes package management. Build reusable chart templates, manage releases, configure values, and use Helm repositories. Use when packaging Kubernetes applications or managing K8s deployments with Helm.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

incident-management

Implement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews. Use when managing production incidents.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

jenkins

Create and manage Jenkins CI/CD pipelines, configure agents, manage plugins, and automate builds. Use when working with Jenkins servers, creating Jenkinsfiles, or setting up build automation for enterprise environments.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

kustomize

Customize Kubernetes manifests without templating using Kustomize. Create base configurations with environment overlays, manage configuration variants, and patch resources declaratively. Use when managing Kubernetes configurations across multiple environments without Helm.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

linux-hardening

Apply CIS benchmarks and secure Linux servers. Configure SSH, manage users, implement firewall rules, and enable security features. Use when hardening Linux systems for production or meeting security compliance requirements.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

llm-caching

Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

llm-cost-optimization

Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

llm-fine-tuning

Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP. Covers dataset prep, training runs, and model export.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

llm-inference-scaling

Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling. Handle traffic spikes, implement queue-based scaling, and optimize cost with spot instances for AI workloads.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

load-balancing

Configure load balancers and traffic distribution. Implement health checks and SSL termination. Use when distributing traffic across servers.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

mac-mini-llm-lab

Configure a Mac mini as a reliable local LLM server with remote access, observability, and power-safe operation. Use when building an always-on private AI inference server on Apple Silicon.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

model-registry-governance

Establish model registry standards, governance controls, metadata schemas, approvals, and lifecycle policies for enterprise AI deployments.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

mongodb

Administer MongoDB databases. Configure replica sets, sharding, and backups. Use when managing MongoDB deployments.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

multi-tenant-llm-hosting

Design secure, multi-tenant LLM hosting platforms with tenant isolation, quotas, billing attribution, noisy-neighbor protection, and per-tenant policy controls.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

mysql

Administer MySQL/MariaDB databases. Configure replication and optimize performance. Use when managing MySQL deployments.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

object-storage

Configure object storage with S3, GCS, and MinIO. Implement lifecycle policies and access controls. Use when managing object storage.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

openclaw-local-mac-mini

Set up OpenClaw locally and run it reliably on a Mac mini for private, always-on local agent workflows.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

openclaw-security-hardening

Harden OpenClaw self-hosted environments with baseline host controls, auth tightening, secret handling, network segmentation, and safe update/rollback workflows. Use when deploying OpenClaw in home labs, startups, or production-like local AI infrastructure.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

openshift

Manage Red Hat OpenShift clusters and deployments. Configure projects, routes, builds, and deploy applications using OpenShift-specific features. Use when working with OpenShift Container Platform or OKD for enterprise Kubernetes.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

planetscale

Operate MySQL-compatible databases on PlanetScale with branching workflows, safe migrations, and production rollouts.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

platform-engineering

Build internal developer platforms (IDPs) with self-service infrastructure, golden paths, and developer portals using Backstage, Crossplane, and score.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

podman

Manage containers using Podman, the daemonless container engine. Run rootless containers, create pods, manage images, and use Docker-compatible commands. Use when working with Podman or requiring rootless container operations.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

policy-as-code

Implement policy as code with OPA, Sentinel, and Kyverno. Automate policy enforcement in CI/CD and infrastructure. Use when enforcing compliance through automation.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

postgresql

Administer PostgreSQL databases. Configure replication, backups, and performance tuning. Use when managing PostgreSQL deployments.

1小时安装量: 1
GitHub Stars: 1168
最近更新: 5月22日

MIT1 文件

查看详情 →