Plugins

Inference host bring-up + tuning suite — Linux/GPU bare-metal host work that sits beneath any inference framework (vLLM, sglang, TensorRT-LLM). Two phases. Bring-up (nvidia-datacenter-bringup): Ubuntu 24.04 LTS from clean OS to gpu-operator cuda-validator passing — B300/B200/H100/A100/L40S/L4 driver + fabricmanager + NVLSM + DOCA-OFED install order, NVIDIA CUDA repo + DOCA repo + air-gap mirror, MOK + DKMS sign-on-build under Secure Boot, Dell PowerEdge XE9780/XE9785 baseboard firmware via iDRAC Redfish DellOemChassis.ExtendedReset, gpu-operator pre-installed-driver-mode integration. Tuning (gpu-host-tuning): read-only snapshot of CPU power state, C-states, NUMA topology, PCIe link state, GPU settings, kernel boot params, sysctl, ulimits, IRQ affinity, container runtime; optional pinned-host↔GPU memcpy bench (torch + numactl); per-lever cheat-sheets to flip settings (governor, EPP, cpuidle, persistence, ECC, hugepages, intel_iommu, NCCL env, tuned-adm profiles, BIOS guidance for Dell XE / SMC / HPE). Surfaces config gaps that bottleneck LMCache CPU-tier throughput, KV offload, NCCL bandwidth, prefix-cache rebuild.

from BLERBZ/blerbz-plugins

Test and release models with evidence: model-level eval harnesses (synthetic ground truth, LLM-as-judge), GPU inference benchmarking (TTFT, tokens/sec, cost), release gates (explainability, fairness, adversarial robustness), rollout strategies (shadow/canary/bandit), 4-monitor drift stack, and GenAI red-teaming.

from squirrelsoft-dev/squirrelsoft-marketplace

from varaku1012/aditi.code

infision 캔버스(이미지/비디오 생성) MCP 서버 + 크리에이티브 작법 스킬(이미지·영상 프롬프트, AI 영화제작).

from blueif16/amazing-claude-code-plugins

Influencer marketing

from yannickloth/claude-router-system

Infrastructure skills: DigitalOcean inspection, domains, DNS.

Docker containerization patterns for Node.js/TypeScript development and production

GitHub Actions, pipelines, deployment

Turborepo CI pipelines with remote caching and affected detection

Environment configuration, Zod validation

Kubernetes manifests, Helm charts, Kustomize overlays, and resource patterns

TypeScript-native Infrastructure as Code with Pulumi

SST (Ion) infrastructure-as-code — TypeScript-first serverless on AWS with Pulumi, resource linking, and live Lambda dev

Infrastructure as Code with HashiCorp Terraform

Kubernetes, Terraform, Helm, GitHub Actions, AWS, GCP, and Linux infrastructure operations

AWS SDK v3 for TypeScript — modular clients, command pattern, S3, DynamoDB, SQS, Lambda, SNS, Secrets Manager

Cloudflare Workers edge compute platform — Wrangler CLI, KV, D1, R2, Durable Objects, Queues, Workers AI

Netlify deployment platform — serverless functions, edge functions, redirects, forms, Blobs, build plugins

Vercel deployment platform — project configuration, serverless/edge functions, Routing Middleware, cron jobs, environment variables, monorepo setup

Infrastructure standards for Proxmox, Terraform, Ansible including deployment pipeline, IP addressing, and secrets management

from FragmentedPacket/claude-marketplace-test

Use skill if you are creating, auditing, or migrating CLAUDE.md, AGENTS.md, or REVIEW.md instruction files, folder-scoped agent guidance, or cross-agent companion entrypoints.

Use skill if you are onboarding a repo to Jean or authoring jean.json and .worktreeinclude — worktree setup/run/teardown/ports proven in a throwaway test worktree, then documented in AGENTS.md.

Use skill if you are scaffolding or refreshing Makefile targets for local dev, tunnels, deploys, R2 sync, Supabase, Railway, Vercel, or Mac shipping.

Content marketing engineer — blog strategy, SEO, thought leadership, developer content, and content calendar

from 15195999826/LomoMarketplace