Claude Skills by jeremylongshore

'Optimize Cohere costs through model selection, token budgets, and usage

'Implement data privacy for Cohere API calls with PII redaction and compliance.

'Collect Cohere debug evidence for support tickets and troubleshooting.

'Deploy Cohere-powered applications to Vercel, Fly.io, and Cloud Run.

'Configure Cohere enterprise API key management, role-based access, and

'Create a minimal working Cohere example with Chat, Embed, and Rerank.

'Install and configure Cohere SDK authentication with API v2.

'Configure Cohere local development with mocking, testing, and hot reload.

'Optimize Cohere API performance with caching, batching, model selection,

'Execute Cohere production deployment checklist and rollback procedures.

'Implement Cohere rate limiting, backoff, and request queuing patterns.

'Apply Cohere security best practices for API key management and access

'Implement Cohere streaming event handling, SSE patterns, and connector

Collect comprehensive infrastructure performance metrics across compute,

'Process use when you need to work with schema comparison.

Competitive analysis and market positioning partner for Product Managers.

'Performs regulatory gap analysis across 7 compliance frameworks with

Read findings JSONL files from cluster 1-4 skills, deduplicate by fingerprint, group by severity, and compose a deliverable- grade markdown vulnerability report with per-finding sections (title, severity, target, detail, remediation, evidence) and a top-level summary table. The canonical written artifact a customer receives at engagement close; precise, reproducible, machine- checkable against source findings. Use when: closing an engagement, generating an interim report, regenerating after C...

'Configure use when you need to work with auto-scaling.

'Configure use when configuring load balancers including ALB, NLB, Nginx,

'Configure this skill configures service meshes like istio and linkerd

Verify that a penetration test has explicit, written, signed authorization before any scanning begins. Reads a Rules-of- Engagement (ROE) attestation file, validates required fields (authorizer, in-scope targets, time window, emergency contact, signature), checks the signer against an allowlist, and emits a CRITICAL finding if anything is missing. Designed as the first skill the orchestrator routes to. Use when: starting a new engagement, after a scope change, or before any cluster 1-4 scan s...

'Compares two contract versions side-by-side to detect added, removed,

'Orchestrates a comprehensive multi-agent contract review that analyzes

Prepare an OSS contribution locally after a read-only contribution audit. Creates explicitly scoped candidate records, repository dossiers, worktrees, test evidence, and gate results, but never publishes to GitHub. Use when the user has selected an issue and asks to set up, research, implement, test, or draft the contribution. Trigger with "/contribute-prepare" or "prepare this contribution locally".

Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary. Shows the exact target, content, command, commit, and test evidence before any mutation. Use when local preparation is complete and the user explicitly asks to post a claim, create a Design Issue, comment, push a branch, or open a pull request. Trigger with "/contribute-publish" or "publish this prepared contribution".

Read-only OSS contribution audit and routing skill. Inspects public GitHub issues, pull requests, repository policy, duplicate work, and contribution readiness without creating files or changing GitHub state. Use when a user asks what is in flight, whether an issue is suitable, or wants a safe first look before preparing or publishing a contribution. Trigger with "/contribute", "audit my contributions", or "qualify this issue".

'Integrate CoreWeave deployments into CI/CD pipelines with GitHub Actions.

'Diagnose and fix CoreWeave GPU scheduling, pod, and networking errors.

'Deploy KServe InferenceService on CoreWeave with autoscaling and GPU

'Run distributed GPU training jobs on CoreWeave with multi-node PyTorch.

'Optimize CoreWeave GPU cloud costs with right-sizing and scheduling.

'Handle training data and model artifacts on CoreWeave persistent storage.

'Collect CoreWeave cluster diagnostics for support tickets.

'Deploy inference services on CoreWeave with Helm charts and Kustomize.

'Configure RBAC and namespace isolation for CoreWeave multi-team GPU

Diagnose the most expensive silent failure on a CoreWeave multi-node GPU job: GPUDirect RDMA falling back from InfiniBand to TCP. When NCCL drops from NET/IB to NET/Socket, collectives keep running with NO error but throughput collapses (commonly 5-20x slower) while every GPU still bills at full rate — 5x the GPU bill for the same work, invisibly. Paste an NCCL_DEBUG=INFO log (and/or a pod-spec, ibstat, or all_reduce_perf output) and the bundled deterministic script verdicts whether RDMA is a...

Hunt down CoreWeave GPU cost leaks — idle reserved capacity, wrong-GPU-type right-sizing waste, allocated-but-idle instances, and on-demand spend that should be committed — then produce a CFO-grokkable, dollar-ranked FinOps report. CoreWeave ships no cost dashboard and no billing API, so the spend view is built from PromQL against its managed Grafana. Use when a user asks why their CoreWeave GPU bill is high, wants to find wasted GPU spend or idle reservations, or needs a GPU FinOps cost repo...

Triage a dead or degraded GPU on a CoreWeave node fast — decide reschedule vs GPU-reset vs node-reboot vs RMA from an Xid code or a pasted dmesg / nvidia-smi blob, so a bad card does not silently kill a multi-day training run. Use when a GPU throws an Xid error, a node "fell off the bus", a training run stalls or NCCL hangs on one rank, or you need to know whether to replace, reset, or just reschedule. Trigger with "xid error", "gpu fell off the bus", "coreweave gpu dead", "should I RMA this ...

'Deploy a GPU workload on CoreWeave with kubectl.

'Incident response runbook for CoreWeave GPU workload failures.

'Configure CoreWeave Kubernetes Service (CKS) access with kubeconfig

'Set up local development workflow for CoreWeave GPU deployments.

'Configure CoreWeave across development, staging, and production environments.

'Set up GPU monitoring and observability for CoreWeave workloads.

'Optimize CoreWeave GPU inference latency and throughput.

'Production readiness checklist for CoreWeave GPU workloads.

'Production-ready patterns for CoreWeave GPU workload management with

'Secure CoreWeave deployments with RBAC, network policies, and secrets

'Upgrade CoreWeave deployments and migrate between GPU types.