vector-index-tuning
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
⌘ K
Newest skills
38 skills
team-request
How team members request infrastructure connection info and handle secrets in team mode
incident-investigate
Investigate an alert, page, or production symptom in an incident channel, or in a team's oncall / monitoring channel — in an alert's own thread, or under a top-level message reporting one — and report findings a human can verify. Ordinary conversation, questions, links and chatter are not alerts: leave those alone — a post that is clearly none of these does not select this skill outside a covered feed channel, where the sorting ladder judges it instead. Use when an alert or page lands, when error rate, latency, or saturation is up, when someone asks "why is X broken", "is this real", "is anyon
hermes-tweet
Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated private or state-changing operations. Use this skill when installing Hermes Tweet, researching X/Twitter accounts, monitoring launch signals, investigating mentions, auditing giveaways, or preparing gated X operations. Use proactively when a Hermes Agent workflow needs current X/Twitter context. Requires XQUIK_API_KEY for read and action tools.
aspire-monitoring
**ANALYSIS SKILL** - Observe Aspire apps: logs, traces, metrics, resource state, telemetry export, browser telemetry, and the standalone dashboard. Routes between local Aspire CLI, AKS workload diagnostics, and deployed Azure resource health. USE FOR: aspire logs, aspire otel logs, aspire otel traces, aspire otel spans, aspire describe, aspire ps, aspire export, aspire dashboard run, describe --include-hidden, browser logs in dashboard, terminal view, DevTunnel URLs, WithBrowserLogs, App Insights query, AKS pod logs, container app logs. DO NOT USE FOR: start/stop/wait (use aspire-orchestration
incident-init
Automatic init the first time Claude acts in an incident or alerts channel — a channel named like #inc-…, #incident-…, #sev0-…/#sev1-…, or one whose recent messages are pages or alerts — posted by PagerDuty, Opsgenie, incident.io, Datadog, Sentry or Grafana, or typed by people relaying them; ordinary talk about having been paged is not an alert — and that is not already set up as a team's oncall / monitoring channel. Run it once per channel, on first contact (just invited, first @-mention, channel just created), before doing whatever was asked: load the oncall memory that oncall setup wrote to
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
system-type-multi-tenant-saas
Domain patterns for multi-tenant SaaS platforms — tenant isolation models, data partitioning, noisy neighbor mitigation, per-tenant configuration, billing metering, and failure modes. Use when designing or evaluating SaaS products that serve multiple customers from shared infrastructure.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
system-type-ml-serving
Domain patterns for ML/AI serving and training systems — model serving, feature stores, training pipelines, experiment tracking, A/B testing, GPU scheduling, and failure modes. Use when designing or evaluating machine learning infrastructure, model serving platforms, or AI-powered product features.
service-mesh-observability
Implement comprehensive observability for service meshes including distributed tracing, metrics, and visualization. Use when setting up mesh monitoring, debugging latency issues, or implementing SLOs for service communication.
instrument-observability
Instruments Microsoft Agent 365 observability into existing .NET AgentFramework, Node.js, or Python agents. Adds OTel-based tracing, context propagation, A365 exporter, manual instrumentation scopes (InvokeAgentScope, InferenceScope, ExecuteToolScope — required for store publishing), and updates configuration files. Asks a two-stage question — agent kind (AI Teammate or Agent (Non AI Teammate)) and auth mode — to determine the correct token path: OBO (`obo` / `agentic-user`) or Service Principal (`s2s`) (FMI 3-hop token chain with Power Platform scope supported for .NET, Node.js, and Python —
task-coordination-strategies
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
a365-code-validator
Validates and optionally fixes Agent 365 observability code so an agent actually emits MAC Activity telemetry. Use when an Agent 365 agent's telemetry isn't reaching MAC Activity or Defender, when spans export (HTTP 200 / "sent") but Activity stays empty, when the caller or agent id looks wrong in reporting, or to pre-flight whether an agent will emit MAC Activity before shipping. Diagnoses and fixes existing instrumentation; do NOT use it to add observability from scratch — use instrument-observability for that. Checks exporter activation, runtime agent-identity binding (vs blueprint id), the