CMEM Pro
claudeCMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Agent skills and MCP configuration for deploying and managing Observe's observability infrastructure
Plugin observe from marketplace observe in observeinc/skills. Commands read from the repo's manifest — 4 days ago.
alert-investigationSRE incident response and root-cause analysis for alerts, pages, incidents, and escalated problems. Load FIRST, together with any reference skills, when: (1) an alert, monitor, or page is firing or was received (PagerDuty, Alertmanager, [FIRING]) (2) an incident record is shared (incident ID, SEV or
debug-k8s-collectionTroubleshoot and debug Observe Agent data collection on Kubernetes. Use this skill whenever the user reports any K8s-side problem with Observe — pods crashing, stuck Pending, ImagePullBackOff, "no data in Observe", missing datastreams, suspected token/secret issues, endpoint reachability failures, o
debug-linux-host-collectionTroubleshoot and debug Observe Agent data collection on Linux hosts. Use this skill whenever the user reports any host-side problem with Observe — the agent failing to start, `observe-agent status` reporting errors, `init-config` failing with unknown flags, "no data in Observe" from a Linux host, fl
deploy-k8s-explorerDeploys a from-scratch Kubernetes onboard to Observe (datastreams, content, ingest token, and helm chart). Use this skill whenever the user mentions onboarding a cluster or setting up Kubernetes in Observe from scratch. Do not load setup-k8s-collection first; if datastreams and an ingest token alrea
deploy-linux-host-explorerFull onboard of a Linux host to Observe, including the agent install: creates datastreams, content, and an ingest token, then installs observe-agent on the host. Use this skill for "onboard my host", "set up a Linux server in Observe from scratch", or any request that needs both Observe-side resourc
generate-opalContains dataset kind selection, column selection rules, core syntax, and the skill index. NEVER generate OPAL, and NEVER invoke an opal-* reference, without first loading this skill. On the Observe CLI, inspect the schema with `observe dataset list`/`view` and, when the caller wants a query run aga
observe-cliUse the Observe CLI (`observe`) to investigate production systems and pull telemetry. Load this skill — do not grep a source checkout — whenever the user wants to: search or tail logs; query metrics; explore traces and spans; correlate events across services, hosts, containers, or Kubernetes resourc
opentelemetry-auto-instrumentationInstalls and configures OpenTelemetry auto-instrumentation for applications written in Java, .NET, Node.js, Python, Ruby. Use when instrumenting applications with opentelemetry auto-instrumentation, auditing existing auto-instrumentation implementations, migrating from vendor locked instrumentation
opentelemetry-manual-instrumentationAdd, change, or debug OpenTelemetry (OTel) instrumentation in code: custom spans, metrics, logs, attributes, context propagation, and resource attributes. Use when writing, changing, reviewing, or debugging manual instrumentation, including OTel SDK setup.
opentelemetry-validationCanned queries for various APM features in Observe. Use to validate auto-instrumentation, or when validating or troubleshooting OpenTelemetry instrumentation for a service sending telemetry to Observe.
outlier-detection-analysisPhi-coefficient of field values vs a bad/good cohort for why X is slow/failing or which attributes they share/have in common, not a plain top-N ranking.
query-card-visualizationHow to fill in a query card's `visualizationTemplate` (the JSON object that renders a chart). Load this whenever the user asks for a chart, graph, plot, trend, "show me over time", ranking, single number/KPI, scatter, waterfall, or map. Acts as the directory for the per-chart JSON schemas in its ref
setup-k8s-backendCreate Observe-side resources for Kubernetes Explorer: datastreams, content packages, and an ingest token. Use this skill when the user wants those tenant objects and no collection-agent install — recreating a datastream, adding a missing token, or provisioning backend objects after a manual removal
setup-k8s-collectionInstalls the Observe Agent helm chart on Kubernetes when datastreams and an ingest token already exist. Use this skill whenever the user mentions helm values, observe/agent install, or collection setup after the backend is in place. Do not use this for a from-scratch onboard — that is deploy-k8s-exp
setup-linux-host-backendCreate Observe-side resources for Host Explorer: datastreams, content packages, and an ingest token. Use this skill when the user wants those tenant objects and no collection-agent install — recreating a datastream, adding a missing token, or provisioning backend objects after a manual removal.
setup-linux-host-collectionInstall and configure the Observe Agent on a Linux host. Use this skill whenever the user mentions installing observe-agent, configuring host monitoring on Ubuntu/Debian or RHEL/CentOS, running `init-config` for the agent, upgrading or uninstalling the observe-agent package, or forwarding applicatio
observeconnects to: https://${user_config.observeBaseUrl}/v1/ai/mcp
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Structured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemetry
2 skills · 1 command · 1 agent
Install the "AAS Observability & Incident Response" editorial skill bundle for Claude Code.
12 skills
Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code, use core services, and complete common tasks.
27 skills · 1 MCP server
Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization
8 skills · 7 agents
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to complement the Honeycomb MCP server.
11 skills · 1 command · 2 agents · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.