By abossard
Azure Monitor Health Model agent skills — end-to-end workflow from resource discovery to deployment using only the standard az CLI. Six skills: discovery, architecture, design, deploy, orchestrator, and signal catalog.
Map discovered Azure resources into a dependency graph and Mermaid diagram, then propose an entity hierarchy. WHEN: 'map architecture', 'draw resource graph', 'show resource dependencies', 'propose health model hierarchy'. PREREQUISITE: healthmodel-discovery must have run first — this skill refuses to start without `.healthmodel/01-discovery.json` and `.healthmodel/00-brief.md`. DO NOT USE FOR: deploying or designing signals (use healthmodel-design / healthmodel-deploy), generic architecture diagrams unrelated to health models.
Deploy and incrementally adapt an Azure Monitor Health Model using Bicep and standard az CLI — no extensions. Uses design files as source of truth, generates a Bicep project, deploys via az deployment group create. WHEN: 'deploy the health model', 'apply the design', 'update health model in Azure', 'push the health model', 'adapt the existing health model'. DO NOT USE FOR: designing entities (use healthmodel-design), discovering resources (use healthmodel-discovery), or operations against unrelated Azure Monitor features.
Design health model entities, signal definitions, and relationships from the architecture graph. Emits complete design files and generates a modular Bicep project for deployment. WHEN: 'design entities and signals', 'propose health thresholds', 'create health model spec', 'generate signal definitions', 'generate bicep for health model'. DO NOT USE FOR: discovery (use healthmodel-discovery), deployment to Azure (use healthmodel-deploy), modifying live health models directly.
Discover Azure resources and interview user to prepare health model inputs. WHEN: 'discover resources for health model', 'scan my Azure', 'what should I monitor', 'interview for health model'. DO NOT USE FOR: deploying health models (use healthmodel-deploy), general resource inventory without health model intent, cost or compliance audits.
Integrate a generated health model Bicep project into existing infrastructure-as-code. Detects IaC type (Bicep/Terraform/none), proposes integration level (NONE/SOME/FULL), generates integration snippets, verifies offline, and asks the user to deploy. WHEN: 'integrate health model into my infra', 'add health model to my bicep', 'connect health model to existing IaC', 'integrate health model bicep'. DO NOT USE FOR: designing entities (use healthmodel-design), deploying standalone health models (use healthmodel-deploy), discovering resources (use healthmodel-discovery), or Terraform module generation.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent skills for building Azure Monitor Health Models end-to-end — from resource discovery to deployment — using only the standard az CLI, jq, and Bash.
No Azure CLI extensions. No Python SDK. No ARM template deployments.
An Azure Monitor Health Model gives you a structured, real-time view of your application's health by organizing resources into a tree of entities with signals (metrics, PromQL, KQL queries) that evaluate health state automatically.
The workflow chains six skills with human checkpoints between phases:
Discovery → Architecture → Design → Deploy
↑
Signal Catalog (reference data)
Orchestrator (chains all phases)
| Skill | Purpose |
|---|---|
| healthmodel-discovery | Interview user, export Azure resources, generate a brief |
| healthmodel-architecture | Build dependency graph, Mermaid diagram, propose entity hierarchy |
| healthmodel-design | Create sparse signal definitions, entities, relationships |
| healthmodel-deploy | Validate → bootstrap → plan → apply → smoke test |
| healthmodel-signal-catalog | Reference: how to discover metrics and write signals for any resource type |
| healthmodel-orchestrator | Chains all four phases with human checkpoints |
az login)az (used offline for schema validation only)az account show -o json | jq '{subscriptionId: .id, name: .name}'
command -v jq && echo "jq: ok"
az bicep version
copilot plugin marketplace add abossard/azure-healthmodel-skills
Or from inside a session:
/plugin marketplace add abossard/azure-healthmodel-skills
copilot plugin install azure-healthmodel-skills@azure-healthmodel-skills
Or from inside a session:
/plugin install azure-healthmodel-skills@azure-healthmodel-skills
git clone https://github.com/abossard/azure-healthmodel-skills.git
cp -R azure-healthmodel-skills/skills/healthmodel-* ~/.agents/skills/
copilot plugin update azure-healthmodel-skills
"discover resources for health model" or "scan my Azure".healthmodel/00-brief.md with SLOs, journeys, concerns"map architecture" or "draw resource graph""design entities and signals""deploy the health model"Or use the orchestrator: "create health model" — it chains all phases.
All intermediate state is saved to .healthmodel/ in your project:
| File | Phase | Content |
|---|---|---|
00-brief.md | Discovery | Human-authored: SLOs, journeys, concerns |
01-discovery.json | Discovery | Interview answers + resource inventory |
02-graph.json | Architecture | Dependency graph + entity hierarchy |
03-design/**/*.json | Design | Sparse signal, entity, relationship definitions |
04-plan.json | Deploy | Per-resource verdict before apply |
04-deployed.json | Deploy | Apply receipt |
You can version-control .healthmodel/, re-run any phase independently, or resume after interruption.
Each design file contains only the fields the skill manages. On deploy, the skill deep-merges design onto live state — portal edits to unmanaged fields are preserved. To stop managing a field, remove it from the design file.
npx claudepluginhub abossard/azure-healthmodel-skills --plugin azure-healthmodel-skillsA learning-focused skill plugin that teaches before implementing — for team onboarding
Azure Monitor Health Model agent skills — end-to-end workflow from resource discovery to deployment using only the standard az CLI. Six skills: discovery, architecture, design, deploy, orchestrator, and signal catalog.
Evidence-based agent orchestration. Four skills (blueprint / replicate / inspect / extract) collapse a brainstorm-plan-code-review pipeline into one tiered human gate, plus a dr-evil agent that drives the flow end-to-end and a frau subagent that runs inspection with full tool access in a fresh context to remove implementation bias. Ships a lab skill that bootstraps the per-repo files into any target repo.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.