abossard

Guide SDK users through setting up their Python environment for Azure AI Content Understanding. Use this skill when users need help installing the SDK, configuring Azure resources, deploying required models, setting environment variables, or running samples.

Domain knowledge for Azure AI Content Understanding. Use this skill to answer questions about Content Understanding concepts, analyzers, field schemas, API operations, and SDK usage. Always consult official documentation before answering.

Run a specific sample for the Azure AI Content Understanding SDK. Use when users want to run a particular sample like sample_analyze_url.py or sample_analyze_invoice.py.

Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_typespec_customized_code_update.

Generate, build, and test Azure SDKs locally from TypeSpec with automatic customization. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "update changelog", "fix SDK build errors", "fix breaking changes", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". DO NOT USE FOR: publishing to package registries, CI pipeline configuration, API design review. INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.

Diagnose and resolve failures in Azure SDK CI and generation pipelines. **UTILITY SKILL**. USE FOR: "pipeline failed", "build failure", "CI check failing", "SDK generation error", "reproduce pipeline locally", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check.

Create and manage release plan work items for Azure SDK releases across languages. **UTILITY SKILL**. USE FOR: "create release plan", "update release plan", "link SDK PR to plan", "namespace approval", "check release plan status". DO NOT USE FOR: SDK code generation, pipeline troubleshooting, API review feedback. INVOKES: azure-sdk-mcp:azsdk_create_release_plan, azure-sdk-mcp:azsdk_get_release_plan, azure-sdk-mcp:azsdk_link_sdk_pull_request_to_release_plan.

Check release readiness and trigger the release pipeline for Azure SDK packages. **UTILITY SKILL**. USE FOR: "release SDK", "trigger release", "check release readiness", "release pipeline", "publish package", "ship SDK". DO NOT USE FOR: SDK development, code generation, pipeline debugging, release plan creation. INVOKES: azure-sdk-mcp:azsdk_release_sdk.

Use when your human partner asks to build, implement, or modify anything — before any creative or implementation work begins. Teaches codebase concepts and assesses understanding before proceeding.

Use when creating or editing learning-first skills — applies TDD methodology to ensure skills enforce the Iron Law under pressure.

Use when starting any conversation - establishes how to find and use learning-first skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when your human partner wants code reviewed — teaches code quality concepts and guides self-review instead of providing fixes.

Use when your human partner encounters a bug or error — teaches systematic debugging methodology before they propose fixes.

Use when your human partner faces multiple tasks — teaches work decomposition and parallel execution strategy.

Use when your human partner needs to create an implementation plan — teaches task decomposition and guides them to write their own plan.

Use when your human partner receives code review feedback — teaches critical evaluation of suggestions before implementing any changes.

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.

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.

Build an Azure Monitor Health Model end-to-end from resource discovery to deployment, using only the standard az CLI. Chains four phase skills with human checkpoints. WHEN: 'create health model', 'build health model', 'monitor my Azure resources with health model', 'set up Azure Monitor health model from scratch'. DO NOT USE FOR: general Azure monitoring setup without health models, Application Insights configuration, or Grafana dashboard creation.

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.

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.

Discovery-driven reference for building Azure Monitor Health Model signals. Shows how to discover metrics with `az monitor metrics list-definitions`, write PromQL / KQL that the design schema accepts, derive thresholds from real data, and verify signals after deploy via `az rest`. WHEN: loaded by healthmodel-design when authoring signal definitions for any resource type. DO NOT USE FOR: direct user invocation, deploying signals (use healthmodel-deploy), discovering resources (use healthmodel-discovery).

End-to-end testing and visual regression for Spring Boot REST APIs using Playwright. Covers Swagger UI verification, REST API smoke tests, CRUD workflows, and screenshot capture. Zero Java dependencies — runs entirely via npx/npm with TypeScript tests. USE FOR: e2e tests, browser tests, API smoke tests, Swagger UI tests, screenshot capture, visual regression, integration tests, Playwright setup.

Architecture diagramming and JPA ERD generation for Spring Boot projects. Uses Mermaid — rendered via npx with zero global installs. Just .mmd text files + one npx command. Also renders natively in GitHub markdown. USE FOR: architecture diagrams, ERD, entity relationship, visual docs, system diagram.

Spring Boot test automation skill. Covers unit testing, integration testing, MockMvc, Mockito, test slices, and test-driven development workflows. USE FOR: writing tests, test failures, test coverage, TDD, MockMvc, Mockito.

REST API development skill for Spring Boot. Covers endpoint design, request/response modeling, validation, error handling, and API documentation. USE FOR: REST endpoints, API design, request validation, error handling, HTTP status codes, OpenAPI.

Database schema management and migration for Spring Boot with JPA/Hibernate. Covers entity design, schema evolution, H2 development database, and production migration strategies. USE FOR: database schema, entity changes, migrations, JPA configuration, H2 console, schema evolution.

Maven build automation for Spring Boot projects. Handles compilation, packaging, dependency management, and build troubleshooting. USE FOR: build errors, dependency issues, Maven wrapper, packaging, compilation failures, dependency tree analysis.

Apply reusable blender scene archetypes (wobble, flow, hard, bullet) with controlled layer behavior. Use when designing or refactoring LedFX blender scenes and masks for readable yet high-impact DJ visuals.

Build or debug LedFX automations through MCP tools with schema-safe effect configs, fallback chains, and palette/gradient validation. Use when writing scripts or commands that call ledfx_* tools, especially set_effect, set_blender, scene, or playlist operations.

Compose phase-based DJ lighting scenes from creative rules into executable direct and blender scene specs. Use when translating a DJ guide into LedFX scene blueprints, role ordering, or phase playlist flows.

Audit DJ lighting playlists for effect-family diversity, strobe density, phase coverage, and role balance. Use when validating that playlists are not repetitive and comply with guide constraints before showtime.

Design rapid directional lighting scenes that read as lightning-bullet motion with controlled intensity. Use when creating high-velocity LED looks with scroll/scan carriers and safe duration/pacing constraints.

Blueprint a coding task from inline context or an existing blueprint. Reads the repo and org wiki page collections, scores and verifies them, thinks silently, self-challenges, and returns a persisted plan. No human review gate. The blueprint is the durable handoff artifact.

Extract lessons once at a coherent task or session boundary into the global raw/wiki knowledge root. Human corrections are the highest-value signal. Every durable claim must cite live code.

Inspect the current-task delta in a fresh subagent context. Verifies active EARS criteria and invalidated baseline proofs, computes an uncertainty-based risk tier, and returns evidence without dispatching another phase. Surfaces evidence, never a verdict.

Replicate a planned task in a tight test-driven loop. Generate -> run -> observe REAL output -> fix. Re-injects blueprint constraints after context compaction or when switching focus. Returns evidence without self-chaining.

Bootstrap minime user-home state only (no repository writes). Creates blueprint templates plus global raw/wiki/schema roots and repo blueprint dirs under VIRTUCON_HQ.

Program moving head fixtures in QLC+ — covers 16-bit pan/tilt DMX addressing, degree-to-DMX conversion, and phantom sweep chaser patterns. Channel layouts shown are for the Hero Spot Wash 140; use query_fixture_channels to discover channels for other fixtures. USE FOR: pan/tilt positioning, moving head scenes, phantom sweep, chaser with blackout reset, beat-synced chasers, Hero Spot Wash fixture programming. DO NOT USE FOR: wash-only fixtures, LED strip effects, ISF shaders.

Design QLC+ Virtual Console layouts — covers audio-reactive OSC faders, submaster control, frame-based grouping, and layer architecture for VC widgets. USE FOR: VC slider setup, OSC input mapping, submaster patterns, audio reactivity control, frame organization, level vs submaster modes. DO NOT USE FOR: function creation (use qlc-moving-head), fixture patching, shader code.

Inspect and render Mermaid blocks in Markdown as themed SVG output with the packaged ahm-diagrammo CLI.

Zellij terminal workspace orchestration for AI agents. Covers the mental model, targeting strategy, screen I/O patterns, safety boundaries, and composition workflows. Use `zellij <command> --help` for exact syntax; this skill teaches *when* and *why* to use each capability.

Analyze JavaScript projects end-to-end and produce a comprehensive TypeScript migration report. Scans all dependencies (npm/yarn), bundler config (webpack v5, Vite, Rollup, esbuild, Parcel), build pipelines, and source code patterns. Searches online for type availability (@types/* packages), known migration blockers, and community guidance. Generates a prioritized, safe migration plan. WHEN: migrate JS to TypeScript, convert JavaScript to TypeScript, TypeScript migration report, JS to TS assessment, check type coverage, analyze dependencies for TypeScript, webpack TypeScript migration, convert project to TypeScript, type safety audit, add TypeScript to existing project, modernize JavaScript project.