PlagueHO

{what this skill teaches agents}

{what this skill teaches agents}

**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.

**WORKFLOW SKILL** — Research, outline, and scaffold a Slidev presentation. Phase 1 researches the topic and generates a detailed OUTLINE.md via runSubagent research and user guidance. Phase 2 generates slides.md, style.css, and images/ from the approved outline. WHEN: "create presentation", "new presentation", "scaffold presentation", "new Slidev deck", "new talk", "create slides", "start a presentation", "presentation about". INVOKES: runSubagent (web search, Microsoft Learn, WorkIQ), vscode_askQuestions, file-system tools. FOR SINGLE OPERATIONS: copy template folder manually.

**WORKFLOW SKILL** — Query WorkIQ for recent activity signals, identify patterns in conversations and meetings, cross-reference with latest tech announcements, and propose aligned demos as GitHub issues. WHEN: "intelligence scan", "what demos to build", "scan recent activity", "WorkIQ scan", "demo proposals from conversations", "identify demo opportunities", "what should I demo next". INVOKES: WorkIQ MCP, web search, GitHub issue tools. FOR SINGLE OPERATIONS: Query WorkIQ MCP directly.

Build an n-layer dependency graph from .NET upgrade assessment data and generate a phased modernization plan. Parses assessment.json from the .NET upgrade tools, extracts project dependency hierarchy via breadth-first layering, splits thick layers to cap projects per sub-layer, and produces a phased upgrade plan with Mermaid diagrams. Each phase targets PR-reviewable scope. SDK-style conversion is Phase 0, then layer-by-layer bottom-up modernization. WHEN: "plan appmod phases", "generate upgrade layers", "dependency layer plan", "phased migration plan", "break down dotnet upgrade", "layer extraction", "modernization phases", "upgrade dependency graph", "PR-sized migration plan", "appmod phasing strategy".

Shared hard rules enforced across all squad agents

How to write comprehensive architectural proposals that drive alignment before code is written

**WORKFLOW SKILL** — Migrate PowerShell Pester v4 tests to Pester v5, covering structural, assertion, and mock changes. WHEN: "upgrade Pester to v5", "migrate Pester v4 to v5", "convert Pester tests to Pester 5", "modernize Pester tests", "Assert-MockCalled to Should -Invoke". INVOKES: run_in_terminal for detection scripts and Invoke-Pester. FOR SINGLE OPERATIONS: edit one assertion or Invoke-Pester call directly.

**WORKFLOW SKILL** — Update Azure Verified Modules (AVM) to their latest versions in Bicep files. Scans for AVM module references, queries the Microsoft Container Registry (MCR) for latest versions, compares using semantic versioning, reviews breaking changes, and applies updates with validation. WHEN: 'update AVM', 'update Bicep modules', 'latest AVM versions', 'update Azure Verified Modules', 'upgrade Bicep dependencies', 'check AVM versions', 'update module versions'. INVOKES: run_in_terminal for MCR API queries and bicep lint. FOR SINGLE OPERATIONS: Use az bicep build to validate individual files.

**WORKFLOW SKILL** — Generate a structured research plan for a Microsoft technology topic, defining scope, research areas, search terms, and output section mapping based on purpose (guide/presentation/lab/demo). WHEN: "create research plan", "plan Microsoft research", "research plan for", "plan technical research", "scope research topic", "define research areas". INVOKES: editFiles. FOR SINGLE OPERATIONS: Create plan.md manually.

**WORKFLOW SKILL** — Mandatory entry point for all research projects. Validates topic, confirms the plan with the user, scaffolds the folder structure, and initializes the research log before any subagent work begins. This skill is ONLY invoked by the research-microsoft-technology orchestrator agent. INVOKES: create-microsoft-research-plan, research-output-scaffolding, vscode_askQuestions. FOR SINGLE OPERATIONS: Not applicable — this skill must always be used to start research.

**WORKFLOW SKILL** — Extract structured research notes from a source URL or document into a standardized YAML-frontmatter markdown note. Applies fixed extraction rules for consistent note-taking across all research areas. WHEN: "create research note", "extract research note", "note from URL", "research note template", "take research notes", "extract findings from". INVOKES: microsoft_docs_search, microsoft_docs_fetch, fetch_webpage, editFiles. FOR SINGLE OPERATIONS: Copy the note template and fill manually.

**WORKFLOW SKILL** — Scaffold the .research/ output folder structure for a research topic, creating note directories per area, log files, and output section placeholders based on the research plan. WHEN: "scaffold research output", "create research folder", "initialize research directory", "set up research workspace", "research output structure", "scaffold .research folder". INVOKES: run_in_terminal for scaffolding scripts. FOR SINGLE OPERATIONS: Create directories manually.

**WORKFLOW SKILL** — Update CHANGELOG.md and tag a new release from commits since the last version tag. WHEN: "release version", "update changelog", "cut release", "tag release", "ship version", "bump version tag", "prepare release", "new version", "changelog update", "push release". INVOKES: run_in_terminal (git log, git tag, git commit, git push), read_file, replace_string_in_file. FOR SINGLE OPERATIONS: Use git tag and git push directly.

**WORKFLOW SKILL** — Scaffold AGENTS.md and .github/copilot-instructions.md by analysing repo structure, code patterns, CI pipeline, and conventions. Generates non-overlapping guidance so agents and code review produce compliant code. WHEN: "create AGENTS.md", "add copilot instructions", "onboard repo for Copilot", "generate copilot-instructions.md", "scaffold repo AI instructions", "add agent instructions to my repo". INVOKES: file read, semantic_search, fetch_webpage. FOR SINGLE OPERATIONS: Edit .github/copilot-instructions.md directly.

**WORKFLOW SKILL** — Update Azure Verified Modules (AVM) to their latest versions in Bicep files. Scans for AVM module references, queries the Microsoft Container Registry (MCR) for latest versions, compares using semantic versioning, reviews breaking changes, and applies updates with validation. WHEN: 'update AVM', 'update Bicep modules', 'latest AVM versions', 'update Azure Verified Modules', 'upgrade Bicep dependencies', 'check AVM versions', 'update module versions'. INVOKES: run_in_terminal for MCR API queries and bicep lint. FOR SINGLE OPERATIONS: Use az bicep build to validate individual files.

**WORKFLOW SKILL** — Provision Azure User Assigned Managed Identities with OIDC federation and RBAC for passwordless GitHub authentication. WHEN: "set up Azure access for GitHub Actions", "configure managed identity for GitHub", "enable passwordless Azure authentication in CI/CD", "configure OIDC federation GitHub Azure", "Copilot coding agent Azure identity". INVOKES: run_in_terminal for PowerShell. FOR SINGLE OPERATIONS: Use az CLI for simple role assignments.

**WORKFLOW SKILL** — Create a new Agent Skill from a user's description and goal, following the agentskills.io specification. Scaffolds directory structure, generates SKILL.md with YAML frontmatter, and validates the result. WHEN: "create a skill", "new skill", "scaffold a skill", "build a skill", "make a skill for", "generate skill", "skill from scratch", "add a new agent skill". INVOKES: run_in_terminal for scaffolding scripts. FOR SINGLE OPERATIONS: Use directly to create the SKILL.md file manually.

**WORKFLOW SKILL** — Generate a reusable GitHub Copilot Agent Skill from a single-purpose refactoring or tech debt Pull Request. WHEN: "create skill from PR", "generate skill from pull request", "PR to skill", "reusable refactoring skill", "tech debt skill from PR". INVOKES: GitHub MCP tools, file system. FOR SINGLE OPERATIONS: Use GitHub MCP directly to read PR diffs.

Converts legacy .NET project files (.csproj, .fsproj, .vbproj) to modern SDK-style format. Use when asked to modernize, upgrade, migrate, or convert .NET projects, or when encountering non-SDK-style project files that need updating to current .NET standards.

Use when working with an Aspire distributed application: operate an AppHost or resources through the Aspire CLI; start, stop, restart, or wait for resources; inspect app state, logs, traces, docs, or health; add integrations; manage secrets/config; publish/deploy or run pipeline steps; initialize an existing app; recover TypeScript `.modules`; find frontend URLs for Playwright; expose custom dashboard/resource commands; or understand Aspire AppHost APIs in C# or TypeScript. Use even if the user says AppHost, resources, dashboard, bootstrap, Playwright URL, or local distributed app workflow without naming Aspire. Do not use for non-Aspire .NET apps, container-only repos without an AppHost, or ordinary build/test tasks.

One-time skill for completing Aspire initialization in an existing app after `aspire init` has dropped the skeleton AppHost. Use this skill when an `aspire.config.json` exists but the AppHost has not yet been wired up.

Query .NET APIs across NuGet packages, platform libraries, and local files. Search for types, list API surfaces, compare and diff versions, find extension methods and implementors. Use whenever you need to answer questions about .NET library contents.

Automate browser interactions, test web pages and work with Playwright tests.

Create a new built-in prompt template JSON file for Prompt Babbler that conforms to the prompt-template.schema.json schema. Use when the user wants to add a new builtin template, create a prompt template, scaffold a template, or add a new babble-to-prompt conversion template. Interviews the user for missing details via vscode_askQuestions, generates a conformant JSON file, and places it in the Templates directory.

Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost. DO NOT USE FOR: non-Aspire .NET apps (use dotnet CLI), container-only deployments (use docker/podman), Azure deployment after local testing (use azure-deploy skill). INVOKES: Aspire CLI commands (aspire start, aspire describe, aspire otel logs, aspire docs search, aspire add), bash. FOR SINGLE OPERATIONS: Use Aspire CLI commands directly for quick resource status or doc lookups.

Automate browser interactions, test web pages and work with Playwright tests.

**WORKFLOW SKILL** - Live-validate a single workshop lab module in the browser and add correct, clarifying screenshots. Requires a specific lab module to be named, confirms the required browser pages are already open AND authenticated (Microsoft Foundry portal at ai.azure.com, and VS Code + Foundry Toolkit in a GitHub Codespace), walks the lab steps literally as an attendee would, captures screenshots at the unclear moments, embeds them with the repo's collapsible pattern, fixes any factual defects it finds, then runs markdownlint and a screenshot-inventory check. WHEN: "add screenshots to lab module", "capture lab screenshots", "update lab NN screenshots", "verify lab module is correct", "validate the lab steps", "screenshot the lab walkthrough". INVOKES: open_browser_page / run_playwright_code (browser automation), read_file, replace_string_in_file, run_in_terminal (markdownlint, validation script). FOR SINGLE OPERATIONS: capture one screenshot with run_playwright_code and embed it manually.

**WORKFLOW SKILL** - Provision a shared Microsoft Foundry workshop environment for multiple attendees. Collects five parameters interactively when not supplied, validates the attendee roster, runs azd provision, and verifies RBAC assignments, AI Search population, audit CSVs, and per-attendee onboarding files. WHEN: "provision workshop", "set up the foundry workshop", "deploy foundry lab", "prepare the workshop environment", "run workshop setup", "provision foundry workshop". INVOKES: vscode_askQuestions, run_in_terminal (azd, az). FOR SINGLE OPERATIONS: Follow docs/guide-organizer.md directly.