By scottdurow
Plan, build, deploy, and test Power Platform solutions including Power Apps Code Apps, Dataverse schemas, Power Pages sites, Fluent UI apps, and ALM pipelines using PAC CLI and browser automation.
Assesses and implements healthy Power Platform ALM: environment strategy, solution architecture, source control, CI/CD pipelines, managed deployments, and operational governance.
Simulates a naive end-user performing usability tasks in a live browser session. Uses Playwright-based browser tools to interact with the UI, narrates what they see and do, and reports confusion, frustration, and dead ends. Used by Usability Engineer agent for structured usability studies. Use when running usability tests, simulating real user behavior, or validating whether a UI is intuitive without prior knowledge.
Performs deep, systematic code review: finds duplication, dead code, anti-patterns, complexity issues, security vulnerabilities, and technical debt before they compound.
Orchestrator agent and single entry point for all user requests. Routes work to specialist agents and team skills, enforces human approval gates for immutable decisions, and maintains project-wide state. Delegates to subagents via runSubagent directly or via skills (team-planning, code-review) depending on task complexity.
Designs data schemas for applications, defining tables, columns, relationships, option sets, and security models without writing code — producing schema design documents.
Interactive browser automation and visual validation using Playwright MCP server and GitHub Copilot Agent Mode. Creates a bridge between the agent and a live browser session (including authenticated user context), with optional scripted Playwright test generation for repeatable checks. Triggers on "browser automation", "interactive browser", "playwright mcp", "test the ui", "ui test", "visual test", "visual regression", "check interface", "deployment smoke test", "post-deploy validation", "config validation".
Deep code audit and technical review skill. Handles code audits (dead wiring, silent failures, stubs, bloat), architecture decisions, security audits, feature design reviews, refactoring plans, and deployment strategy reviews. Produces actionable reports with file:line references grouped by severity, or structured decision documents with trade-off analysis. Triggers on "code review", "audit the code", "review the code", "find dead code", "find placeholders", "check for stubs", "prune the code", "code cleanup", "implementation review", "completeness check", "find unused code", "architecture decision", "security audit", "design review", "refactoring plan", "deployment review", "team review", "review team", "collaborative review".
Comprehensive Dataverse data model reviewer and critic. Evaluates proposed schemas against 74+ rules covering naming, normalization, data types, business rules, evolvability, and platform-specific best practices. Produces structured assessments with actionable feedback. Triggers on "review my data model", "critique this schema", "is my Dataverse design correct", "data model review", "schema review", "evaluate my tables", "check my data model", "Dataverse best practices review", "normalization check".
Shared prerequisite steps for any skill that interacts with the Dataverse OData Web API. Covers PAC CLI authentication, Azure CLI token acquisition, WhoAmI validation, environment URL extraction, and token refresh patterns. Triggers on "pac auth", "dataverse auth", "dataverse prerequisites", "connect to dataverse", "environment setup", "pac env who", "dataverse token", "azure cli token dataverse".
Expert guidance for the Microsoft Dataverse Web API metadata and schema management. Programmatically create tables, columns, relationships, forms, views, app modules, and sitemaps using OData v4.0 RESTful endpoints. Treats application structure as code. Also covers the Dataverse MCP server for natural language queries and CRUD via GitHub Copilot. Triggers on "dataverse api", "web api", "create table", "EntityDefinitions", "AttributeMetadata", "RelationshipDefinitions", "POST /EntityDefinitions", "PublishXml", "dataverse schema", "programmatic schema", "api metadata", "dataverse mcp", "mcp server", "dataverse mcp server", "@microsoft/dataverse", "mcp setup", "mcp dataverse".
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.
Version: 1.0.3
Skills and agents that give GitHub Copilot deep knowledge of the Microsoft Power Platform — planning, building, deploying, and testing Power Apps Code Apps, Dataverse schemas, and Power Pages code sites from VS Code.
Skills are loaded automatically when relevant to your request, or invoked manually via /skill-name in chat. Each skill folder contains a SKILL.md with domain instructions and a resources/ directory with reference docs loaded on demand.
| Skill | Description |
|---|---|
| team-planning | Multi-agent planning orchestrator (Data Modeler, UX Designer, Tester, The Critic) |
| workflow-state | Persists planning/execution state to .copilot/state/ for resume after chat resets |
| dataverse-solution-web-api | Creates Dataverse schema (tables, columns, relationships, views, forms) via Web API |
| dataverse-data-review | 74+ rule automated assessment of Dataverse data models |
| dataverse-prerequisites | PAC CLI auth, Azure CLI token, WhoAmI validation, publisher prefix extraction |
| power-apps-code-apps | End-to-end Code App: Plan → Schema → Scaffold → Build → Connect → Deploy |
| power-pages | End-to-end Power Pages code site: creation, auth, data model, Web API, deployment, SEO |
| ioc-development-pattern | Build against in-memory data first, swap to real backends later |
| vite-react | Vite + React + TypeScript best practices and project structure |
| ui-fluentui-react | Fluent UI v9 business app patterns: forms, data tables, dialogs, navigation |
| ui-wireframes | Low-fidelity clickable HTML wireframes and Mermaid flow diagrams |
| ui-website | Website design: CSS theming, typography, color palettes, accessibility |
| code-review | Deep code audit + multi-perspective technical decision review |
| power-apps-genpage | Generative pages for model-driven apps: React v17 + Fluent UI V9 single-file pages |
| browser-automation | Interactive browser automation and visual validation via Playwright MCP |
| powerplatform-alm | Environment strategy, solution architecture, CI/CD pipelines, managed deployments |
| Agent | Spawned By | Role |
|---|---|---|
| Consultant | — | Orchestrator — routes work to specialist agents |
| Data Modeler | Consultant (via team-planning) | Designs Dataverse schemas |
| UX Designer | Consultant (via team-planning) | Designs UI/UX, creates wireframes |
| Tester | Consultant (via team-planning) | Test strategy and coverage |
| The Critic | Consultant (via team-planning) | Challenges assumptions, finds blind spots |
| Developer | Consultant | Autonomous implementation, browser testing, iteration |
| Code Reviewer | Consultant, Developer | Code quality and security analysis |
| Solution Architect | Consultant | System architecture design |
| Technical Writer | Consultant | Documentation quality |
| ALM Engineer | Consultant (via team-planning) | ALM strategy and deployment |
| Usability Engineer | Tester | Conducts structured usability studies |
| Average User | Usability Engineer | Simulates end-user for usability testing |
Agents support guided workflow transitions via handoff buttons that appear after a response completes:
| From | Button | To |
|---|---|---|
| Consultant | Start Implementation | Developer |
| Developer | Review Code | Code Reviewer |
| Code Reviewer | Address Findings | Developer |
| Usability Engineer | Fix Usability Issues | Developer |
| Usability Engineer | Redesign UX | UX Designer |
Install from the VS Code Marketplace (coming soon).
Add the plugin location to your VS Code User Settings (settings.json):
"chat.pluginLocations": {
"scottdurow/power-platform-full-stack-skills": true
}
Or, if you've forked or cloned the repo locally, use a file:/// path instead:
"chat.pluginLocations": {
"file:///C:/repos/power-platform-full-stack-skills": true
}
No files are copied — VS Code reads skills and agents directly from the source.
Prerequisite: VS Code with GitHub Copilot Chat
How agents engage across the lifecycle of a solution — fanning out to specialists, converging results, then fanning out again:
graph TD
REQ["📋 Request"]
REQ --> PM["🎯 Consultant"]
PM -->|"fan-out"| DM["📊 Data Modeler"]
PM -->|"fan-out"| UX["🎨 UX Designer"]
PM -->|"fan-out"| SA["🏗️ Solution Architect"]
PM -->|"fan-out"| TST["🧪 Tester"]
DM --> DRAFTS["📑 Draft Designs"]
UX --> DRAFTS
SA --> DRAFTS
TST --> DRAFTS
npx claudepluginhub scottdurow/power-platform-full-stack-skills --plugin power-platform-full-stackComprehensive 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.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques