doctor

Powercademy's living conventions for Power Platform delivery — Dataverse schema judgement (statecode over custom status, solution and publisher discipline, dependency packaging), the Power Automate and PCF lessons that cost hours once (editing live flows, child-flow contracts, whether PCF is the right tool, the premium-licensing trap), applied before and alongside any build, model-driven app UX (every command button has an icon that says what it does, modal focused-task dialogs), the tool-selection ladder (purpose-built tools, then SDK / Web API / CLI, browser automation only where nothing else reaches), plus the writing-skills house standard for authoring skills that work in both runtimes. Each rule carries its reasoning; the lists grow with every corrected mistake.

6 skills

Power Platform ALM the Powercademy way — design the delivery process (environments, solution segmentation, publisher, the config boundary, promotion path and approvals), then run promotions with checkpoints that stop before anything irreversible. Routes execution to Microsoft's Dataverse solution skills, native pipelines and pac CLI rather than rebuilding them. A production import is always a red checkpoint.

2 skills · 1 MCP server

Make the canvas app decisions that generation can't — is canvas even the right shape, delegation and data strategy, screen and navigation architecture, conventions — then hand a decided build plan to Microsoft's canvas authoring tooling. Checkpoints at real data volumes, because a 50-row test proves nothing. Methodology, not mechanics.

1 skill · 1 MCP server

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

DataHub development and interaction toolkit with connector planning, PR review, catalog search, metadata enrichment, lineage tracing, data quality management, and connection setup skills

13 skills · 8 commands · 4 agents

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

CI/CD pipeline configuration, GitHub Actions/GitLab CI workflow setup, and automated deployment pipeline orchestration

4 skills · 1 command · 5 agents

Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts

13 skills · hooks

Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).

6 skills · 1 agent · hooks