AgentKit Core
codexDeeply personalized Skills4-IT workflows spanning .NET, Power Platform, MCP/agents, training business, consulting delivery and knowledge/relationship context.
119 skills
Design practical, audience-aware IT training programs using the Skills4-IT training methodology, including needs analysis, learning objectives, course flow, assessments, instructor briefs and delivery-readiness checks.
Plugin training-creator in RemseyMailjard/agentkit. Commands read from the repo's manifest — 1 month ago.
adapt-trainingUse when an existing training must be adapted for a different audience, duration, technical depth, delivery mode or organizational context.
analyze-audienceUse when a training design needs an explicit audience profile covering prior knowledge, roles, motivation, technical level and likely learning barriers.
analyze-training-needUse when a client request, brief or idea must be translated into a clear training problem, scope, constraints and success criteria before design starts.
create-assessmentUse when a training needs questions, practical checks or assessment tasks that verify whether learners achieved the defined learning objectives.
create-instructor-briefUse when an instructor needs a concise delivery brief covering audience, objectives, agenda, demos, labs, logistics, risks and fallback options.
define-learning-objectivesUse when a training needs measurable learning objectives derived from the training need, audience and intended workplace outcomes.
design-trainingUse when a user asks to design the structure and learning flow of a practical training from an approved need, audience and set of objectives.
review-training-readinessUse when a training package must be checked before delivery for content, environment, access, timing, instructor and participant readiness.
Deeply personalized Skills4-IT workflows spanning .NET, Power Platform, MCP/agents, training business, consulting delivery and knowledge/relationship context.
119 skills
Design, build, review, secure and test Model Context Protocol servers using repeatable Skills4-IT engineering workflows.
6 skills
Review and improve .NET repositories using repeatable Skills4-IT quality workflows for correctness, architecture, ASP.NET Core, EF Core, security and remediation.
5 skills
Create, review, test and adapt practical hands-on IT labs using repeatable Skills4-IT instructional design workflows.
5 skills
Scaffolded OneNote knowledge and memory plugin for AgentKit. Defines context-retrieval and knowledge-capture skill boundaries ahead of a future MCP-backed implementation.
4 skills · 1 MCP server
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
hooks
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
1 skill · 9 commands
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring.
19 skills
Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
1 skill · 3 commands · 1 agent
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.