By tachyon-beep
Build and manage dynamic neural networks that grow, prune, and adapt topology during training, with support for continual learning, gradient isolation, PEFT/LoRA adapters, modular composition, and lifecycle orchestration.
Uses power tools
Uses Bash, Write, or Edit tools
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.
npx claudepluginhub tachyon-beep/skillpacks --plugin yzmir-dynamic-architectures26 professional skillpacks with 173+ TDD-validated skills covering AI/ML, Python, DevOps, security, and full-stack development.
DevOps and deployment automation - CI/CD pipelines, zero-downtime deployments - 1 skill, 2 commands, 2 agents
CMMI-based SDLC framework (Levels 2-4) with GitHub/Azure DevOps integration (8 skills, 4 agents) - comprehensive process guidance for high-quality software development with specialist support for architecture decisions, quality assurance, bug triage, and process routing
SME (Subject Matter Expert) Agent Protocol - mandatory protocol for all specialist agents defining fact-finding requirements, output contracts, confidence/risk assessment, and qualification of advice.
TDD-validated implementation planning with plan review quality gate (2 skills, 5 agents, 1 command) - write plans, validate against codebase reality before execution
Build and configure neural network architectures
Universal software engineering methodology: systematic debugging, safe refactoring, code review, incident response, technical debt triage, and codebase comprehension. Language-agnostic foundations for professional engineering practice.
ML engineering plugin: Give your AI coding agent ML engineering superpowers.
Train ML models with scikit-learn, PyTorch, TensorFlow. Use for classification/regression, neural networks, hyperparameter tuning, or encountering overfitting, underfitting, convergence issues.
AI/ML development: LLM architecture, prompt engineering, ML ops, and NLP with production deployment focus
Eval-gated LLM fine-tuning lifecycle: LoRA/QLoRA SFT, preference optimization (DPO/ORPO/KTO), GRPO/RLVR, vision SFT, and quantized export — Unsloth-first with TRL fallback, no eval harness means no fine-tune