Ai-Ml plugins

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

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4

8 skills · 3 commands · 3 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

2 skills · 1 command · 3 agents

Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)

1 skill · 3 commands · 1 agent

Firebase Genkit expert for production-ready AI workflows with RAG and tool calling

1 skill · 1 command · 1 agent

AI ethics and fairness validation

1 skill · 1 command

LLM application development, prompt engineering, and AI assistant optimization

5 skills · 3 commands · 2 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

1 skill · 1 command · 3 agents

Multi-agent system optimization, agent improvement workflows, and context management

1 skill · 2 commands · 1 agent

LLM application development, prompt engineering, and AI assistant optimization

5 skills · 3 commands · 2 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

1 skill · 1 command · 3 agents

Multi-agent system optimization, agent improvement workflows, and context management

1 skill · 2 commands · 1 agent

LLM application development, prompt engineering, and AI assistant optimization

4 skills · 3 commands · 2 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

1 skill · 1 command · 3 agents

Multi-agent system optimization, agent improvement workflows, and context management

2 commands · 1 agent

Use when paired or branched ML experiments need uncertainty estimates, grouped splits, selection-bias controls, power analysis, or abstention calibration.

1 skill · 3 commands · 2 agents

Use when reinforcement-learning environment, reward, data-regime, algorithm or evaluation decisions need implementation checks.

1 skill · 3 commands · 2 agents

Use when an LLM application needs model/configuration evaluation, retrieval, context/cost controls, fine-tuning, tool reliability or safety checks.

1 skill · 3 commands · 2 agents

LLM and prompt evaluation with Promptfoo, DeepEval and Ragas, Giskard vulnerability scans, Langfuse tracing, and golden-dataset regression suites. Audits eval suites for methodology errors. Agents (prompt-eval-reviewer, llm-red-team-planner) review an eval suite and plan adversarial probe campaigns across the OWASP LLM Top 10.

7 skills · 2 agents

ML model testing: Giskard and Deepchecks validation, Evidently drift monitoring, Fairlearn fairness metrics, and model performance regression gates. Assigns risk tiers with the fairness and explainability evidence each tier requires, and wires Jupyter notebook CI with papermill, nbval, testbook and nbstripout.

7 skills

AI-assisted test generation: LLM-written tests from natural-language specs with confidence scoring, spec coverage gap mapping, and model-based testing. Builds state-machine models and turns them into test suites, and adds adversarial review agents (ai-test-curator, ai-test-shallow-coverage-critic) that catch hallucinated APIs, weak assertions, and happy-path-only coverage.

3 skills · 2 agents

Multi-agent mesh orchestration for Claude Code. Define agent workflows in YAML, run them with tx start, observe with tx spy/msg/logs.

1 skill · 1 command

Model architecture design, training strategies, debugging, and paper interpretation (PyTorch/TensorFlow).

1 skill

Evaluation strategies, prompt engineering, red teaming, and regression testing for LLMs.

1 skill

Retrieval-Augmented Generation: chunking, embeddings, vector search, reranking, and grounded answers.

1 skill

LLM application development, prompt engineering, and AI assistant optimization

4 skills · 3 commands · 2 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

1 skill · 1 command · 3 agents

Multi-agent system optimization, agent improvement workflows, and context management

2 commands · 1 agent

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.2

8 skills · 3 commands · 3 agents

ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows

1 skill · 1 command · 3 agents