wshobson/agents

Prompts from wshobson/agents

• Ml Pipeline

  text

  Orchestrate specialized agents to build a production ML pipeline from data analysis through training, deployment, and monitoring

  by wshobson

• Mlops Engineer

  agent

  Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

  by wshobson

• Ml Engineer

  agent

  Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

  by wshobson

• Data Scientist

  agent

  Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence. Use PROACTIVELY for data analysis tasks, ML modeling, statistical analysis, and data-driven insights.

  by wshobson

• Vision Sft

  skill

  Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.

  by wshobson

• Trace To Training Data

  skill

  Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.

  by wshobson

• Quantized Export

  skill

  Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.

  by wshobson

• Preference Optimization

  skill

  Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

  by wshobson

• Lora Qlora Recipes

  skill

  Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, choosing rank/alpha/target modules, or deciding between LoRA, QLoRA, and full fine-tuning.

  by wshobson

• Grpo Rlvr Training

  skill

  Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.

  by wshobson

• Finetuning Method Selection

  skill

  Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.

  by wshobson

• Eval Harness First

  skill

  Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.

  by wshobson

• Dataset Curation

  skill

  Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.

  by wshobson

• Checkpoint Promotion

  skill

  Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.

  by wshobson

• Promote Checkpoint

  text

  Re-gate an existing fine-tuned checkpoint against the current eval harness and export it on PROMOTE

  by wshobson

• Finetune

  text

  Run the eval-gated fine-tuning lifecycle end to end — eval harness, method selection, data, environment, training, checkpoint gate, export

  by wshobson

• Llm Finetuning Training Engineer

  agent

  Fine-tuning implementation workhorse — prepares datasets, generates Unsloth-first training scripts, launches and monitors runs, and exports artifacts. Use after a training brief exists, for dataset preparation, training execution, or model export.

  by wshobson

• Llm Finetuning Eval Engineer

  agent

  Evaluation gatekeeper for fine-tuning — builds golden sets and graders, calibrates judges, baselines base models, and issues checkpoint promotion verdicts. Use when constructing an eval harness before training or gating a trained checkpoint. Deliberately independent from training execution.

  by wshobson

• Llm Finetuning Architect

  agent

  Fine-tuning strategist who owns the eval gate and method/model selection. Refuses to plan training without a baselined eval harness. Use PROACTIVELY when a user wants to fine-tune a model, before any training configuration exists.

  by wshobson

• Vector Index Tuning

  skill

  Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

  by wshobson

• Similarity Search Patterns

  skill

  Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

  by wshobson

• Rag Implementation

  skill

  Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

  by wshobson

• Prompt Engineering Patterns

  skill

  This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.

  by wshobson

• Llm Evaluation

  skill

  Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

  by wshobson

• Langchain Architecture

  skill

  Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

  by wshobson

• Hybrid Search Implementation

  skill

  Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

  by wshobson

• Embedding Strategies

  skill

  Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

  by wshobson

• Prompt Optimize

  text

  Optimize prompts for production with CoT, few-shot, and constitutional AI patterns

  by wshobson

• Langchain Agent

  text

  Create LangGraph-based agent with modern patterns

  by wshobson

• Ai Assistant

  text

  Build AI assistant application with NLU, dialog management, and integrations

  by wshobson