lawwu

lawwu/mcp-lightcast

Instructions file

Instructions for lawwu/mcp-lightcast, covering claude.md, project overview, essential commands, development setup and running the server.

lawwu/agentic-ml-plugin

Plugin Claude Code

Machine learning skills for Claude Code.

lawwu/agentic-ml-plugin

Instructions file CodexOpenCode

AGENTS.md instructions for lawwu/agentic-ml-plugin, covering agentic ml skills, keep updated, changelog conventions, structure and creating a skill.

lawwu/agentic-ml-plugin

Instructions file

Claude Code instructions for lawwu/agentic-ml-plugin, a project described as: Agentic Machine Learning Plugin.

lawwu/agentic-ml-plugin

Plugin Claude Code

Skills for machine learning workflows: monitoring training runs, debugging models, and managing experiments.

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Continuously monitors a machine learning training run (local, remote, or cloud) until it completes or hits a critical issue. Supports local log files, SSH targets, process names, Vertex AI Pipeline jobs, and Vertex AI Custom training jobs. Run this automatically whenever a training job is started or handed off — poll…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Benchmarks end-to-end ML execution quality across multiple modes (no-plugin/manual, plugin-driven, and AutoGluon-backed AutoML). Automatically identifies exactly one dataset scenario (hard-fraud, hard-attrition, or xhard-churn) and runs the benchmark against that single scenario. Use when asked to compare E2E…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Builds and evaluates non-ML baselines (majority class, mean predictor, simple rules, naive forecasting) to establish the performance floor that ML must beat. Use when asked to build a baseline, establish a heuristic baseline, create a non-ML baseline, or before training a model to satisfy Rule 1 of Google's Rules of…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Dry-run a preprocessing pipeline on a small sample to catch shape, dtype, value range, padding, special token, label encoding, and collation issues before full training. Writes inline validation code tailored to your pipeline. Invoke this automatically whenever someone is about to start a training run, has changed…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Profile and validate a dataset before training. Works with CSV, Parquet, JSONL, HuggingFace datasets, image directories, and database tables (PostgreSQL, MySQL, BigQuery, SQLite, Snowflake). Checks for missing values, duplicates, class imbalance, split leakage, outliers, schema drift, and format issues. Produces a…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Evaluates a model checkpoint using HF Trainer.evaluate(), lm-evaluation-harness, or a custom eval script. Loads the checkpoint, runs evaluation, parses results, computes deltas against a baseline, and produces a structured results report. Run this automatically after training completes or a checkpoint is saved to gate…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Diagnoses failed or unstable machine learning training runs across local logs, artifact directories, process targets, experiment trackers, and Vertex AI pipelines. Collects evidence, classifies failure mode, performs root-cause analysis, and delivers a prioritized recovery plan. Run this automatically whenever a…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Create a visual presentation demonstrating business value of a trained model using showboat. Use after evaluation and explainability to synthesize findings into a stakeholder-ready demo. Invoke when asked to show business value, create a model presentation, generate a demo, or produce a stakeholder report.

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Generates feature importance, bias audit, and model card before promotion. Invoke automatically after evaluation completes — even if the user says "looks good, let's ship it" or "ready to deploy." Deploying without interpretability review risks hidden biases, spurious correlations, and regulatory exposure. Also invoke…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Explores data sources and engineers leakage-safe model features from files or databases. Use when asked to create features from raw tables/datasets, design joins and aggregations for a target label, improve model signal, or map business outcomes into trainable predictor sets. Invoke this automatically whenever the…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Orchestrates an end-to-end machine learning run from objective setup through dataset audit, data pipeline checks, training supervision, failure recovery, and evaluation gating. Use when asked to run or manage the full ML lifecycle, coordinate multiple ML skills, or deliver a Go/No-Go promotion decision with artifacts.…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Designs a structured ML experiment plan with hypothesis, model candidates, hyperparameter search space, compute budget, and experiment ordering. Invoke automatically whenever a user has a defined target and wants to start training — even if they just say "let's train a model", "I want to try a few models", or "what…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Recommend new research approaches, modeling ideas, and loss function modifications after a training run completes. Use this skill whenever you want to know what to try next, get modeling improvement suggestions, explore research ideas, suggest architecture changes, propose loss function modifications, or brainstorm…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Reviews and validates machine learning target/label definitions against business outcomes before modeling. Use when asked to define or audit the prediction target, select metrics, set acceptance criteria, detect leakage risk, or choose split strategy for a new ML project. Invoke this automatically whenever a user…

lawwu/agentic-ml-plugin

Skill Claude CodeCodex

Launch and manage ML training with early stopping, hyperparameter configuration, and checkpoint management. Wraps babysit-training for monitoring and check-failed-run for failure recovery. Use when asked to train a model, start a training run, fine-tune a model, or execute a training command.