SirNosh/bmad-ml

bmad-ml-chamber

Architecture specialist for model and training systems. Use when the user asks to talk to Chamber, requests the ML architect, or needs model architecture decisions.

bmad-ml-gekko

Data pipeline specialist for ML experiments. Use when the user asks to talk to Gekko, requests the data engineer, or needs DataLoader optimization.

bmad-ml-jett

Fast-executing ML engineer for experiments. Use when the user asks to talk to Jett, requests the ML engineer, or needs experiment implementation.

bmad-ml-kayo

Adversarial reviewer that stress-tests claims and conclusions. Use when the user asks to talk to KAY/O, requests an adversarial review, or needs claims validated before publication.

bmad-ml-omen

Standard reviewer for correctness and reproducibility. Use when the user asks to talk to Omen, requests a code review, or needs reproducibility verification.

bmad-ml-astra

Interdisciplinary synthesis and cross-domain transfer specialist. Use when the user asks to talk to Astra, requests the synthesizer, or needs cross-field insight connections and multi-modal research directions.

bmad-ml-breach

Experimental methodology and statistical rigor specialist. Use when the user asks to talk to Breach, requests the methodologist, or needs experiment design review, ablation planning, and reproducibility protocols.

bmad-ml-cypher

Dataset analysis and data quality specialist. Use when the user asks to talk to Cypher, requests the data detective, or needs dataset assessment, bias analysis, and benchmark evaluation.

bmad-ml-fade

Frontier research tracking and trend scouting specialist. Use when the user asks to talk to Fade, requests the scout, or needs arxiv monitoring, paradigm shift detection, and emerging method analysis.

bmad-ml-killjoy

Systems ML and hardware-aware optimization specialist. Use when the user asks to talk to Killjoy, requests the systems researcher, or needs compute-aware architecture tradeoffs, distributed training, and inference optimization.

bmad-ml-sage

Mathematical foundations and theory specialist. Use when the user asks to talk to Sage, requests the theorist, or needs mathematical analysis, proofs, and convergence guarantees.

bmad-ml-sova

Literature survey and SOTA tracking specialist. Use when the user asks to talk to Sova, requests the research tracker, or needs literature review, citation mapping, and paper analysis.

bmad-ml-viper

Adversarial robustness and ML safety specialist. Use when the user asks to talk to Viper, requests the adversary, or needs failure mode analysis, attack surface review, and robustness evaluation.

bmad-ml-dumbledore

AI product architect guiding PRD-equivalent planning, architecture, and delivery planning decisions. Use when the user asks to talk to Dumbledore, requests the AI architect, or needs structured planning for an AI product.

bmad-ml-hagrid

Data pipeline specialist for AI system integration. Use when the user asks to talk to Hagrid, requests data integration, or needs embedding pipeline or vector DB setup.

bmad-ml-hermione

Implementation specialist for LLM applications and AI systems. Use when the user asks to talk to Hermione, requests the AI engineer, or needs to build an LLM app or agent system.

bmad-ml-luna

Prompt and interaction designer for reliable AI behavior. Use when the user asks to talk to Luna, requests prompt engineering, or needs agent behavior specification.

bmad-ml-mcgonagall

MLOps lead for deployment, monitoring, and scaling. Use when the user asks to talk to McGonagall, requests deployment help, or needs CI/CD for AI systems.

bmad-ml-moody

AI QA and evaluation specialist for quality gates. Use when the user asks to talk to Moody, requests AI evaluation, or needs regression tests for AI systems.

bmad-ml-snape

AI security and safety specialist for guardrails and adversarial resilience. Use when the user asks to talk to Snape, requests a safety audit, or needs guardrails design.

bmad-ml-nosh

Shared orchestrator for AI Lab and AI Startup divisions. Use when the user asks to talk to Nosh, requests the ML orchestrator, or says "what should we do next".

bmad-ml-evaluation-criteria

Define evaluation metrics and acceptance thresholds. Use when the user requests to "define evaluation criteria" or "set acceptance thresholds".

bmad-ml-experiment-design

Design experiment with hypotheses and controls. Use when the user requests to "design an experiment" or "create an experiment design".

bmad-ml-chamber

Architecture specialist for model and training systems. Use when the user asks to talk to Chamber, requests the ML architect, or needs model architecture decisions.

bmad-ml-model-architecture

Design model architecture with decision records. Use when the user requests to "design the model architecture" or "create architecture ADRs".

bmad-ml-readiness-check

Assess implementation readiness before experimentation. Use when the user requests to "run a readiness check" or "check implementation readiness".

bmad-ml-training-pipeline

Design reproducible training pipeline specification. Use when the user requests to "design the training pipeline" or "create a training pipeline".

bmad-ml-adversarial-review

Stress-test claims and challenge experiment conclusions. Use when the user requests to "run an adversarial review" or "challenge the results".

bmad-ml-code-review

Review ML code for correctness and reproducibility. Use when the user requests to "review the code" or "run a code review".

bmad-ml-experiment-tracking

Update and maintain experiment tracking state. Use when the user requests to "update experiment tracking" or "check experiment status".

bmad-ml-gekko

Data pipeline specialist for ML experiments. Use when the user asks to talk to Gekko, requests the data engineer, or needs DataLoader optimization.

bmad-ml-implement-experiment

Implement experiment code from approved designs. Use when the user requests to "implement the experiment" or "start coding the experiment".

bmad-ml-jett

Fast-executing ML engineer for experiments. Use when the user asks to talk to Jett, requests the ML engineer, or needs experiment implementation.

bmad-ml-kayo

Adversarial reviewer that stress-tests claims and conclusions. Use when the user asks to talk to KAY/O, requests an adversarial review, or needs claims validated before publication.

bmad-ml-model-optimization

Optimize model quality, efficiency, and robustness. Use when the user requests to "optimize the model" or "run model optimization".

bmad-ml-omen

Standard reviewer for correctness and reproducibility. Use when the user asks to talk to Omen, requests a code review, or needs reproducibility verification.

bmad-ml-quick-experiment

Run fast lightweight experiment without full overhead. Use when the user requests to "run a quick experiment" or "test a quick hypothesis".

bmad-ml-results-analysis

Analyze experiment results with metric interpretation. Use when the user requests to "analyze the results" or "create a results report".

bmad-ml-onboard-lab

Scan and onboard existing ML project. Use when the user requests to "onboard my ML project" or "scan the codebase for ML context".

bmad-ml-lab-meeting

Run an AI Lab division meeting with research and build agents (no AI Startup agents). Use when the user requests to "start a lab meeting", "convene the lab", or "run a sprint retrospective for the lab".