rl-skills

Orchestrator agent for agent-01-discovery

Orchestrator agent for agent-02-simulation

Orchestrator agent for agent-03-baseline

Orchestrator agent for agent-04-training

Orchestrator agent for agent-05-evaluator

Orchestrator agent for agent-06-deployment

Imposes hard limits on maximum computational timesteps and financial cloud spend for hyperparameter sweeps and training loops.

Aggressively audit W&B metrics and simulation replays to ensure the agent is solving the problem and not exploiting simulation bugs.

This skill should be used when the user asks to "evaluate feasibility", "check if RL is needed", "apply Occam's razor", or "compare with supervised learning". Do NOT proceed with RL formulations without passing this check.

This skill evaluates whether a fast, safe, and accurate simulation environment can be built for the agent to train in.

Develop a hard-coded, rule-based algorithm to establish the primary business baseline that the RL network must beat.

Develop a baseline random agent to stress-test the environment and establish minimum performance bounds.

This skill should be used when the user wants to "activate the rl evaluator", "invoke the evaluator agent", "evaluate the RL policy", "run evaluation tests", "diagnose training failures", "test robustness", "create visualization plots", "analyze saliency maps", or says "I need the evaluator to review the project". Orchestrates all evaluation, testing, and analysis tasks for a trained reinforcement learning policy.

This skill should be used when the user wants to "activate the rl mlops engineer", "invoke the mlops agent", "set up experiment tracking", "configure hyperparameter tuning", "scale distributed training", "configure checkpointing", "set up W&B or MLflow", "run Optuna/Ray Tune", or says "I need the mlops engineer to review the project". Orchestrates all infrastructure, tracking, and operational pipeline tasks for a reinforcement learning system.

This skill should be used when the user wants to "activate the rl algo engineer", "invoke the algorithm engineer", "implement the RL algorithm", "design neural networks for RL", "build the training loop", "implement PPO/SAC/DQN", "design the policy network", "configure replay buffers", or says "I need the algo engineer to review the project". Orchestrates all neural network and algorithm implementation tasks for a reinforcement learning system.

This skill should be used when the user wants to "activate the rl architect", "invoke the architect agent", "define the MDP", "formulate the RL problem", "design the state space", "design the reward function", "select the RL algorithm", or says "I need the architect to review the project". Orchestrates all theoretical design tasks for a reinforcement learning system from problem formulation to algorithm selection.

This skill should be used when the user wants to "activate the rl env engineer", "invoke the environment engineer", "implement the Gymnasium environment", "build the simulation", "implement observation wrappers", "add domain randomization", "integrate MuJoCo or PyBullet", or says "I need the env engineer to review the project". Orchestrates all simulation and environment implementation tasks for a reinforcement learning system.

This skill should be used when the user asks to "analyze saliency", "compute feature saliency", "run Grad-CAM", "apply integrated gradients", "extract attention weights", "visualize what the agent looks at", "inspect temporal attention maps", or "check if the memory architecture is useful". Do NOT hallucinate parameters outside the boundaries of Analyze Saliency and Values.

This skill should be used when the user asks to "blueprint the system architecture", "map the RL data flow", "design the RL pipeline", "define environment-agent interaction", "architect replay buffer placement", "design rollout and learner layers", or "draw the end-to-end RL system diagram". Do NOT hallucinate parameters outside the boundaries of Blueprint System Architecture.

This skill should be used when the user asks to "conduct adversarial testing", "run adversarial RL tests", "pit agents against antagonists", "apply FGSM attacks", "inject adversarial noise into observations", "test agent robustness against adversarial policies", "generate an adversarial stress report", or "find worst-case boundaries". Do NOT hallucinate parameters outside the boundaries of Conduct Adversarial RL Testing.

This skill should be used when the user asks to "configure checkpointing", "implement checkpoint strategy", "save best model", "set up EvalCallback", "implement periodic snapshots", "save replay buffer to disk", "resume training from checkpoint", or "implement EMA weights". Do NOT hallucinate parameters outside the boundaries of Configure Checkpoint Strategy.

This skill should be used when the user asks to "configure distributed rollouts", "set up SubprocVecEnv", "parallelize environment simulation", "scale rollout workers with Ray", "implement Ape-X architecture", "use IMPALA rollout workers", "serialize simulation across CPU clusters", or "calculate batch size for parallel envs". Do NOT hallucinate parameters outside the boundaries of Configure Distributed Rollouts.

This skill should be used when the user asks to "configure hyperparameter tuning", "set up Optuna for RL", "implement hyperparameter search", "use Ray Tune PBT", "implement population based training", "prune bad RL trials", "tune learning rate for RL", or "automate hyperparameter optimization". Do NOT hallucinate parameters outside the boundaries of Configure Hyperparameter Tuning.

This skill should be used when the user asks to "configure a replay buffer", "implement PER", "set up prioritized experience replay", "implement HER", "add hindsight experience replay", "build a ring buffer for RL", or "configure sample distributions for off-policy algorithms". Do NOT use for On-Policy algorithms (e.g., PPO/TRPO) as they do not maintain long-term replay buffers.

This skill should be used when the user asks to "create OOD tests", "test out-of-distribution robustness", "inject observation noise", "apply domain shift", "simulate actuator failure", "zero out action channels", "test agent outside training distribution", or "expose overfitting to training conditions". Do NOT hallucinate parameters outside the boundaries of Create OOD Robustness Tests.

This skill should be used when the user asks to "define the action space", "design action boundaries", "choose between discrete and continuous actions", "set up action masking", "formulate the action vector", "design agent action output", or "determine what actions the agent can take". Do NOT hallucinate parameters outside the boundaries of Define Action Space ($A$).

This skill should be used when the user asks to "define the MDP", "specify transition dynamics", "set episode termination conditions", "define truncation vs termination", "establish reset conditions", "determine if the problem is model-based or model-free", or "design the Markov Decision Process". Do NOT hallucinate parameters outside the boundaries of Define MDP & Transition Rules.

This skill should be used when the user asks to "define the state space", "design the observation space", "specify what the agent observes", "determine the agent's inputs", "assess the Markov property", "design observation normalization", or "formulate the observation vector". Do NOT hallucinate parameters outside the boundaries of Define State Space ($S$).

This skill should be used when the user asks to "design an adversarial environment", "implement a PAIRED pipeline", "create an antagonist policy", "build competitive dynamics for curriculum", "zero-sum environment design", or "make the environment challenge the agent". Do NOT hallucinate parameters outside the boundaries of Design Adversarial Environments.

This skill should be used when the user asks to "design an eval loop", "build a deterministic evaluation loop", "disable stochastic sampling during eval", "run deterministic policy inference", "evaluate agent performance properly", "set up isolated evaluation environments", "compute mean and std of episode rewards", or "run N-episode policy assessment". Do NOT hallucinate parameters outside the boundaries of Design Deterministic Eval Loop.

This skill should be used when the user asks to "design a feature extractor", "build a CNN feature extractor", "implement a Nature CNN", "add a ResNet backbone to RL", "handle dictionary observations", "process image observations in RL", "build preprocessing layers", or "implement multi-modal observation handling". Do NOT use Dropout or BatchNorm inside standard RL pipelines.

This skill should be used when the user asks to "design hierarchical RL", "implement the options framework", "build a meta-controller", "design sub-policies", "handle long-horizon tasks", "decompose tasks into subgoals", or "implement HRL with HIRO or feudal networks". Do NOT hallucinate parameters outside the boundaries of Design Hierarchical RL (HRL) Space.

This skill should be used when the user asks to "design a policy network", "implement an actor network", "build the action distribution layer", "implement Categorical distribution for RL", "implement Gaussian policy", "handle continuous action spaces", "implement multi-discrete actions", or "build the actor head for PPO/SAC/TD3". Do NOT apply Softmax directly to the network output before creating a Categorical distribution.

This skill should be used when the user asks to "design the reward function", "define the reward signal", "formulate reward shaping", "prevent reward hacking", "balance sparse and dense rewards", "add step penalties", or "structure multi-objective rewards". Do NOT hallucinate parameters outside the boundaries of Design Reward Function ($R$).

This skill should be used when the user asks to "design a value network", "implement a critic", "build a Q-network", "implement twin critic", "add target networks", "implement Polyak averaging", "build a state-value V(s) network", "build an action-value Q(s,a) network", or "design the critic for SAC/TD3/PPO". Do NOT apply any activation function to the final State-Value output layer.

This skill should be used when the user asks to "diagnose training failures", "debug policy collapse", "fix gradient vanishing", "address Q-value overestimation", "fix entropy collapse", "solve catastrophic forgetting", "understand why training crashed", "reward is stuck", "agent stops exploring", or "policy performance suddenly dropped". Do NOT hallucinate parameters outside the boundaries of Diagnose Training Failures.

This skill should be used when the user asks to "evaluate MARL equilibria", "test Nash equilibrium", "measure exploitability", "run cross-play evaluation", "run round-robin agent matchups", "check for catastrophic cycle-forgetting", "test population play", "validate multi-agent stability", or "check if the agent is in Nash equilibrium". Do NOT hallucinate parameters outside the boundaries of Evaluate MARL Equilibria.

This skill should be used when the user asks to "formulate imitation learning", "implement behavioral cloning", "design GAIL", "implement inverse reinforcement learning", "learn from expert demonstrations", "set up BC from human trajectories", or "use demonstration data to train an RL agent". Do NOT hallucinate parameters outside the boundaries of Formulate IRL and Imitation Learning.

This skill should be used when the user asks to "formulate multi-agent RL", "design MARL architecture", "implement CTDE", "set up cooperative or competitive agents", "design MAPPO", "implement QMIX", "handle multi-agent observation spaces", or "define agent communication protocols". Do NOT hallucinate parameters outside the boundaries of Formulate MARL Architecture.

This skill should be used when the user asks to "implement domain randomization", "add DR to the environment", "prevent sim-to-real gap", "randomize physics parameters", "apply ADR", "automatic domain randomization", or "randomize mass friction gravity". Do NOT hallucinate parameters outside the boundaries of Implement Domain Randomization.