MPC Controller Skill
Expert skill for Model Predictive Control implementation and tuning
npx skills add a5c-ai/babysitter --skill mpc-controller --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# MPC Controller Skill ## Overview Expert skill for designing, implementing, and tuning Model Predictive Controllers for robotic systems, including both linear and nonlinear MPC. ## Capabilities - Derive kinematic and dynamic robot models - Formulate MPC optimization problems (QP, NLP) - Configure CasADi for symbolic differentiation - Set up ACADO code generation for real-time MPC - Implement constraint handling (velocity, acceleration, collision) - Configure cost function weights (tracking, control effort) - Implement warm starting for fast convergence - Set up NMPC for nonlinear systems - Configure terminal constraints and costs - Optimize solver parameters for real-time execution ## Target Processes - mpc-controller-design.js - trajectory-optimization.js - dynamic-obstacle-avoidance.js - path-planning-algorithm.js ## Dependencies - CasADi - ACADO Toolkit - OSQP - qpOASES - Ipopt ## Usage Context This skill is invoked when processes require advanced model-based control, trajectory tracking with constraints, or real-time optimization-based control strategies. ## Output Artifacts - MPC formulation code - CasADi symbolic models - ACADO generated code - QP/NLP solver configurations -
- Overview
- Capabilities
- Target Processes
- Dependencies
- Usage Context
- Output Artifacts
What does the MPC Controller Skill skill do?
Expert skill for Model Predictive Control implementation and tuning
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill mpc-controller --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.