How do I install the Dymos Trajectory skill?

Run npx skillmds@latest add ashfordeou/dymos-trajectory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dymos Trajectory safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dymos Trajectory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dymos Trajectory free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Dymos Trajectory?

ashfordeOU (@ashfordeou) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dymos Trajectory by ashfordeou — Agent Skill

Name: Dymos Trajectory
Author: ashfordeOU

Dymos Trajectory

Use when setting up and assessing pseudospectral trajectory optimization with Dymos: plan optimal-control problems as phases with collocation nodes, check that phase setup includes initial-state and final bounds plus an objective, and verify convergence, state continuity across segments, and total delta-v against expected budgets for ascent or orbit-transfer trajectories. Flags under-resolved phases (fewer than 5 nodes), unconverged runs, and discontinuities at segment boundaries. Trigger: trajectory optimization, optimal control, dymos, pseudospectral, phase, convergence, collocation, launch ascent, bounds.

ashfordeOU 94b88db 3 files · 9.8 KB Updated Sep 17, 2026

File contents

Dymos Trajectory Optimization (gnc-autonomy/optimal-control/dymos-trajectory)

Use when the task is pseudospectral trajectory optimization with Dymos: phase setup, convergence checks, and trajectory validation.

Domain quick reference

Dymos transcribes optimal-control problems into phases solved with pseudospectral collocation; each phase needs a node count, state bounds, and an objective.
Minimum usable collocation node count in this contract: 5.
A solved trajectory must converge within the iteration and tolerance limits (default max_iter 50, tol_limit 1e-4).
State values must be continuous across segment boundaries.
Total delta-v should match the expected budget within a tolerance (default 10%).

Workflow

Define the phases: node count, initial- and final-state bounds, objective.
Check phase setup completeness with scripts/dymos_logic.py before solving.
Solve and check convergence (iterations, tolerance).
Verify state continuity at segment boundaries.
Compare total delta-v against the expected budget.

Pitfalls

Solving with under-resolved phases (fewer than 5 nodes) and trusting the result.
Missing initial/final bounds or objective in the phase definition.
Accepting a run that hit the iteration cap without tightening the mesh or scaling.
Treating segment-boundary discontinuities as converged.

Behavior contract (gate 3)

The phase-setup, convergence, continuity, and delta-v logic is exercised by the gate 3 contract test: scripts/test_dymos.py against scripts/dymos_logic.py (stdlib unittest, offline). Run: python3 scripts/test_dymos.py

Compliance

ARP4754A is proprietary (SAE); name + paraphrase only per standards-map.yaml and brief 06 (revision note: ARP4754B supersedes; this skill keys to A, the certification-baseline revision).
compliance: STANDARDS-REF, gated: false.

---name: dymos-trajectorydescription: Use when setting up and assessing pseudospectral trajectory optimization with Dymos: plan optimal-control problems as phases with collocation nodes, check that phase setup includes initial-state and final bounds plus an objective, and verify convergence, state continuity across segments, and total delta-v against expected budgets for ascent or orbit-transfer trajectories. Flags under-resolved phases (fewer than 5 nodes), unconverged runs, and discontinuities at segment boundaries. Trigger: trajectory optimization, optimal control, dymos, pseudospectral, phase, convergence, collocation, launch ascent, bounds.license: Apache-2.0---# Dymos Trajectory Optimization (gnc-autonomy/optimal-control/dymos-trajectory)Use when the task is pseudospectral trajectory optimization withDymos: phase setup, convergence checks, and trajectory validation.## Domain quick reference- Dymos transcribes optimal-control problems into phases solved with pseudospectral collocation; each phase needs a node count, state bounds, and an objective.- Minimum usable collocation node count in this contract: 5.- A solved trajectory must converge within the iteration and tolerance limits (default max_iter 50, tol_limit 1e-4).- State values must be continuous across segment boundaries.- Total delta-v should match the expected budget within a tolerance (default 10%).## Workflow1. Define the phases: node count, initial- and final-state bounds, objective.2. Check phase setup completeness with scripts/dymos_logic.py before solving.3. Solve and check convergence (iterations, tolerance).4. Verify state continuity at segment boundaries.5. Compare total delta-v against the expected budget.## Pitfalls- Solving with under-resolved phases (fewer than 5 nodes) and trusting the result.- Missing initial/final bounds or objective in the phase definition.- Accepting a run that hit the iteration cap without tightening the mesh or scaling.- Treating segment-boundary discontinuities as converged.## Behavior contract (gate 3)The phase-setup, convergence, continuity, and delta-v logic isexercised by the gate 3 contract test: scripts/test_dymos.py againstscripts/dymos_logic.py (stdlib unittest, offline). Run:python3 scripts/test_dymos.py## Compliance- ARP4754A is proprietary (SAE); name + paraphrase only per standards-map.yaml and brief 06 (revision note: ARP4754B supersedes; this skill keys to A, the certification-baseline revision).- compliance: STANDARDS-REF, gated: false.

Frequently asked questions