Menu
Use when reproducing, deploying, diagnosing, tuning, visualizing, or reporting computational math research code with a coding agent
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Route AI4Math computational mathematics tasks to the appropriate bundled skill package.
This skill should be used when the user asks to search for external algorithms, find related implementations, discover alternative approaches, or look up papers and code for computational math optimization methods.
This skill should be used when the user asks to tune parameters, run hyperparameter search, optimize algorithm settings, or find the best configuration for a computational math method.
Use when classifying a computational math repository or task into a broad domain before choosing specialist Skills, references, runtimes, and validation evidence.
Use when a user starts an end-to-end computational math research-code reproduction, deployment, tuning, visualization, or reporting workflow with a coding agent.
This skill should be used when the user asks to detect what algorithm family a piece of code uses, identify optimization methods, or classify computational math approaches such as ADMM, PPA, proximal gradient, or primal-dual methods.
| name | scientific-computing-reproduction |
| description | Use when reproducing, deploying, diagnosing, tuning, visualizing, or reporting computational math research code with a coding agent |
This repository is a Skill-first computational math reproduction and tuning skill pack for coding agents. This file is a compatibility entrypoint for the shared Skill layer.
Start end-to-end work from:
skills/computational_math_reproduction_workflow_skill/SKILL.md
Use skills/registry.yaml to route to domain, runtime, environment, diagnosis, tuning, visualization, review, and reporting Skills.
This root SKILL.md is not the workflow driver. It is a compatibility entrypoint for platforms that expect one top-level Skill file.
| Platform | Adapter |
|---|---|
| Codex plugin | .codex-plugin/plugin.json |
| Codex local skills | .codex/INSTALL.md |
| Claude Code | .claude-plugin/plugin.json, CLAUDE.md |
| Cursor | .cursor-plugin/plugin.json |
| OpenCode | .opencode/INSTALL.md |
| Gemini CLI | GEMINI.md |
| Agent contract | AGENTS.md |
All adapters point back to the shared Skill layer under skills/. Do not fork workflow behavior into platform-specific files.
outputs/{run_id}/.matlab_runtime_skill, not as the controller.