OpenParable
Skip to content
← Back to skills

Optimization From Data Orchestrator

Apps & Automation
optimization-from-data-orchestrator

Optimization From Data Orchestrator is an Agent Skill for apps & automation published in the NVIDIA/cuopt-examples repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/NVIDIA/cuopt-examples/blob/HEAD/cuopt_on_nemoclaw/openclaw-skills/optimization-from-data-orchestrator/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/optimization-from-data-orchestrator, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Optimization From Data Orchestrator

Top-level coordinator when a user provides tabular data and wants a constructive plan (schedule, assign, allocate, route — any wording).

NemoClaw: read cuopt-sandbox/references/activation.md for skill order and cuOpt-before-heuristic rules.

When to use

Both must hold:

  • tabular data provided or expected (CSV, etc.)
  • user wants a plan from that data (any phrasing; minimize/optimal not required)

Skip for analytics-only requests (summarize, chart, filter), fully pre-specified math outside this flow, or explicit replayable/auditable path.

Sequence

Step 0 (NemoClaw — do not skip): See cuopt-sandbox — probe → env → smoke. No schedule/heuristic output before smoke passes.

  1. optimization-intent-router — optimization family (LP/MILP/QP/routing)
  2. optimization-mode-router — only if replay/audit/export signals
  3. tabular-optimization-ingestion — table roles (interpretation only)
  4. cuopt-model-mapper — clarify if needed, map to cuOpt, solve

Handoffs after step 4:

  • LP / MILP / QP → numerical-optimization-formulation → cuopt-numerical-optimization-api-python
  • Routing → routing-formulation → cuopt-routing-api-python

Guardrails

  • First solver that emits assignments/schedules must be cuOpt after step 0
  • Ingestion steps do not authorize heuristic or greedy stand-ins
  • Do not skip intent classification; do not use cuOpt for pure analytics
  • One focused clarification beats a long questionnaire