agentsclimarketplace
Sign in

Mission control model optimization

Skill MN755/Codex-Mission_Control/.codex/skills/mission-control-model-optimization

Use Mission Control to plan bounded TensorFlow model optimization work such as quantization or pruning with explicit tradeoffs.From its SKILL.md

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-model-optimization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, 262 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Model Optimization

Purpose

Use Mission Control to plan or review TensorFlow model-optimization work so quantization, pruning, and compression changes stay evidence-backed.

The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.

Use when

  • The repo uses TensorFlow Model Optimization Toolkit or equivalent flows.
  • The user wants smaller, faster, or more device-friendly models.
  • Accuracy tradeoffs must stay visible.

Workflow

  1. Establish the baseline model size, latency, and quality.
  2. Ask Mission Control to keep optimization work bounded and comparable.
  3. Capture before/after artifact evidence plus any degraded metrics.
  4. Keep deployment target constraints visible throughout the loop.

Mission Control calls

Tools:

  • mission_control_start_task
  • mission_control_get_status
  • mission_control_get_handoff_summary

Resources:

  • mission-control://projects/{project_id}/validation-summary
  • mission-control://projects/{project_id}/handoff

Never do

  • Do not optimize blindly without a baseline.
  • Do not celebrate a smaller model that quietly became worse where the product actually cares.

Example invocation

Use Mission Control to evaluate TensorFlow quantization or pruning changes against the current baseline.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,871. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.