agentsclimarketplace
Sign in

Mission control tflite deployment

Skill MN755/Codex-Mission_Control/.codex/skills/mission-control-tflite-deployment

Route TensorFlow Lite export and edge-readiness checks through Mission Control with explicit artifact and constraint validation.From its SKILL.md

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-tflite-deployment

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, 268 tokens by cl100k_base, as published. Nobody here has run it

Mission Control TensorFlow Lite Deployment

Purpose

Use Mission Control to validate TensorFlow Lite export and edge-deployment work so mobile or device targets get real artifact checks.

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 exports .tflite artifacts.
  • The user wants mobile, embedded, or edge deployment help.
  • Size, latency, or accuracy constraints matter.

Workflow

  1. Confirm the SavedModel or training source artifact.
  2. Ask Mission Control to validate conversion plus target constraints.
  3. Capture the produced .tflite artifact path and any post-conversion checks.
  4. Call out accuracy, latency, or memory risk instead of hiding it.

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 claim edge readiness because a conversion command exists.
  • Do not hide accuracy or latency regressions behind a successful export.

Example invocation

Use Mission Control to export and validate the TensorFlow Lite artifact for this product path.

What ships with it

Read from the repository

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

Keep looking

Skills are one crate of 326,144. 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.