agentsclimarketplace

Mission control keras finetuning

Skill MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-keras-finetuning

An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-keras-finetuning

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.

What its author says it does

Copied from the file, not written here

Route Keras fine-tuning and transfer-learning work through Mission Control with explicit baseline, unfreeze, and evaluation steps.

SKILL.md

1.5 KB, as published. Nobody here has run it

Mission Control Keras Fine-Tuning

Purpose

Use Mission Control to plan or execute Keras fine-tuning so transfer-learning changes preserve baseline comparisons and evaluation evidence.

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 user wants TensorFlow Hub or pretrained-model fine-tuning.
  • The repo already has a Keras model but the training strategy needs work.
  • Baseline versus tuned behavior needs to stay explicit.

Workflow

  1. Establish the current baseline model and metrics.
  2. Ask Mission Control to plan the freeze, unfreeze, and evaluation loop.
  3. Capture before/after evidence instead of declaring the tuned model better by instinct.
  4. Keep export compatibility visible if the tuned model must ship.

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 fine-tune blindly without a baseline.
  • Do not confuse a transfer-learning experiment with a product-ready model.

Example invocation

Use Mission Control to fine-tune the Keras model and compare it against the current baseline.

Keep looking

Skills are one crate of 328,083. 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.