agentsclimarketplace

Mission control tf data pipelines

Skill MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-tf-data-pipelines

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-tf-data-pipelines

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

Use Mission Control to design or repair tf.data pipelines with explicit throughput, caching, and validation evidence.

SKILL.md

1.5 KB, as published. Nobody here has run it

Mission Control tf.data Pipelines

Purpose

Route TensorFlow input-pipeline work through Mission Control so tf.data changes stay measurable instead of becoming slow-motion folklore.

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 tf.data.
  • Data loading, batching, caching, shuffling, or TFRecord handling is the problem.
  • Training looks slow or unstable because the input path is suspect.

Workflow

  1. Identify the current data sources and pipeline entry points.
  2. Ask Mission Control to isolate whether correctness, throughput, or product skew is the main issue.
  3. Keep dataset construction, preprocessing, and training consumption visible as separate stages.
  4. Capture throughput or correctness evidence after the pipeline change.

Mission Control calls

Tools:

  • mission_control_start_task
  • mission_control_get_status

Resources:

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

Never do

  • Do not change the input pipeline without naming the data source and expected improvement.
  • Do not claim the model is fixed when the real problem was the pipeline.

Example invocation

Use Mission Control to fix the tf.data pipeline and show what evidence improved.

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.