agentsclimarketplace

Mission control tensorboard observability

Skill MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-tensorboard-observability

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-tensorboard-observability

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 turn TensorBoard logs and training curves into explicit validation evidence.

SKILL.md

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

Mission Control TensorBoard Observability

Purpose

Use Mission Control to plan or review TensorBoard-backed observability so training claims have actual telemetry behind them.

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 logs to TensorBoard.
  • The user wants to understand training behavior, regressions, or tuning outcomes.
  • Model quality claims need evidence.

Workflow

  1. Confirm where TensorBoard logs live.
  2. Ask Mission Control to read the training lane together with tests or export results.
  3. Summarize the useful signals, not every pixel in the curve set.
  4. Keep missing logs visible as a blocker instead of faking insight.

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 describe training as healthy if there are no logs or metrics.
  • Do not confuse pretty curves with product readiness.

Example invocation

Use Mission Control to review the TensorBoard evidence for this TensorFlow training run.

Gives 0 of the 12 instructions most monitoring observability skills give in 262 tokens

Counted across 481 of the 483 authors here whose files we hold, read 2026-08-06

  • link every alert to a runbookin 43 of 481, across 35 files
  • use structured json loggingin 36 of 481, across 31 files
  • alert on user-facing symptomsin 20 of 481, across 15 files
  • emit structured JSON logs with stable event namesin 18 of 481, across 13 files
  • propagate trace context across boundariesin 16 of 481
  • use histograms for latency trackingin 14 of 481, across 9 files
  • use OpenTelemetry for distributed tracingin 13 of 481, across 8 files
  • include a correlation ID on every log linein 13 of 481, across 8 files
  • Define service level objectivesin 10 of 481, across 7 files
  • Call useAzureMonitor before importing other modulesin 9 of 481, across 2 files
  • stop and ask for clarification if inputs are missingin 9 of 481, across 2 files
  • define on-call questions before adding telemetryin 9 of 481, across 4 files

Said here and by no other author read

  • confirm where tensorboard logs live
  • ask mission control to read training lane results
  • summarize useful signals only
  • keep missing logs visible as a blocker

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.