Autolab Reporter
Productivityautolab-reporterAutolab Reporter is an Agent Skill for productivity published in the burtenshaw/multiautoresearch repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/burtenshaw/multiautoresearch/blob/HEAD/pre-training/.agents/skills/autolab-reporter/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/autolab-reporter, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Use this for the control-plane view of the experiment fleet.
Workflow
- Load the local operator env:
. ~/.autolab/credentials
- Sync the latest HF Jobs into Trackio:
uv run scripts/trackio_reporter.py sync --project autolab
- Review the human-readable summary:
uv run scripts/trackio_reporter.py summary --max-jobs 25
- Keep the live dashboard open when monitoring parallel runs:
uv run scripts/trackio_reporter.py dashboard --project autolab --mcp-server --no-footer
- For continuous reporting:
uv run scripts/trackio_reporter.py sync --project autolab --watch --interval 300
What To Watch
- active experiment jobs versus non-experiment jobs
- duplicate active jobs for the same experiment or hypothesis
preparejobs that still carry experiment labels, which usually indicate wasted bootstrap work- leaderboard entries that actually beat the current local promoted master
Guardrails
- Treat the reporter as the source of truth for fleet status, not stale shell output from one worker.
- If the reporter shows anomalies, fix those before launching more work into the same queue.
- Use the reporter to decide whether parallel capacity is real. A slot occupied by a duplicate or bootstrap job is not useful parallelism.