PyAutoLabs

Start-of-day wake-up routine for the PyAuto workspace — sync every repo to main and clean generated cruft (local), then a gh-API status glance (overnight scheduled-run conclusions, version-pin drift, resume context) plus /health and /hygiene, ending in one prioritized digest. Runs on the CLI and on mobile Claude Code chat / Codex (auto-skips local-only steps when there is no workspace). Use when starting the day or asked for a morning status/cleanup pass.

Coordinate PyAuto build, deploy, or release execution through the PyAutoBrain Build Agent, including its vitals consultation and PyAutoHands delegation. Use when the user asks to build, publish, deploy, or release.

Use the single PyAuto health door for readiness assessment, validation sweeps, active-work status, release-run status, or worktree status through the Brain and Heart-owned procedures.

Periodic hygiene sweep across PyAuto repos and worktrees — audit stale feature branches, tracking refs, stashes, and dirty checkouts, then execute per-bucket cleanups after confirmation. Use for end-of-week tidying or unwieldy branch lists.

Ship PyAutoLabs source-library changes — run tests, commit, push, open pending-release PRs, analyze downstream workspace impact, and update the issue and PyAutoMind task state.

Analyze how a mature PyAuto domain assistant should be reproduced as an exact clone, sibling, or seed through the PyAutoBrain Clone Agent, and birth a lightweight seed once a human has answered the clone-mode question. Use for assistant-cell cloning decisions and seed births.

Run the visualization review loop through the PyAutoBrain Eyes Agent — survey a visualization workspace's figure surface, render via its gallery harness, review figures with the human, and route accepted critiques to intake/start_dev. Use when the user wants to look at, judge, or update the organism's plots and figures.

Hear and answer the PyAuto community through the PyAutoBrain Community Agent — scan every repo for user-filed issues awaiting a response, triage one issue's context sufficiency, then draft human-approved replies and route actionable work via start_dev_for_user. Use when responding to external users' GitHub issues or checking what the community is waiting on.

Build Jupyter notebooks and the LLM catalogue (llms-full.txt + workspace_index.json) from scripts, commit, push, raise a PR to main, merge it, then return to main locally.

Use when you need to execute Python files under scripts/ in this PyAutoGalaxy workspace, follow PyAutoHands's autogalaxy no_run policy, run in test mode by default, and fix failing scripts in place as you go without maintaining script_errors.md, script_errors_full.md, or .script_runner state.

Convert a PyAutoMind prompt file into a GitHub issue and register it — the Mind issue and registry primitive that start_dev delegates to.

Regenerate and optionally publish the PyAutoMind and PyAutoMemory fresh-slate template repositories from their live sources. Use for template drift checks or a human-confirmed template spawn, never for ordinary repository cloning.

Build Jupyter notebooks from scripts, commit, push, raise a PR to main, merge it, then return to main locally.

Build Jupyter notebooks from scripts, commit, push, raise a PR to main, merge it, then return to main locally.

Prepare PyAuto workspace repositories for a release by validating clean main branches, formatting and generating artifacts, committing, pushing, and dispatching the PyAutoHands release workflow. Use only after Heart readiness and the human version choice.