PyAutoBrainAgents & workflows

intake — File classified prompts; never start developmentconductor

batch — Propose a review-budgeted batch; collect its resultsconductor

community — Triage community threads; human-approved replies and development handoffsconductor

feature — Select, size and plan featuresconductor

bug — Classify regressions and plan repairsconductor

refactor — Plan behavior-preserving restructuringconductor

workspace — Plan or survey examples and tutorialsconductor

eyes — Survey figures and route accepted critiquesconductor

profiling — Plan campaigns; ingest results; triage profiling driftconductor

cortex — Pull science runs and record human checkinsconductor

hygiene — Prioritize upkeep and delegate fixesconductor

clone — Plan assistant births or synchronize generic filesconductor

build — Consult vitals and coordinate Hands executionconductor

release — Coordinate release rehearsal, validation and nightly executionconductor

health — Assess health and route repairsconductor

vitals — Read authoritative Heart readinessfaculty

review — Prepare independent CLEAN/FINDINGS/BLOCKED branch reviewfaculty

memory — Recall cited scientific and task historyfaculty

samplers — Inspect sampler coverage, tiers and benchmarksfaculty

sizing — Estimate task difficultyfaculty

brain — Run a named PyAutoBrain conductor or faculty directly through bin/pyauto-brain.skill

ci-speedup — Find the slowest CI parts on the PyAutoHeart board (smoke scripts, unit tests, workflow gates), and drive speed-ups through the dev flow.skill

docs — Start PyAutoLabs documentation, tutorial, notebook, example, or narrative-prose work through the Brain development workflow with the docs woskill

feedback — Draft user-reviewed feedback on using PyAutoLabs software and assistants (goals, successes, friction, evidence).skill

issue-cleanup — Reconcile the PyAuto GitHub issue trackers — audit open issues against Mind completion records and merged PRs, bucket them, close only what skill

prm — Judge every CI run and matrix leg, merge human-authorized PRs when green, then close the issue and Mind task and clean the worktree.skill

repo-cleanup — Periodic hygiene sweep across PyAuto repos and worktrees — audit stale feature branches, tracking refs, stashes, and dirty checkouts, then eskill

research — Start exploratory scientific, algorithmic, architectural, or prior-art investigation through the PyAutoBrain development workflow with the rskill

route — Infer the appropriate PyAutoBrain command or development work type from a free-form PyAutoLabs request.skill

sampler-pipeline — Trial a new non-linear sampler via ingest → prototype → profile → promote, up to a full PyAutoFit implementation.skill

ship-library — Validate and ship PyAuto library changes to pending-release PRs, including downstream impact and Mind state.skill

ship-workspace — Validate and ship PyAuto workspace or tutorial changes behind the library-first gate, then update Mind state.skill

start-dev — Plan and register PyAutoLabs development work, then route it to a library or workspace worktree.skill

start-dev-for-user — Start a PyAutoLabs development task for another contributor, including plan, issue, branch, and handoff preparation without claiming the locskill

start-library — Create or resume claimed PyAuto library worktrees after start-dev and prepare them for source edits.skill

start-workspace — Set up PyAutoLabs workspace or tutorial development — attach or create workspace worktrees, inspect upstream library API changes, and registskill

update-issue — Post a progress update to a GitHub issue from the current CLI session — commits, summary, and remaining work.skill