with one click
marin
marin contains 31 collected skills from marin-community, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Lint, run the pre-PR checks, commit, push, and author or update the branch's pull request in the required plain-text format. Use when committing, pushing, or creating/updating a PR.
Modify or upstream a Grug/Grugformer experiment variant.
Run a perf gate on a PR that touches lib/zephyr internals.
Curate the experiment report index at docs/reports/index.md.
Triage a failed canary ferry run (CI-invoked).
Refresh Marin TPU-vLLM forks from a tpu-inference release/LKG pair, update exact SHA pins, run TPU smokes, and open the Marin PR.
Profile JAX training and analyze hotspots. Use when profiling or optimizing training throughput.
Multi-agent correctness review of a pull request.
Write or revise Marin tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding what test would catch a bug.
In CI, run the infra/lint catalog review over a PR.
End-to-end workflow to fix a GitHub issue in marin-community/marin.
Launch, monitor, and seal Marin canary and daily ferry runs.
Scheduled scrub: docs and code parity.
Scheduled scrub: repository self-improvement.
Produce a 1-page design doc, open a PR, and ping Discord for review.
Monitor an Iris job and recover it on failure. Use when asked to babysit or watch a job or run.
Launch, monitor, hand off, resume, rollback, or babysit expensive Marin production. Typically >=1e22 model flops.
De-rot markdown docs in lib/iris, lib/zephyr, and lib/fray.
Multi-session research workflow: logbooks, experiment issues, and W&B.
Scheduled scrub: TL;DR blocks on experiment issues.
Register or inspect a Hugging Face dataset for Marin pipelines.
Add, modify, or autotune a TPU/GPU Pallas kernel.
Retire legacy experiment scripts behind a dated archive tag.
Launch and babysit Zephyr pipeline jobs on Iris.
Debug code bugs or Iris/Zephyr/TPU infrastructure faults with a structured debug log.
File a GitHub issue for a bug or improvement found this session.
Reserve an Iris-backed TPU worker for fast debugging with dev_tpu.py.
Restart the Iris controller with state preservation.
Scan logs too large to read directly, using Gemini (scripts/logscan.py).
Write a postmortem ops log to .agents/ops/. Use after an infrastructure-debugging session.
Marin house writing style. Use when drafting or revising Marin-authored prose.