Scheduled scrub: TL;DR blocks on experiment issues.
原文语言:英语
菜单
SkillsMP 已收集 marin-community/marin 中的 43 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 43 个已收集 Skill。
Scheduled scrub: TL;DR blocks on experiment issues.
原文语言:英语
Launch, monitor, hand off, resume, rollback, or babysit expensive Marin production. Typically >=1e22 model flops.
原文语言:英语
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.
原文语言:英语
Rebase one Marin fork onto newer upstream per its config/external/migration.toml descriptor, run the fork's e2e, and open the Marin PR or file a blocker issue.
原文语言:英语
Clean a branch with strict gates for low-value tests and agentic prose. Use when asked to deslop, simplify, clean up, make a diff minimal, review test quality, tighten comments/docs/PR text, or remove AI-writing patterns such as rhetorical "X, not Y"…
原文语言:英语
Marin house writing style. Use when drafting or revising Marin-authored prose, including commit messages and GitHub PR, issue, or comment text.
原文语言:英语
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.
原文语言:英语
Run a Zephyr control and treatment on pre-normalized data and compare per-stage Finelog CPU, elapsed-time, and memory stats. Use for ad hoc comparisons and PR performance gates; add named treatments only when requested.
原文语言:英语
Search and cite Marin's Echo activity and wiki, then capture incident records or reusable shared knowledge. Use when looking for prior discussions, decisions, workflows, incident patterns, exact errors, tags, or identifiers; when prior context could shorten…
原文语言:英语
Add, modify, or autotune a TPU/GPU Pallas kernel.
原文语言:英语
Publish a tagged postmortem incident record to Echo. Use after an infrastructure or durable debugging session, then link the canonical Echo URL from the associated PR or issue.
原文语言:英语
Produce a 1-page design proposal for an explicit design task or a design-level change identified by another change workflow. Do not use to answer or evaluate an idea inline.
原文语言:英语
End-to-end workflow to fix a GitHub issue in marin-community/marin.
原文语言:英语
Launch, monitor, and seal Marin canary and daily ferry runs.
原文语言:英语
Deploy the Iris controller to one cluster or across the fleet, with automatic progress through passed gates. Use when restarting, rolling out, or rolling back a controller.
原文语言:英语
Add a GCP IAM or IAP user grant to the marin-iac Pulumi stacks, encrypting human principals. Use when someone needs access to a project role, bucket/secret/service account, or an IAP-gated web service (evaldash, grafana), whether requested locally or on a…
原文语言:英语
Review a marin-iac user-grant PR by decrypting the changed principals into the real emails and grants, confirm with the user, then approve, merge, and drive pulumi up. Use when reviewing a PR that edits iam_data.yaml or a service's IAP viewers.
原文语言:英语
Reserve Iris-backed CoreWeave H100 or GB200 nodes with dev_gpu.py. Use for interactive GPU debugging, multi-node tests, or reconnecting to a dev GPU session.
原文语言:英语
Investigate a vLLM serve's performance (throughput, TTFT/TPOT latency, queue depth, KV-cache usage) from durable Finelog telemetry with SQL. Use when asked how an inference or eval serve performed, or why it was slow. For kernel-level JAX profiling, use…
原文语言:英语
Debug code bugs or Iris/Zephyr/TPU infrastructure faults with a structured incident record.
原文语言:英语
Diagnose and safely recover stuck terminating Kubernetes pods on Marin CoreWeave clusters, especially node-bound GPU pods. Use for deletion hangs, suspected uninterruptible GPU/NCCL waits, node cordoning or reboot decisions, and force-deletion requests.
原文语言:英语
Retire legacy experiment scripts behind a dated archive tag.
原文语言:英语
De-rot markdown docs in lib/iris, lib/zephyr, and lib/fray.
原文语言:英语
Curate the experiment report index at docs/reports/index.md.
原文语言:英语
Profile JAX training and analyze hotspots. Use when profiling or optimizing training throughput.
原文语言:英语
Multi-session research workflow: compose logbooks, experiment issues, documentation updates, and snapshot discipline for long-running investigations.
原文语言:英语
Create stable commit or tag snapshots for task milestones, experiment results, and reproducible artifact links.
原文语言:英语
File a GitHub issue for a bug or improvement found this session.
原文语言:英语
Multi-agent correctness review of a pull request.
原文语言:英语
Monitor an Iris job and recover it on failure. Use when asked to babysit or watch a job or run.
原文语言:英语
Triage a failed canary ferry run (CI-invoked).
原文语言:英语
In CI, run the infra/lint catalog review over a PR.
原文语言:英语
Register or inspect a Hugging Face dataset for Marin pipelines.
原文语言:英语
Forage prior work before or during Marin research threads: search internal Marin artifacts and external literature/code; produce a cited brief with negative results and ranked experiment hypotheses.
原文语言:英语
Maintain append-only task/research logbooks and publish the important parts upward into coordinating GitHub issues.
原文语言:英语
Update documentation, runbooks, and reusable task guidance when implementation work or experiments change behavior or operational practice.
原文语言:英语
Use W&B runs, reports, and artifacts consistently for experiments, benchmarks, and task results with dense numeric output.
原文语言:英语
Modify or upstream a Grug/Grugformer experiment variant.
原文语言:英语
Scheduled scrub: docs and code parity.
原文语言:英语
Scheduled scrub: repository self-improvement.
原文语言:英语