marin-community
@marin-community Organization
Public Skills
trace-pulumi-diff
by marin-community
Run a read-only preview for a specified Marin infra/pulumi stack and trace each pending resource change to merged pull requests since its latest successful update when that update records a clean Git checkout. Use when a stack has unapplied changes or drift and someone needs to know which PRs explain the preview.
deploy-hero-change
by marin-community
"Deploy a significant code change (backend, kernel, optimizer, data path) to the live hero run: relaunch it under a new run id from a permanent checkpoint, compare against the old run over a trial window, and roll back if the gate fails; use only when the user asks to deploy a change to the hero."
marina-applet
by marin-community
Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet. Use for Artifact+-style web apps that should run behind Marina authentication, carry small bundled assets or data, use an applet-owned Postgres schema, or add a trusted Python ASGI backend without a Marina image deployment.
review-pr
by marin-community
Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.
write-ops-log
by marin-community
Publish a tagged Echo record after every incident, then link its canonical URL from the associated pull request or issue.
consult-echo
by marin-community
Search or cite Echo when Marin's prior-work policy applies, another selected workflow requires it, or the user explicitly asks; do not substitute it for local code search.
refresh-fork
by marin-community
Refresh a named Marin external fork pin onto a newer upstream base using its configured descriptor and required end-to-end test.
lint-review
by marin-community
Run the read-only infra/lint PR reporter only when invoked by CI or explicitly requested; do not select it for the commit workflow's fix-and-respond review.
commit
by marin-community
Use only when a change is ready to commit, push, or open or update its pull request; do not activate during implementation.
query-finelog
by marin-community
Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding. Use for schema discovery, SQL, memory or CPU summaries, hub-versus-regional comparisons, counter semantics, and query-performance diagnosis.
triage-canary
by marin-community
Triage a failed canary ferry run only when invoked by CI with the required CANARY context.
use-iris
by marin-community
Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs. Use for ordinary Iris operations, including babysitting a job, controller rollouts, accelerator sessions, and stuck CoreWeave pods. Use a narrower production-run or Zephyr skill when that workflow is explicitly requested.
run-ferries
by marin-community
Launch, monitor, or seal a Marin canary or daily ferry only when explicitly requested.
manage-hero-run
by marin-community
Launch, resume, monitor, hand off, or seal an explicitly requested production-critical Marin run, normally at least 1e22 FLOPs.
run-research
by marin-community
Run a coordinated multi-session research program only when explicitly requested; maintain a logbook and durable snapshots.
debug
by marin-community
Diagnose a stated code, JAX, Marin, Iris, Zephyr, or TPU fault or startup/performance regression; do not activate for ordinary implementation or optimization without a symptom.
review-grant
by marin-community
Review an explicitly identified marin-iac grant PR that edits IAM data or a deploy-target module, confirm its decrypted principals and roles, then apply only the confirmed grant.
add-grant
by marin-community
Implement a fully specified request for a GCP IAM resource grant or Cloud Run IAP viewer in marin-iac.
task-logbook
by marin-community
Maintain a task logbook only when explicitly requested for durable cross-session notes, reproducible experiments, or a coordinating issue; entries are append-only while summary indices may change.
profile-training
by marin-community
Profile a named JAX, Levanter, or Marin run, or investigate a measured startup, compilation, initialization, or throughput bottleneck.
wandb-reporting
by marin-community
Publish W&B runs, reports, or artifacts only when explicitly requested or required for a requested experiment's dense numeric results.
scrub-experiment-issue-tldrs
by marin-community
Run the experiment-issue TL;DR scrub only from its scheduler or an explicit request for that scrub.
scrub-docs-code-parity
by marin-community
Run the docs/code-parity scrub only from its scheduler or an explicit request for that scrub.
scan-logs
by marin-community
Use scripts/logscan.py only when explicitly requested to scan an oversized log or to perform Gemini-backed log analysis.