all publishers

marin-community

@marin-community source repo

53 published skills

  1. ▌
    Debug 2 · marin-community
    Debug code bugs and operational faults while recording distilled hypotheses, evidence, and outcomes in Marin's shared Echo work log.
    4.1k repo stars
  2. ▌
    Commit 2 · marin-community
    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.
    4.1k repo stars
  3. ▌
    File Issue 2 · marin-community
    File a GitHub issue for a bug or improvement found this session.
    4.1k repo stars
  4. ▌
    Write Tests 2 · marin-community
    Write or revise 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.
    4.1k repo stars
  5. ▌
    Consult Echo 2 · marin-community bundle
    Search and cite Marin's shared Echo wiki, repository index, issues, pull requests, and optional Discord history. Use when prior cross-project decisions, incidents, workflows, exact errors, or reusable knowledge could inform a task, and before adding or revising an Echo wiki entry.
    4.1k repo stars
  6. ▌
    Write Ops Log 2 · marin-community
    Publish a durable debugging or infrastructure incident record to Echo. Use when a multi-step investigation reaches a conclusion, a failure needs a postmortem, or a recovery pattern should be visible across Marin projects.
    4.1k repo stars
  7. ▌
    Writing Style 2 · marin-community bundle
    Marin house writing style. Use when drafting or revising Marin-authored prose, including commit messages and GitHub PR, issue, or comment text.
    4.1k repo stars
  8. ▌
    Task Logbook · marin-community
    Maintain a cross-project task or research log in Echo. Use for multi-step investigations, experiments, long-running implementation work, or any task whose milestones must survive the current agent session without adding a repository logbook file.
    4.1k repo stars
  9. ▌
    Write Design Doc · marin-community
    Publish or revise a concise cross-project design proposal in Echo. Use for an explicit design task or a design-level change whose context, decision, interfaces, tradeoffs, and rollout need review without adding a repository design document.
    4.1k repo stars
  10. ▌
    Rl Supervisor Init · marin-community
    Initialize and run a focused RL operations session across Iris and explicitly selected supported backends: inventory jobs, dispatch diagnosis, perform authorized lifecycle actions, and maintain a reproducible handoff for an explicit list of experiment directories. This is a no-commit role that never edits repository code or configuration and never opens or updates pull requests.
    4.1k repo stars
  11. ▌
    Rl Agentic Job Cleanup · marin-community
    Preserve and, when authorized, publish a terminal agentic Iris RL run: stop pending retries, select and validate a checkpoint, export model weights, preserve metrics and traces, verify destinations, and only then reclaim storage. Use for runs with an agent harness or per-trial artifacts; use rl-standard-job-cleanup for parquet-only RL.
    4.1k repo stars
  12. ▌
    Rl Agentic Launch Iris · marin-community
    Validate, submit, and observe agentic MarinSkyRL training on Iris when the configuration uses Harbor, Daytona, terminal-bench, or another sandboxed agent harness.
    4.1k repo stars
  13. ▌
    Build Gpu Rl Image Iris · marin-community
    Build and validate compatibility MarinSkyRL GPU-RL containers when the user explicitly requests one. Maintained Iris training and utilities use frozen environments instead.
    4.1k repo stars
  14. ▌
    Rl Job Health Deep Dive · marin-community
    Diagnose one live or suspect RL job on Iris or an explicitly selected supported backend and return an evidence-backed KILL, NO-KILL, or ERROR recommendation. Use when ordinary state and metric checks cannot distinguish progress from a silent stall, or when validating a new model, geometry, configuration, or image. This is a read-only repository role: it never edits code, commits, pushes, opens PRs, or kills jobs.
    4.1k repo stars
  15. ▌
    Rl Standard Job Cleanup · marin-community
    Preserve, validate, and hand off a terminal standard MarinSkyRL run backed by dataset rows and programmatic rewards, without an agent harness or per-trial artifacts. Use after completion or failure, or before an authorized cancellation. Use rl-agentic-job-cleanup for agent trajectories.
    4.1k repo stars
  16. ▌
    Rl Standard Launch Iris · marin-community
    Validate, submit, and observe standard MarinSkyRL training on Iris for dataset-backed rewards without Harbor, Daytona, terminal-bench, or another agent harness.
    4.1k repo stars
  17. ▌
    Experiment Status Artifact · marin-community
    Render a fleet of experiment runs as a compact, operational status artifact. Use when a user needs a dashboard or overview across multiple runs, arms, datasets, or configurations rather than a prose report.
    4.1k repo stars
  18. ▌
    Debug · 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.
    4.1k repo stars
  19. ▌
    Commit · marin-community
    Use only when a change is ready to commit, push, or open or update its pull request; do not activate during implementation.
    4.1k repo stars
  20. ▌
    Noslop · marin-community bundle
    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.
    4.1k repo stars
  21. ▌
    Research · marin-community bundle
    Research an explicitly requested Marin question or coordinate a multi-session experiment; find prior work, assess evidence, and record results in the task's existing durable surface.
    4.1k repo stars
  22. ▌
    Use Iris · marin-community bundle
    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.
    4.1k repo stars
  23. ▌
    Add Grant · marin-community
    Implement a fully specified request for a GCP IAM resource grant or Cloud Run IAP viewer in marin-iac.
    4.1k repo stars
  24. ▌
    Fix Issue · marin-community
    Implement and land a fix for an explicitly identified marin-community/marin GitHub issue.
    4.1k repo stars
  25. ▌
    Review Pr · marin-community
    Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.
    4.1k repo stars
  26. ▌
    Scan Logs · marin-community
    Use scripts/logscan.py only when explicitly requested to scan an oversized log or to perform Gemini-backed log analysis.
    4.1k repo stars
  27. ▌
    File Issue · marin-community
    File a GitHub issue only when explicitly requested or delegated by another selected workflow; do not create issues merely because a problem was found.
    4.1k repo stars
  28. ▌
    Add Dataset · marin-community
    Register a named Hugging Face dataset for Marin by inspecting its schema and adding the appropriate experiments/datasets module.
    4.1k repo stars
  29. ▌
    Change Grug · marin-community
    Modify or upstream behavior in a named Grug/Grugformer experiment variant.
    4.1k repo stars
  30. ▌
    Lint Review · 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.
    4.1k repo stars
  31. ▌
    Run Ferries · marin-community
    Launch, monitor, or seal a Marin canary or daily ferry only when explicitly requested.
    4.1k repo stars
  32. ▌
    Update Docs · marin-community
    Update durable docs when explicitly requested or when current work changes behavior, exposes stale instructions, establishes an operational pattern, or yields reusable research guidance.
    4.1k repo stars
  33. ▌
    Write Tests · marin-community
    Add, revise, or review Marin tests for an explicit behavior change, regression, or test-quality request.
    4.1k repo stars
  34. ▌
    Consult Echo · marin-community bundle
    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.
    4.1k repo stars
  35. ▌
    Refresh Fork · marin-community bundle
    Refresh a named Marin external fork pin onto a newer upstream base using its configured descriptor and required end-to-end test.
    4.1k repo stars
  36. ▌
    Review Grant · 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.
    4.1k repo stars
  37. ▌
    Marina Applet · marin-community bundle
    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.
    4.1k repo stars
  38. ▌
    Query Finelog · 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.
    4.1k repo stars
  39. ▌
    Triage Canary · marin-community
    Triage a failed canary ferry run only when invoked by CI with the required CANARY context.
    4.1k repo stars
  40. ▌
    Write Ops Log · marin-community
    Publish a tagged Echo record after a live infrastructure incident, then link its canonical URL from the associated pull request or issue.
    4.1k repo stars
  41. ▌
    Writing Style · marin-community bundle
    Apply Marin house style when producing or revising commit, pull-request, issue, comment, documentation, report, or blog prose.
    4.1k repo stars
  42. ▌
    Ab Test Zephyr · marin-community
    Run an explicitly requested Zephyr control/treatment benchmark on the same pre-normalized sample and compare Finelog stage metrics.
    4.1k repo stars
  43. ▌
    Babysit Zephyr · marin-community
    Launch or continuously monitor a specified Zephyr pipeline on Iris only when asked to babysit it; restart only after explicit approval.
    4.1k repo stars
  44. ▌
    Manage Hero Run · marin-community
    Launch, resume, monitor, hand off, or seal an explicitly requested production-critical Marin run, normally at least 1e22 FLOPs.
    4.1k repo stars
  45. ▌
    Profile Training · marin-community
    Profile a named JAX, Levanter, or Marin run, or investigate a measured startup, compilation, initialization, or throughput bottleneck.
    4.1k repo stars
  46. ▌
    Add Pallas Kernel · marin-community bundle
    Add or change a named Pallas/Mosaic kernel, including its reference implementation, correctness tests, wrapper, or requested tuning.
    4.1k repo stars
  47. ▌
    Trace Pulumi Diff · marin-community bundle
    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.
    4.1k repo stars
  48. ▌
    Deploy Hero Change · 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.
    4.1k repo stars
  49. ▌
    Archive Experiments · marin-community
    Archive explicitly named legacy experiment files by publishing a dated tag and canonical issue breadcrumbs.
    4.1k repo stars
  50. ▌
    Organize Experiments · marin-community
    Harvest experiment issue reports and curate docs/reports/index.md only when explicitly requested.
    4.1k repo stars
  51. ▌
    Scrub Docs Code Parity · marin-community
    Run the docs/code-parity scrub only from its scheduler or an explicit request for that scrub.
    4.1k repo stars
  52. ▌
    Scrub Experiment Issue Tldrs · marin-community
    Run the experiment-issue TL;DR scrub only from its scheduler or an explicit request for that scrub.
    4.1k repo stars
  53. ▌
    Scrub Reflection Self Improvement · marin-community
    Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.
    4.1k repo stars