marin-community

Review a Marin pull request as a complete change, checking how it fits existing code, where simpler structures could work, and what might break beyond the edited lines. Receive findings with evidence and concrete replacements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing the design of a large pull request
• Checking structural issues in AI-generated code
• Investigating effects beyond the edited lines

Collect experiment reports from issues and organize them in an existing Markdown index. It places entries in relevant sections, merges WandB experiment links into existing records, and checks for duplicate entries and formatting inconsistencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding new experiment reports to an index
• Sorting uncategorized experiments
• Merging WandB links into existing entries

Profile JAX, Levanter, or Marin training to investigate slow startup, compilation, initialization, or throughput. Turn execution traces, recorded timing events, into structured reports, identify costly operations, and compare performance before and after a bounded change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate slow training startup or compilation
• Identify costly operations and communication delays
• Compare training performance before and after a change

Update external forks used by Marin to newer upstream code, review which custom patches to retain, update pinned revisions, and run required tests before preparing a draft pull request for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Update a fork to newer upstream code
• Review which custom patches to keep or drop
• Refresh related forks in one pull request

Analyze oversized logs with natural-language queries using Gemini. Extract matching original lines with line numbers, produce a Markdown summary, or combine both steps to focus a report on relevant errors and events.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find relevant lines in an oversized log
• Summarize log events around a specific question
• Extract errors before generating a focused report

Preview pending infrastructure changes in a specified Marin Pulumi stack without applying them. Trace each change to supporting code and merged pull requests when deployment history provides a reliable Git baseline.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking pending infrastructure changes before deployment
• Finding pull requests that explain resource changes
• Investigating differences without a matching code change

Register Hugging Face datasets for Marin by inspecting their structure without downloading the full dataset. Identify text fields, configurations, and data splits, then add a dataset module and validate the mapping with a sample.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Registering a Hugging Face dataset for Marin
• Inspecting text fields without a full dataset download
• Checking configurations and data splits

Review recent issues, pull requests, and recurring operational problems to choose a concrete repository improvement. Check for duplicate work, implement a suitable change, or document a plan and follow-up when implementation is blocked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find recurring problems in contributor workflows
• Update outdated documentation and agent instructions
• Reduce repeated manual work in operations

Design or revise Marin experiment pipelines by connecting reusable tasks and their outputs in a dependency graph. Organize shared implementations separately from experiment settings, then check that the workflow connects the intended inputs and stages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an experiment workflow entrypoint
• Connecting pipeline stages and outputs
• Separating reusable code from experiment settings

Review a Marin access-change pull request by decrypting user identities and explaining their roles and resources. After explicit human confirmation, merge the request and apply only the verified permission changes through Pulumi.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking who receives access in an encrypted grant request
• Reviewing roles and resources before approving access
• Applying confirmed permission additions or revocations

Prepare completed changes for commit and pull request review. It cleans the diff, runs repository checks, commits and pushes changes, prepares the pull request, and monitors automated checks and review feedback after publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking completed changes before committing
• Creating or updating a pull request
• Responding to CI failures and review feedback

Turn a specified GCP access request into a reviewable Pulumi change and pull request. Select the narrowest suitable role and encrypt personal email identities, covering resource permissions and Cloud Run viewer access through IAP, an access gateway.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a request for GCS bucket read access
• Add a viewer to a Cloud Run service protected by IAP
• Prepare service account impersonation permissions

Add or update Pallas/Mosaic kernels, specialized computation routines for JAX. The skill covers reference implementations, output and gradient checks, public wrappers, fallback behavior, performance benchmarks, and hardware-specific tuning when requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a Pallas kernel for a JAX computation
• Checking outputs and gradients against a reference
• Maintaining backend selection and fallback behavior

Preserve old experiment scripts with a dated Git tag, a named snapshot of the code, and add comments linking related GitHub issues to the archived files and cleanup pull request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving a snapshot of old experiment scripts
• Linking experiment issues to archived files
• Updating archive notices after a tag changes

Review a branch diff for tests that do not protect meaningful behavior, prose that adds no useful information, and unnecessary code structures. When editing is authorized, simplify the changes and verify them with focused tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing tests that do not protect meaningful behavior
• Trimming redundant comments and documentation
• Simplifying unused helpers and compatibility code

Investigate Marin questions or coordinate experiments across sessions by reviewing prior work, testing explanations against conflicting evidence, and recording conclusions. Results include source links, limitations, and confidence in the conversation or an existing project record.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review prior work on a Marin question
• Coordinate experiments across multiple sessions
• Compare hypotheses against conflicting and negative results

Check documentation and operator scripts against current code and command conventions. Correct confirmed mismatches in small, focused changes, publish them through a pull request, and report what was inspected when no update is needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check README instructions against current behavior
• Update outdated command examples
• Review documentation and code consistency on a schedule

Keep documentation aligned with changes to behavior, configuration, and operational procedures. It updates existing pages, corrects stale instructions, and preserves reusable workflow or research guidance so future readers can find authoritative information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Updating user documentation after behavior changes
• Correcting outdated operational procedures
• Documenting reusable agent workflows

Write and revise commits, pull requests, issues, documentation, reports, and blog posts using Marin's editorial style. Lead with results, support claims with evidence, explain limitations, and adapt the structure to the publication format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revising commit messages and pull request descriptions
• Writing issues with clear results and evidence
• Editing technical documentation and tutorials

Check a new internal Marin developer’s local environment and access to development services. Distinguish setup problems from missing permissions, repair authorized local issues, and provide a checklist of verified capabilities and remaining access requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a new Marin developer
• Validating a completed development setup
• Diagnosing missing service access

Investigate Finelog logs and runtime measurements for Iris tasks, training, and vLLM. Discover available fields, write time-bounded SQL, summarize resource usage, compare central and regional records, and interpret counters correctly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing Iris task memory and CPU usage
• Comparing central and regional logs for forwarding delays
• Aggregating vLLM counters with reset handling

Review a specified Marin pull request for newly introduced defects, repository instruction violations, and concrete maintenance problems. Receive findings backed by code evidence, with optional posting of review comments to GitHub.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check a pull request for newly introduced defects
• Verify compliance with repository instructions
• Review test quality and consistency across call sites

Review GitHub experiment issues and update concise summaries that explain the setup, investigation, and current conclusion. Add useful supporting links and maintain labels so newcomers can understand both ongoing and completed work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add summaries to experiment issues
• Update stale conclusions or unresolved blockers
• Make closed experiment issues easier to understand

Operate Iris jobs and tasks, from submission and monitoring to debugging and recovery. The skill also guides scheduling checks, coordination between clusters, controller deployments, development GPU or TPU reservations, and investigation of stuck CoreWeave pods.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitoring Iris jobs and investigating failures
• Diagnosing scheduling delays and cross-cluster coordination
• Deploying or rolling back controllers