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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Run Marin canary checks for training health or daily experiments with small configuration changes. Monitor each job to completion, record evaluation results, and close daily runs with a version tag and log update.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Diagnose failed canary ferry runs, automated checks for failures or regressions, when invoked by CI with the required context. It gathers logs, classifies the cause, and files a GitHub issue with supporting evidence.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Upload model weights to Hugging Face Hub with an OpenMDW 1.1 license and a required research warning. Check the published README and license file after uploading or updating to confirm that the required information is present.
中文简介正在准备中。当前显示英语简介。
Manage files in GCS, CoreWeave S3, R2, and local storage through Marin's fsutil command-line tool. List, inspect, copy, move, or synchronize data using bucket connections defined in the checkout's configuration.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Publish concise infrastructure incident records in Echo, with symptoms, response steps, causes, and evidence links. Search for existing records first, update ongoing incidents, and connect the published record to its related pull request or issue.
中文简介正在准备中。当前显示英语简介。
Add, revise, or review Marin tests for behavior changes, recurring bugs, or test quality improvements. Follow project testing guides to check meaningful behavior and protect public interfaces that external users depend on.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Compare Zephyr changes using the same prepared dataset and matching execution settings. Analyze Finelog metrics for each processing stage to distinguish CPU efficiency, elapsed time, and peak memory changes, then report improvements, regressions, or tradeoffs.
中文简介正在准备中。当前显示英语简介。