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.
Update durable docs when explicitly requested or when current work changes behavior, exposes stale instructions, establishes an operational pattern, or yields reusable research guidance.
Review the instructions the agent will receive before you install.
Use this when a task changes behavior, reveals stale instructions, creates a new operational pattern, or produces guidance that should survive outside the issue thread.
Prefer editing the nearest existing doc over adding a new one. Add a new doc only when the topic lacks a natural home or would make an existing page unfocused.
Follow .agents/skills/writing-style/SKILL.md for writing-style guidance.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
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.
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.
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.
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.
Launch and continuously monitor a specified Zephyr pipeline on Iris when asked. It checks coordinator and worker health, tracks stage progress, identifies stalled or repeated failures, and requires explicit approval before stopping or restarting jobs.