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.
Harvest experiment issue reports and curate docs/reports/index.md only when explicitly requested.
Review the instructions the agent will receive before you install.
Curate docs/reports/index.md after new experiment issues are harvested: fold fresh entries into the right sections, refresh links, and leave ## Uncategorized empty.
uv commands.docs/reports/index.md.uv run scripts/pm/itemize_experiment_issues.py to append new experiments.docs/reports/index.md and identify the additions in ## Uncategorized.Training and Performance, Data Experiments).## Uncategorized.## Uncategorized and add a note explaining why.https://wandb.ai/... links when available; keep legacy api.wandb.ai links only if the direct share link does not exist.[] next to each experiment title.## Uncategorized empty whenever possible; a single placeholder sentence is fine.rg "^- " docs/reports/index.md to confirm bullets exist only under curated sections, not under ## Uncategorized.uv run scripts/pm/itemize_experiment_issues.py if unsure that all experiments were captured.markdownlint docs/reports/index.md to catch formatting drift.scripts/pm/itemize_experiment_issues.py for source data generation..agents/skills/archive-experiments/SKILL.md for retiring legacy experiments.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.