Top Rated
The most starred skills loved by the community. Quality guaranteed!
task-logbook
by marin-community
Maintain a task logbook only when explicitly requested for durable cross-session notes, reproducible experiments, or a coordinating issue; entries are append-only while summary indices may change.
ab-test-zephyr
by marin-community
Run an explicitly requested Zephyr control/treatment benchmark on the same pre-normalized sample and compare Finelog stage metrics.
babysit-zephyr
by marin-community
Launch or continuously monitor a specified Zephyr pipeline on Iris only when asked to babysit it; restart only after explicit approval.
add-dataset
by marin-community
Register a named Hugging Face dataset for Marin by inspecting its schema and adding the appropriate experiments/datasets module.
add-pallas-kernel
by marin-community
Add or change a named Pallas/Mosaic kernel, including its reference implementation, correctness tests, wrapper, or requested tuning.
archive-experiments
by marin-community
Archive explicitly named legacy experiment files by publishing a dated tag and canonical issue breadcrumbs.
change-grug
by marin-community
Modify or upstream behavior in a named Grug/Grugformer experiment variant.
file-issue
by 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.
fix-docs
by marin-community
De-rot Markdown under lib/iris, lib/zephyr, or lib/fray only when explicitly requested.
fix-issue
by marin-community
Implement and land a fix for an explicitly identified marin-community/marin GitHub issue.
organize-experiments
by marin-community
Harvest experiment issue reports and curate docs/reports/index.md only when explicitly requested.
profile-training
by marin-community
Profile a named JAX, Levanter, or Marin run, or investigate a measured startup, compilation, initialization, or throughput bottleneck.
task-snapshot
by marin-community
Create a commit or tag snapshot only when explicitly requested for a milestone, reproducibility checkpoint, handoff, or pinned artifact.
scan-logs
by marin-community
Use scripts/logscan.py only when explicitly requested to scan an oversized log or to perform Gemini-backed log analysis.
scrub-docs-code-parity
by marin-community
Run the docs/code-parity scrub only from its scheduler or an explicit request for that scrub.
scrub-experiment-issue-tldrs
by marin-community
Run the experiment-issue TL;DR scrub only from its scheduler or an explicit request for that scrub.
scrub-reflection-self-improvement
by marin-community
Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.
update-docs
by 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.
wandb-reporting
by marin-community
Publish W&B runs, reports, or artifacts only when explicitly requested or required for a requested experiment's dense numeric results.
write-design-doc
by marin-community
Create Marin design-doc artifacts only when explicitly asked for a design doc, one-pager, or proposal; do not use for inline architecture discussion.
write-tests
by marin-community
Add, revise, or review Marin tests for an explicit behavior change, regression, or test-quality request.
writing-style
by marin-community
Apply Marin house style when producing or revising commit, pull-request, issue, comment, documentation, report, or blog prose.
background-research
by marin-community
Perform an explicitly requested prior-work search for a Marin research, design, or experiment decision and produce a cited brief.
skill-parallel-agents
by nyldn
Multi-tentacled orchestration using Double Diamond methodology. Use when: PRIORITY TRIGGERS (always invoke immediately):. "/octo:multi" (explicit command). "run this with all providers", "run with all providers"