Skip to content
cccskills
FreePublished on GitHub

research-engineering

Explore Marin designs, datasets, and experimental pipelines through iterative analysis. Keep a runnable research branch and notebook that record alternatives and results, then prepare selected code for Marin pull requests.

OriginalShow the original description

Explore Marin designs, datasets, and experimental pipelines through iterative analysis and experiments; preserve a runnable research branch and notebook, then promote selected code into Marin PRs. Use for experimental programs, not bounded background research or routine debugging.

marin-community/marin4,043 stars(GitHub 4,043 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Compare implementation approaches through experiments
  • Analyze datasets before choosing an implementation
  • Record a research program’s attempts and results
  • Promote selected experimental code into Marin PRs

Files included (2)

  • SKILL.md3.1 KB
  • agents/openai.yaml293 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Research engineering

Use this skill when answering a question requires exploring alternatives, analyzing data or artifacts, or iterating on experiments before choosing an implementation. Work can start before any run is launched. Background research alone follows experiment records.

Read the research engineering guide for the record, branch, and promotion workflow. Read the current marin-logbooks guidelines before creating or updating its branches; research branches inherit Marin's root instructions rather than the logbooks index branch's instructions.

Coordinate the work

  • Start from the decision, baseline, constraints, and useful stopping condition. Search prior work through use-echo and inspect the current checkout.
  • Use a task issue in marin-community/marin-logbooks as the public entry point. Reuse an existing issue; when the task authorizes a new public research program, use file-issue with target repository marin-community/marin-logbooks to create its coordinating issue. An existing Marin issue can link to it. Do not publish private work without authorization.
  • Work on a Marin-derived branch in logbooks. Preserve the notebook and supporting analysis alongside the actual experimental source changes.
  • Record why each meaningful alternative was tried, the evidence it produced, what was learned, and the next decision. Commit and push supporting code and notebook entries before a milestone issue update or handoff.
  • Keep the issue body current and its comments useful as a readable account of the important attempts, results, and changes of direction.
  • Extract selected code into Marin contribution branches. Use manage-pr for their validation, publication, and feedback; keep the research branch intact. A useful negative result can finish a program without a code PR.

Delegate execution

Use the domain skill for each concrete operation, such as add-dataset, write-pipeline, launch-rl, add-pallas-kernel, or profile-training. use-iris owns job operations and query-finelog owns telemetry queries. This coordinating workflow does not authorize compute launches or recovery actions beyond the task's scope. Record meaningful restarts under their actual execution identities.

Babysit launched runs and PRs through a heartbeat: a scheduled follow-up in the host application that resumes monitoring after the active turn. Keep one monitor per task with its execution or PR identity, latest observation, owner, and exit condition. Report meaningful changes and required action; stay quiet while unchanged. Use use-iris for job completion checks and manage-pr for PR feedback and exit conditions.

Reviews

No reviews yet. Tell others what you thought.

Comments

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.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ab-test-zephyr

FreeSummary

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.

  • Compare Zephyr performance before and after a PR
  • Assess speed gains against additional CPU usage
  • Check peak memory and out-of-memory regressions
marin-community/marin4KUpdated Oct 29, 2026

add-dataset

FreeSummary

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.

  • Registering a Hugging Face dataset for Marin
  • Inspecting text fields without a full dataset download
  • Checking configurations and data splits
marin-community/marin4KUpdated Oct 29, 2026

add-grant

FreeSummary

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.

  • Prepare a request for GCS bucket read access
  • Add a viewer to a Cloud Run service protected by IAP
  • Prepare service account impersonation permissions
marin-community/marin4KUpdated Oct 29, 2026

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.

  • Adding a Pallas kernel for a JAX computation
  • Checking outputs and gradients against a reference
  • Maintaining backend selection and fallback behavior
marin-community/marin4KUpdated Oct 29, 2026

change-grug

FreeSummary

Try model or training changes in a copied Grug or Grugformer experiment, document the differences, and bring successful changes back into the base template while removing superseded experiment code and checking behavior.

  • Try changes to attention or masking
  • Experiment with optimizers or training loops
  • Bring successful changes into the base template
marin-community/marin4KUpdated Oct 29, 2026

Organize Marin experiment reports into a maintained index, or archive explicitly named older experiments using lasting tags and issue references. Existing conclusions and canonical links are preserved so experiment records remain traceable.

  • Organizing an index of experiment reports
  • Consolidating canonical report entries
  • Archiving named legacy experiments
marin-community/marin4KUpdated Oct 29, 2026

See all skills by marin-community

Report a problem with this skill