Skip to content
cccskills
FreePublished on GitHub

assign-experiment

Create a typed assignment branch and draft PR for one student. Use when the advisor has a concrete hypothesis and the student has no open `status:wip` or `status:review` assignment.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md1.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Assign an experiment

Read the current baseline. Use the immutable program.md snapshot embedded in your system prompt as policy when you write one complete assignment:

  • a falsifiable hypothesis and mechanism;
  • exact files and changes in scope;
  • baseline metrics and W&B evidence;
  • commands, run limits, metrics, and stopping conditions; and
  • one student, one branch, and one experiment.

Fetch the configured advisor branch and record its exact remote SHA. Call create_assignment with this operation-specific payload; the runtime supplies and enforces the configured advisor branch and student allowlist:

{
  "assignment_id": "stable-assignment-id",
  "revision_id": "initial-revision-id",
  "student": "student-name",
  "expected_base_sha": "FETCHED_REMOTE_ADVISOR_SHA",
  "head_branch": "student-name/hypothesis-slug",
  "title": "Concise hypothesis title",
  "body": "Complete actionable experiment brief"
}

The tool creates an empty assignment commit without changing the advisor worktree, pushes the branch with a lease, creates or reconciles one draft PR, adds the exact routing labels, embeds the typed assignment marker, verifies the result, and rejects a second active assignment for the student.

Do not create the branch, PR, labels, or assignment marker through shell commands. If the tool reports stale state, refresh the named SHA and re-evaluate rather than bypassing the precondition.

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

Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

Operator-side analysis of historical ML experiment PRs in Senpai research tracks. Use this skill whenever the user asks to: analyze experiments, categorize PRs, bucket experiments, summarize what's been tried, understand experiment history, review merged vs closed results, or asks "what experiments have we run / worked / failed". Also triggers for: "pull the latest experiments", "what's been tried so far", "category breakdown of PRs", "which experiments succeeded", "noam track analysis". When a branch name is mentioned (e.g. "noam branch", "on the noam branch"), pass it as the base branch to scope the fetch to just those PRs.

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

Create or improve a Senpai target repository's program.md. Use this skill whenever the user wants to point Senpai at a fresh ML or research target repository, define the research objective, primary metric, benchmark contract, allowed edit boundaries, W&B reporting contract, or prepare a repo for autonomous advisor/student experiment loops.

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

Open GitHub Issues for human input and respond to the researcher team. Use this skill whenever you need to handle a human_issue event, respond to human issues, ask humans a question, or check team communications. Also triggers for: "any human messages?", "check issues", "respond to humans".

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

Choose, configure, launch, and collect bounded subagents for research and engineering decisions. Root agents and delegation-capable subagents should read this before delegating: every task requires an explicit model tier, and high-leverage work such as research ideation, round planning, plateau pivots, large research reviews, hard optimization, disputed evidence, and expensive experiment portfolios requires frontier judgment.

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

Search the general web or scholarly publications through Exa. Use for current public information, official documentation, source code, release notes, papers, preprints, journals, or literature research.

The English summary is being prepared. Showing the original description.

wandb/senpai37Updated Oct 17, 2026

See all skills by wandb

Report a problem with this skill