Maintain and publish the advisor-owned current research state, durable research-ideas syntheses, and dataset analysis. Use when evidence or human guidance changes the research focus or direction, durable research ideas should be recorded, or dataset understanding changes.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use the immutable program.md snapshot embedded in your system prompt. It defines
target-specific objectives, metrics, constraints, protected files, and any
baseline or research-log format.
Maintain these advisor-owned artifacts:
Keep research/CURRENT_RESEARCH_STATE.md as a living, pruned view of the
current high-level focus, themes, hypotheses, experiments, and potential next
directions. Do not use it as an archive or experiment-by-experiment log. Use
this schema:
# SENPAI Research State
- <current date and time>
- <most recent research direction from human researcher team>
- <current research focus and themes>
- <list of potential next research directions and themes>
Optionally record durable research or round-planning synthesis in
research/RESEARCH_IDEAS_<YYYY-MM-DD_HH:MM>.md.
Save rigorous dataset analysis and durable future dataset insights in
research/DATASET_ANALYSIS.md.
Commit only advisor-owned changes. Read the current remote advisor-branch SHA
and the local commit SHA, then call publish_advisor_branch:
{
"remote_branch_sha_before_push": "REMOTE_SHA_BEFORE_PUSH",
"local_commit_sha": "LOCAL_COMMIT_SHA"
}
Do not publish the advisor branch with git push.
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.
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.
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.
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.
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.
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.
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.