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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Read the current baseline. Use the immutable program.md snapshot embedded in your system prompt as policy when you write one complete assignment:
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.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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".
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。