跳到正文
cccskills
免费在 GitHub 公开

alphaxiv-paper-lookup

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。

wandb/senpai

实测评分 未实测

查看安装方法

包含的文件（1）

  • SKILL.md2.3 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

AlphaXiv Paper Lookup

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.

When to Use

  • User shares an arxiv URL (e.g. arxiv.org/abs/2401.12345)
  • User mentions a paper ID (e.g. 2401.12345)
  • User asks you to explain, summarize, or analyze a research paper
  • User shares an alphaxiv URL (e.g. alphaxiv.org/overview/2401.12345)

Workflow

Step 1: Extract the paper ID

Parse the paper ID from whatever the user provides:

InputPaper ID
https://arxiv.org/abs/2401.123452401.12345
https://arxiv.org/pdf/2401.123452401.12345
https://alphaxiv.org/overview/2401.123452401.12345
2401.12345v22401.12345v2
2401.123452401.12345

Step 2: Fetch the machine-readable report

curl -s "https://alphaxiv.org/overview/{PAPER_ID}.md"

This returns the intermediate machine-readable report — a structured, detailed analysis of the paper optimized for LLM consumption. One call, plain markdown, no JSON parsing.

If this returns 404, the report hasn't been generated for this paper yet.

Step 3: If you need more detail, fetch the full paper text

If the report doesn't contain the specific information the user is asking about (e.g. a particular equation, table, or section), fetch the full paper text:

curl -s "https://alphaxiv.org/abs/{PAPER_ID}.md"

This returns the full extracted text of the paper as markdown. Only use this as a fallback — the report is usually sufficient.

If this returns 404, the full text hasn't been processed yet. As a last resort, direct the user to the PDF at https://arxiv.org/pdf/{PAPER_ID}.

Error Handling

  • 404 on Step 2: Report not generated for this paper.
  • 404 on Step 3: Full text not yet extracted for this paper.

Notes

  • No authentication required — these are public endpoints.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

analyze-experiments

免费

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。

wandb/senpai372026年10月24日 更新

assign-experiment

免费

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。

wandb/senpai372026年10月24日 更新

bootstrap-target

免费

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。

wandb/senpai372026年10月24日 更新

check-human-issues

免费

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。

wandb/senpai372026年10月24日 更新

check-senpai-experiments

免费

Check scientific progress and operational health of a Senpai research program against the mission in its target repository's program.md. Use for experiment updates, health checks, current advisor/student activity, promising or failed experiments, W&B/GitHub reconciliation, evaluation status, and next research priorities. Produce a fresh, read-only, evidence-backed report with clear implications and actions. Do not use for cluster-capacity-only checks or to mutate research state.

中文简介正在准备中。当前显示原文说明。

wandb/senpai372026年10月24日 更新

delegate-subagents

免费

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。

wandb/senpai372026年10月24日 更新

查看 wandb 的全部技能

报告此技能的问题