调研与学习技能

Developer reference for Senpai's retired direct-GitHub experiment logging workflow. Use only when auditing or migrating legacy research tracks.

中文简介正在准备中。当前显示原文说明。

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。

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。

Produce a fresh, read-only status report for a Senpai research track from GitHub, W&B, and the current agent's local controller state.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Coach the user through a rigorous, repository-grounded interview to create or improve program.md. Use when a target repository lacks program.md, its goals, metrics, data, or guardrails are unclear, or the user asks to be grilled about an autoresearch setup.

中文简介正在准备中。当前显示原文说明。

Elicit and challenge data-analysis requirements before querying. Use when the user asks ambiguous data questions, requests business/report answers, needs metric definitions clarified, or may be drawing decisions from incomplete data.

中文简介正在准备中。当前显示原文说明。

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

中文简介正在准备中。当前显示原文说明。

Load the essential AI Factory project context before work begins. Reads configured DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, RULES, and applicable AGENTS.md files, then returns a compact session handoff suitable for continuing or forking. Use at the start of a new session or after context loss.

中文简介正在准备中。当前显示原文说明。

Delegate an approved finite batch of engineering or research responsibilities, independent or linked by explicit predecessor inputs, using the operator's existing worker channel. Use for repository discovery, multiple search directions, evidence merging, repeated checks and substantial dirty work; keep internally coupled single tasks with one worker and explicit solo work in the main session.

中文简介正在准备中。当前显示原文说明。

将学术论文转换为交互式 HTML 课程 + Markdown 文档 + PPTX 演示文稿，一键生成全部三种输出

中文简介正在准备中。当前显示原文说明。

Enter explore mode to investigate ideas, systems, problems, and requirements before planning. Use explicit ultra mode when the user wants a durable adaptive research bundle with an index and only the justified C4, ADR, or dependency artifacts.

中文简介正在准备中。当前显示原文说明。

Elicit and challenge data-analysis requirements before querying. Use when the user asks ambiguous data questions, requests business/report answers, needs metric definitions clarified, or may be drawing decisions from incomplete data.

中文简介正在准备中。当前显示原文说明。

ACPXを使ってClaude CodeとCodexへ読み取り専用の調査を依頼し、人間の回答を挟んで最終レポートをまとめる

中文简介正在准备中。当前显示原文说明。

Turn photos with a clearly isolated landmark into two-color 3:4 kraft-paper stencil posters, in split comparison or full-canvas mode. Do not use when no single landmark is recognizable.

中文简介正在准备中。当前显示原文说明。

Turn uploaded photos into full-canvas 3:4 handcrafted travel diorama posters. Use for papercraft models, tactile miniature travel scenes, or when this skill is invoked.

中文简介正在准备中。当前显示原文说明。

Turn travel photos with recognizable people into 3:4 posters where real photographed environments contain warm-white paper sketch figures, in split comparison or full-canvas mode.

中文简介正在准备中。当前显示原文说明。

Turn photos into quiet 3:4 editorial posters using pure black ink masses, controlled stippling, pristine ivory paper, and either split comparison or full-canvas composition.

中文简介正在准备中。当前显示原文说明。

Turn travel photos into restrained 3:4 charcoal memory studies that physically fade into clean paper, with split comparison or full-canvas composition.

中文简介正在准备中。当前显示原文说明。

Turn uploaded travel photos into full-canvas 3:4 pixel-dissolve landscapes with abundant paper white. Use for curated limited-palette pixel studies or when this skill is invoked.

中文简介正在准备中。当前显示原文说明。

Use when planning a multi-article content strategy from a research corpus, creating domain maps for content topology, building production plans for pillar and cluster articles, or tracking cross-article production.

中文简介正在准备中。当前显示原文说明。

Use when ingesting source material for a writing project, building a knowledge map from notes and documents, identifying research gaps, or preparing a research corpus for content creation.

中文简介正在准备中。当前显示原文说明。

Use when capturing research artifacts to a vault or knowledge base, formatting source citations, saving synthesized connections from a writing project, or enriching a knowledge base with produced content.

中文简介正在准备中。当前显示原文说明。