全部能力

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

将学术论文转化为深度技术文章，支持多种写作风格选择。 使用 MinerU Cloud API 高精度解析 PDF，自动提取图片、表格、公式。 可选公式讲解、GitHub 代码分析，生成 Markdown 和 HTML 格式。

Builds interactive HTML presentation from project docs with Mermaid diagrams. Use when sharing project overview with stakeholders.

验证研究报告中所有声明的引用准确性、来源质量和格式规范性。确保每个事实性声明都有可验证的来源，并提供来源质量评级。当最终确定研究报告、审查他人研究、发布或分享研究之前使用此技能。

Explore-lane code adaptation skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated…

Set up or update the agent-first engineering harness for any repository. Implements the complete scaffolding that makes AI coding agents effective: knowledge maps (AGENTS.md as a concise TOC), structured documentation, architecture boundaries, enforcement rules (.harness/*.yml specs), quality scoring, and process patterns for agent-driven development. Use this skill whenever someone wants to make a repo agent-ready, set up AGENTS.md or docs/ structure, define domain boundaries or golden principles, generate .harness/ configuration, audit agent readiness, or update an existing harness. Also trigger when a user reports problems with agent effectiveness, context management, or architectural drift — these are symptoms of a missing or stale harness. Trigger on: "harness this repo", "set up harness", "agent-first setup", "make this agent-ready", "update the harness", "assess agent readiness", "set up AGENTS.md", "organize for agents", or any discussion about structuring a codebase for AI agent workflows.

Create lead magnets and gated content to capture email subscribers and leads. Use when asked to design checklists, templates, calculators, mini-courses, whitepapers, or other downloadable content offers. Trigger phrases: "lead magnet", "gated content", "email capture", "content offer", "free download", "checklist", "template", "whitepaper", "swipe file", "content upgrade", "opt-in offer".

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews,…

Trusted-lane training execution skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively…

Documentation generation workflow covering API docs, architecture docs, README files, code comments, and technical writing.

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants…

Track competitor blog posts, whitepapers, and content strategy. Identify content gaps in your strategy.

Integrate Firebase services including Authentication, Firestore, Cloud Messaging, Crashlytics, and Analytics. Use when adding backend capabilities, push…

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does…

Generate pre-call research briefs with company news, stakeholder backgrounds, and custom discovery question sets.

Search the web for information. Use when you need to look something up, find current information, or research a topic.

Agent-native CLI for Exa web search and content retrieval workflows.

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze,…

Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds…