Loading...
Loading...
Found 57 Skills
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
Writing technical blog posts about tldraw features and implementation details. Use when creating blog content about how tldraw solves interesting problems.
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry
Document codebase as-is with research directory for historical context
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 9-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.
Multi-agent orchestration workflow for deep research: Split a research objective into parallel sub-objectives, run sub-processes using Claude Code non-interactive mode (`claude -p`); prioritize installed skills for network access and data collection, followed by MCP tools; aggregate sub-results with scripts and refine them chapter by chapter, and finally deliver "finished report file path + summary of key conclusions/recommendations". Applicable scenarios: systematic web/data research, competitor/industry analysis, batch link/dataset shard retrieval, long-form writing and evidence integration, or scenarios where users mention "deep research/Deep Research/Wide Research/multi-agent parallel research/multi-process research".
Research a topic in depth using web search, academic papers, and citation graphs. Use when the user asks to research, investigate, or explore a topic thoroughly.
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
Search the web using the agent's built-in WebSearch tool. Use when you need to find current information, verify facts, or research topics. No API key required. Keywords: search, web, internet, lookup, find, research, current events, facts.
Comprehensive DeepResearch methodology for conducting rigorous, traceable research projects with quality gates, structured analysis, and decision-ready deliverables. Use when (1) Conducting deep research projects requiring evidence-based analysis, (2) Managing research progress with quality gates and artifacts, (3) Producing research reports with traceable sources and structured reasoning, (4) Applying OSINT verification techniques, (5) Using structured analytic techniques (ACH, Key Assumptions Check, Red Team), (6) Expressing uncertainty and confidence in research findings, (7) Ensuring research deliverables meet intelligence tradecraft standards (ICD 203/206/208)