Yang Ruofeng

Check BibTeX references against web records and export field differences in a spreadsheet. Independent checking depends on an isolated web agent; without isolation, results flag potential issues rather than certify matching entries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking bibliography fields before paper submission
• Finding author omissions and ordering errors
• Reviewing reference discrepancies in a spreadsheet

Compare local BibTeX references with independently retrieved web records to identify missing or reordered authors, incorrect years, venues, and identifiers. Export a side-by-side spreadsheet with per-reference verdicts and evidence for discrepancies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking bibliography fields before paper submission
• Finding author omissions and ordering errors
• Reviewing reference discrepancies in a spreadsheet

Develop mathematical proofs in Lean, a system that checks formal proofs, continue unfinished projects, or audit existing results. Check that the theorem matches the original claim, examine its assumptions, and prepare sources and commands for reproduction.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a mathematical statement into a checked Lean proof
• Continue an unfinished Lean proof project
• Audit whether a theorem proves the original claim

Build a runnable prototype from a plain feature request, then add capabilities one step at a time. The skill records consequential assumptions before coding, checks each step, and reports remaining placeholders, deferred work, and review limits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a runnable prototype from a feature description
• Extending a prototype through checked feature steps
• Recording decisions where requirements are unclear

Launch machine learning training jobs on local or remote GPUs. The skill checks available GPU memory, synchronizes code, saves logs, and verifies startup, with optional experiment tracking and support for Vast.ai and Modal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch training on an available remote GPU
• Run experiments locally with CUDA or MPS
• Record training metrics with W&B

Create paper figures and LaTeX comparison tables from experiment data in JSON or CSV files. Save reproducible plotting scripts, use consistent styling, and check rendered figures for readability, fair comparisons, and captions supported by the data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plotting training curves
• Comparing methods and ablation results
• Combining results across datasets into multiple panels

Review mathematical proofs in LaTeX for logical gaps, missing assumptions, and unjustified steps. Attempt counterexamples, develop explicit repairs, and repeat the review, producing an audit report that distinguishes completed fixes from assumptions and unresolved proof obligations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking theorem assumptions and logical dependencies
• Finding counterexamples to key lemmas
• Repairing missing derivations in LaTeX proofs

Build a section-by-section paper outline from experiment results and review findings. Map claims to evidence, allocate pages for the target venue, and plan figures and citations in PAPER_PLAN.md before drafting the paper.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan a paper before writing the first draft
• Connect research claims to experimental evidence
• Fit sections within a venue’s page limit

Build a PDF from a LaTeX paper, diagnose compilation errors, and fix common problems with citations, references, and figures. Check page limits, anonymity, and embedded fonts, then report remaining warnings before submission.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a PDF from a LaTeX manuscript
• Fix compilation and citation errors
• Check a manuscript against a submission page limit

Turn requirements into Mermaid diagrams, including process flows, system structures, and timelines. Save editable diagram code, a Markdown version, and a PNG preview, then check syntax, arrow directions, labels, and readability.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping a business process
• Illustrating API message sequences
• Diagramming database relationships

Create model architecture diagrams and method illustrations for academic papers using Gemini. Codex plans the figure and reviews generated images for correct connections, content, layout, and readability, guiding repeated revisions toward a clearer final figure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Illustrate a model architecture for a paper
• Show a method's processing steps and data flow
• Create a conceptual comparison diagram

Turn a paper outline and research narrative into a section-by-section LaTeX draft. Incorporate figures and verified bibliography entries, adapt formatting to the target venue, and review clarity, evidence alignment, and consistency across sections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a LaTeX paper from an existing outline
• Prepare formatting and citations for a target venue
• Review consistency between claims, evidence, and proofs

Apply staged skill improvements selected by the user after a fresh review of the actual changes. It backs up target files, applies passing patches, and records review evidence and change history for later inspection or reversal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Apply selected patches after a meta-optimize run
• Review staged changes immediately before applying them
• Keep backups for reverting skill changes

Manage mathematical proof projects across Codex runs, keeping sources, attempts, and unresolved steps organized. Prepare manual GPT Pro handoffs for difficult steps, then check returned arguments and edit the proof for clarity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continue a proof from a previous run
• Prepare a manual GPT Pro handoff for a difficult lemma
• Track proof sources and unresolved steps

Monitor machine learning training through WandB or training logs. Check for invalid numbers, worsening metrics, and stalled improvement, then report whether to continue, wait, or stop, preserving evidence and notes when stopping a run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitoring loss and evaluation metrics during training
• Investigating invalid numbers or diverging training
• Assessing whether stalled training should continue

Evaluate whether completed experiments support a research claim using a separate Codex reviewer. Identify unsupported conclusions and missing evidence, then determine whether to revise the claim, run additional experiments, or move toward paper writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check research claims before drafting a paper
• Plan additional experiments for incomplete evidence
• Reconsider an approach after unsupported results

Reviews research ideas, papers, and experimental results through repeated critical discussion. Identifies unsupported claims, missing experiments, and weaknesses in the paper’s story, then records agreed conclusions, evidence requirements, and prioritized improvements in a review document.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing research claims before submission
• Planning the minimum additional experiments
• Matching possible results to defensible claims

Check a paper’s numbers, comparisons, and evaluation scope against raw experiment files. A fresh reviewer receives only source evidence and paper files, then reports discrepancies in rounding, aggregation, settings, and reported improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify reported numbers before paper submission
• Check averages and counts across experiment runs
• Recalculate claimed percentage improvements

Polish existing academic PPTX or Beamer slides through page-by-page Codex review against a reference PDF. Adjust typography, spacing, colors, and text overflow while preserving content, keeping the original deck, and recording each change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improve slide readability before an academic presentation
• Match PPTX visual balance to a Beamer reference
• Fix text overflow and layout drift across slides

Measure scripts, running processes, or whole systems to find performance bottlenecks. Select suitable tools, add measurement code when needed, and report CPU, GPU, memory, and communication findings with prioritized recommendations and a record of file changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding slow functions in a Python script
• Investigating CPU and GPU memory usage
• Measuring communication overhead across multiple GPUs

Rent and manage vast.ai GPUs based on the training task rather than a chosen hardware model. The skill estimates requirements, compares offers by total expected cost, prepares the selected instance, and retrieves results before destroying it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a cloud GPU for a training task
• Comparing rental offers by estimated total cost
• Preparing a rented GPU environment for experiments

Turn a broad robotics research direction into ranked ideas with concrete benchmarks and simulation plans. The workflow combines literature review, novelty checks, and external critique while accounting for hardware access, safety, evaluation metrics, and failure cases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore research topics in manipulation or navigation
• Plan simulation studies before using physical robots
• Check novelty and feasibility of robotics ideas

Create pixel art illustrations as SVG files, a scalable image format, for READMEs, documentation, and slides. Build character portraits, conversations, or group scenes, then refine colors, speech bubbles, arrows, and spacing to fit the requested layout.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a pixel art hero image for a README
• Illustrate a conversation with characters and speech bubbles
• Make a character illustration in project colors

Develop patent application drafts from an invention description, covering prior art searches, claims that define protection scope, specifications, and examiner-style review. Compile documents for China, the United States, or Europe, with human checkpoints throughout.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning an invention description into application drafts
• Assessing prior art before drafting claims
• Preparing patent drafts for CN, US, or EP