QingFeng Li

Organize complex tasks using three Markdown files for plans, findings, and progress. The skill keeps decisions, discoveries, errors, and test results in project files that an agent can consult when making decisions or resuming work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning tasks with multiple stages
• Recording findings during research
• Resuming work after a break

Implement filtering, aggregation, joins, and file processing with Polars for tabular data that fits in memory. Use lazy evaluation, which optimizes operations before running them, and parallel execution to improve pipelines and migrate pandas code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Migrate slow pandas processing to Polars
• Filter and aggregate CSV or Parquet data
• Join multiple tables and reshape results

Analyze Neuropixels neural recordings from raw data through quality review. Supports preprocessing, motion correction, spike sorting to separate signals by neuron, quality metrics, visual inspection, reports, and exports for further review or data sharing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preprocess recordings and correct probe drift
• Separate neural signals with Kilosort4
• Select units using Allen or IBL quality criteria

Design and implement repeatable workflows that clean, encode, transform, and validate raw data for machine learning. Get a preprocessing plan or implementation outline, with clear steps and guidance on where further checks are needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing raw data for machine learning
• Automating recurring data cleaning
• Planning data extraction, transformation, and loading

Create interactive charts in Python for exploring scientific, statistical, geographic, and financial data. Choose quick plotting or detailed customization, add hover details and zoom controls, and export results as interactive HTML or static images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring measurement relationships with scatter plots
• Comparing distributions across groups
• Inspecting time series with a range slider

Analyze relationships between people, objects, or places using Python networks. Build connection diagrams, find shortest paths, identify important nodes and closely connected groups, visualize network structure, and save the resulting data and measurements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Visualize social or citation networks
• Find shortest routes through a network
• Identify important nodes and connected groups

Turn existing logs, measurements, or user reports into a prioritized performance improvement plan. It ranks frontend, backend, database, and infrastructure changes by expected impact and effort, and suggests validation steps for checking whether improvements worked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritizing website loading improvements
• Planning database query optimization
• Organizing API response time improvements

Screen compound collections for drug discovery using established drug-likeness rules, structural warnings, and molecular complexity measures. Detect relevant chemical groups, apply property limits, and generate filtering results to support compound selection and prioritization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening compound collections for drug-like candidates
• Detecting potentially problematic structures
• Prioritizing compounds during lead optimization

Search current web information and recent scientific literature with Perplexity through OpenRouter and LiteLLM. Get answers with source citations, choose models for different research needs, and save results as JSON for further use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find recent scientific papers
• Verify claims with cited sources
• Compare current technologies and approaches

Search biomedical literature in PubMed using combined conditions and MeSH, its standardized subject terms. Build search strategies, retrieve abstracts and citation records through the REST API, and export results for reference management or analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a literature search for a systematic review
• Filter papers by author, date, or study type
• Retrieve abstracts and citation records in batches

Search NIH Metabolomics Workbench for metabolite structures, study details, and experimental data. Standardize metabolite names with RefMet, find candidate compounds from mass spectrometry measurements, and filter studies by disease, sample source, or analytical method.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding studies that measure a specific metabolite
• Standardizing metabolite names with RefMet
• Finding compound candidates from mass spectrometry measurements

Create research posters intended for PowerPoint using HTML and CSS templates. Arrange large visuals and concise text, preview the layout in a browser, and follow PDF export or PPTX creation steps with readability and overflow checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating research posters for PowerPoint
• Previewing and adjusting poster layouts in a browser
• Arranging large figures with concise research findings

Deploy web projects to Netlify with its command-line tool. The skill checks authentication and project settings, links or creates a site, and publishes a preview or production version with deployment URLs and log links.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publishing a web project on Netlify
• Sharing a preview URL before production
• Linking a project to an existing Netlify site

Work with crystal structures and materials calculations in Python. Convert structure files, examine symmetry and stability, analyze electronic properties, prepare calculation inputs, and retrieve computed materials data from Materials Project using pymatgen and its supporting tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert crystal structure files between CIF and POSCAR
• Analyze crystal symmetry and neighboring atoms
• Create phase diagrams and assess material stability

Measure indicator calculation speed with BenchmarkDotNet, a benchmarking tool for .NET. Compare batch, incremental, and streaming implementations, detect slowdowns against saved results, and evaluate changes intended to reduce processing time and memory allocations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing batch, incremental, and streaming performance
• Detecting performance regressions after code changes
• Adding benchmarks for a new indicator

Write structured reviews of scientific manuscripts and grant proposals. Assess methods, statistics, reproducibility, ethics, and reporting completeness, then organize strengths, major concerns, minor issues, and specific suggestions into constructive feedback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a journal manuscript review
• Reviewing a research grant proposal
• Checking methods and statistical reporting before revision

Reviews machine learning preprocessing, features, and data splits for data leakage: information unavailable when making a real prediction. Identifies risky statistics, future data, and validation setups, then suggests corrections using only appropriate training information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing normalization and missing value imputation
• Checking feature selection and target encoding
• Finding future information in time series features

Audit Node.js processes started by VCO, identify which are managed and still active, and report stale processes eligible for cleanup. Produce Markdown or JSON reports and simulate cleanup while keeping external and unknown processes outside the candidate set.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing accumulated Node.js processes after long VCO runs
• Recording VCO-launched processes through a wrapper
• Producing Markdown or JSON process ownership reports

Choose a mathematical approach for a problem you do not yet know how to model. Guided questions clarify change, uncertainty, optimization goals, and required precision, leading to a recommended framework, starting equations, tools, and related skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a mathematical approach for a real-world problem
• Deciding how to model discrete or continuous change
• Selecting methods for uncertainty or optimization

Keeps existing requests for OpenAI documentation guidance working by directing them to the local openai-docs skill. It reuses the canonical instructions, references, and scripts while preserving compatibility with older callers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping older skill requests working
• Reusing documentation references and scripts
• Maintaining continuity in skill catalogs

Design and automate machine learning workflows from data preparation through training, validation, deployment, and monitoring. Provides guidance and templates for reproducible experiments, quality checks, gradual model rollouts, and restoring a previous model when problems occur.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a new machine learning pipeline
• Creating reproducible training workflows
• Adding quality checks before model deployment

Find current official documentation for building with OpenAI products and APIs. Provides source-linked guidance on Codex, APIs, SDKs, and model capabilities or limits, using dedicated documentation tools before searching official OpenAI websites.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check how to use the Responses API
• Look up Codex features and usage
• Research app development with Apps SDK or Agents SDK

Perform arithmetic, algebra, calculus, matrix operations, number theory, and statistics with SymPy, a symbolic mathematics library. Return exact expressions, numerical values, and LaTeX notation for checking calculations or using results in other work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calculate exact fractions and roots
• Simplify expressions and solve equations
• Check derivatives, integrals, and limits

Process physiological recordings in Python, including heart, brain, breathing, and muscle signals. Supports signal cleaning, heart rate variability measurements, stimulus response analysis, and combined analysis of multiple signal types.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calculate heart rate variability from ECG recordings
• Analyze EEG power across frequency bands
• Compare skin conductance responses to stimuli