QingFeng Li

Build reinforcement learning experiments, where agents learn actions from rewards, using Stable Baselines3. Get guidance on choosing algorithms, creating Gymnasium environments, training and evaluating agents, monitoring progress, and saving models for later use.

• Choosing an algorithm for a reinforcement learning experiment
• Creating and checking a custom Gymnasium environment
• Monitoring training and saving checkpoints

Get guidance on fine-tuning language models with Unsloth, including LoRA and QLoRA methods for training with fewer resources. The skill points to documentation for understanding APIs, implementing training code, debugging problems, and exploring speed and memory optimizations.

• Exploring faster training with lower memory use
• Learning about LoRA and QLoRA fine-tuning
• Checking Unsloth features and APIs

Check code and agent outputs, track reliability scores, and roll back changes that fail a chosen threshold. Includes quality reports, live monitoring, and integration with automated build and deployment workflows.

• Checking code produced by AI agents
• Rolling back changes that fail verification
• Tracking quality trends over time

Create, edit, analyze, and format Excel, CSV, and TSV files using Python. Preserves existing spreadsheet styles and formulas, checks references, and supports summaries, charts, and readable layouts for new workbooks.

• Editing Excel files while preserving formulas and formatting
• Filtering and summarizing CSV or TSV data
• Creating workbooks with formulas

Turn a feature specification into a technical implementation plan. Organizes technology choices, research decisions, data models, and interface agreements into project files, while checking that the design follows the project's documented principles.

• Create a technical plan from a feature specification
• Resolve open questions about technology choices
• Document data models and external interfaces

Review existing charts for clear communication, appropriate chart types, readable labels, scales, and color choices. Get concrete suggestions for simplifying layouts, improving accessibility, and making the visualization suit its intended audience.

• Reviewing whether an existing chart communicates clearly
• Fixing chart labels, legends, and scales
• Checking colors and accessibility

Analyze research data with suitable statistical tests, regression, correlation, or Bayesian methods. Check assumptions, estimate effect sizes and uncertainty, plan sample sizes, and prepare figures, tables, and reports following APA academic reporting conventions.

• Choosing statistical tests for research data
• Checking analysis assumptions and alternative methods
• Estimating sample sizes before collecting data

Create or update a project's governing development principles, covering code quality, testing, and architectural constraints. Maintain the constitution document, record version changes, and align related planning, specification, and task templates with the revised rules.

• Establishing development principles at project kickoff
• Documenting quality and testing standards
• Updating principles and tracking version changes

Turn text into audio files for narration, product demos, phone prompts, or accessibility reads using the OpenAI Audio API. Choose built-in voices and delivery directions, then generate a single clip or a batch of files.

• Create narration from an explainer script
• Generate a voiceover for a product demo
• Produce a batch of phone menu prompts

Build PyTorch machine learning workflows for molecules, proteins, and biomedical relationships. Get guidance on datasets, model selection, training, and evaluation for property prediction, protein modeling, molecule generation, and planning synthesis routes from target molecules.

• Predicting molecular solubility and toxicity
• Predicting protein function from sequences or structures
• Exploring new drug uses through biomedical relationships

Guides single-cell RNA-seq analysis, which examines gene activity in individual cells. Covers data loading, quality checks, clustering, marker genes, cell type annotation, and plots, with AnnData handling and scVI/scANVI workflow planning.

• Checking and filtering single-cell RNA-seq data
• Visualizing cell groups with UMAP or t-SNE
• Finding marker genes and annotating cell types

Manage repeated work on a task in Codex with iteration limits, completion conditions, and saved progress. Advance iterations manually with the default engine, or use the optional open-ralph-wiggum command-line tool for automatic iteration.

• Starting repeated work with an iteration limit
• Advancing to the next iteration manually
• Checking the current loop state

Create statistical charts in Python with seaborn to explore distributions, compare groups, and examine relationships between variables. Build scatter plots, heatmaps, regression charts, and multi-panel figures, then adjust styling and export figures for reports or publications.

• Exploring data distributions and outliers
• Comparing measurements across groups
• Visualizing correlations with a heatmap

Build Python simulations with SimPy to study queues and shared resources such as machines, staff, or servers. Model events over time, measure waiting times and utilization, and compare capacity choices.

• Compare service waiting times under different staffing levels
• Measure machine utilization on a production line
• Model inventory flows between producers and consumers

Review code for security risks in authentication, APIs, input handling, and data access. Identify issues such as exposed secrets, injection, and missing access checks, then report severity, file evidence, proposed fixes, and verification steps.

• Reviewing authentication and access controls
• Checking for exposed secrets and unsafe logs
• Auditing input handling and file uploads

Review Python, JavaScript/TypeScript, and Go code for security issues using guidance for the project's languages and frameworks. Get prioritized findings, suggested improvements, or help writing new code with safer defaults.

• Review an existing application's security
• Create a report organized by severity
• Write new code with safer defaults

Inspect production errors in Sentry through read-only API queries. Summarize unresolved issues, occurrence counts, and recent events, then examine individual issue and event details to understand what has been happening.

• Reviewing unresolved production issues from the last 24 hours
• Checking occurrence counts and when errors were last seen
• Inspecting events linked to a specific issue

Create slides for research talks, conferences, and thesis defenses. Plan the narrative and timing, incorporate figures and citations, and produce PDF slides or editable PowerPoint presentations with consistent visual design.

• Prepare a conference talk around key research findings
• Build a thesis defense presentation
• Adapt research figures for a seminar

Prepare code review requests with an implementation summary, requirements, and the exact Git commit range. Assemble reviewer instructions and organize follow-up actions by severity after a feature is completed or before changes are merged.

• Requesting a review after completing a feature
• Preparing review materials before merging changes
• Getting a fresh perspective on a difficult bug

Design and improve prompts and structured responses for AI applications. The skill also guides evaluation, retrieval augmented generation, which uses retrieved material to inform answers, and agent architecture, with references and scripts for production workflows.

• Improving prompts and response formats
• Evaluating answers based on retrieved documents
• Designing AI agent systems

Process mass spectrometry data in Python with PyOpenMS. Read common file formats, smooth and normalize signals, detect peaks, align samples, and process peptide identification results for protein and metabolite quantification workflows.

• Reading mzML files and inspecting spectra
• Smoothing and normalizing mass spectrometry signals
• Aligning and comparing metabolite peaks across samples

Draft and revise scientific manuscript prose from research notes and results. Organize sections, write abstracts and figure captions, integrate citations, and refine terminology and clarity while following study reporting guidelines and journal requirements.

• Turning research notes into manuscript sections
• Writing an abstract within journal word limits
• Refining captions and integrating citations

Evaluate scientific papers and claims by examining study design, statistics, bias, and the strength of supporting evidence. Helps distinguish supported conclusions from overstatements and provides constructive recommendations for improving research methods and interpretation.

• Assessing the evidence behind a paper's conclusions
• Finding bias and statistical interpretation errors
• Comparing studies with conflicting findings

Analyze git history to map contributors to security-sensitive files, identify reliance on too few people, and find stale areas. Export CSV and JSON results for ownership reviews, graph exploration, and comparison with CODEOWNERS.

• Find stale security-sensitive code with few maintainers
• Check reliance on individual authentication or cryptography maintainers
• Compare CODEOWNERS with actual contribution history