QingFeng Li

Review papers, research proposals, and literature reviews with the ScholarEval framework. Assess research questions, methods, analysis, writing, and references, then produce evidence-based feedback with prioritized improvements and optional scores for each relevant dimension.

中文简介正在准备中。当前显示英语简介。

• Review a paper before journal or conference submission
• Assess research questions and methodology
• Evaluate the coverage and synthesis of a literature review

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.

中文简介正在准备中。当前显示英语简介。

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

Build research slides from text sources using Slidev, Marp, Reveal.js, or Quarto. Keep source files manageable, reuse exported figures, and produce reproducible PDF presentations with a clear sequence and one conclusion per slide.

中文简介正在准备中。当前显示英语简介。

• Manage research slide versions as text
• Reuse original figures without screenshots
• Connect reports and slides through Quarto

Clarify an existing feature specification before implementation planning. The skill prioritizes consequential gaps, asks focused questions one at a time, updates the specification with accepted answers, and summarizes unresolved decisions and recommended next steps.

中文简介正在准备中。当前显示英语简介。

• Resolving unclear requirements before implementation planning
• Defining error behavior and measurable completion criteria
• Recording agreed answers directly in a specification

Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.

中文简介正在准备中。当前显示英语简介。

• Exploring features in a pretrained SAE
• Training an SAE for a selected model layer
• Investigating inactive features and reconstruction errors

Bridge `/speckit.*` commands to `/vibe` execution guidance in Codex. A PowerShell router preserves the familiar command model and leaves official spec-kit prompts unchanged, helping carry existing workflows into `/vibe-first` execution.

中文简介正在准备中。当前显示英语简介。

• Using existing `/speckit.*` commands with Codex
• Getting `/vibe` guidance for an implementation command
• Checking the router's command list

Find reusable Agent Skills by keyword, category, or tag through prompts.chat. Review descriptions and included files, retrieve a chosen skill, and install its instructions, reference documents, scripts, and configuration files for Claude.

中文简介正在准备中。当前显示英语简介。

• Finding a code review skill
• Searching for testing skills
• Retrieving all files for a specific skill

Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.

中文简介正在准备中。当前显示英语简介。

• Choose a lower-cost cloud for GPU training
• Run long training jobs with recovery after interruptions
• Configure distributed training across multiple machines

Analyze how long events take to occur, including records where observation ends before the event. Use Python to prepare data, fit and compare survival models, and evaluate predictions with measures suited to incomplete observations.

中文简介正在准备中。当前显示英语简介。

• Analyze time to events with incomplete observations
• Compare Cox models and Random Survival Forests
• Select features in datasets with many variables

Structure PyTorch training code with PyTorch Lightning, separating model logic, data preparation, and training settings. Use templates and configuration examples to add checkpoints, experiment logs, and distributed training that runs across multiple GPUs or TPUs.

中文简介正在准备中。当前显示英语简介。

• Restructuring PyTorch code into LightningModules
• Building reusable data preparation pipelines
• Configuring training across multiple GPUs or TPUs

Create focused checklists to review requirements before implementation. Using project specifications and plans, the skill turns gaps, vague wording, conflicting requirements, and missing scenarios into questions that help authors and reviewers assess specification quality.

中文简介正在准备中。当前显示英语简介。

• Finding missing requirements before implementation
• Reviewing vague language and acceptance criteria
• Assessing UX or API specification quality

Review specifications, plans, and tasks together before implementation. Identify missing task coverage, duplicate requirements, unclear wording, and conflicting decisions, then receive a prioritized report with recommendations without changing project files.

中文简介正在准备中。当前显示英语简介。

• Reviewing specifications and plans before implementation
• Finding requirements with no corresponding tasks
• Checking compliance with project principles

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.

中文简介正在准备中。当前显示英语简介。

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

Search scholarly literature in OpenAlex by topic, author, or institution. Explore citation counts and publication trends, find freely accessible papers, and export research records to CSV for further analysis.

中文简介正在准备中。当前显示英语简介。

• Finding papers on a research topic
• Reviewing an author's or institution's publications
• Tracking publication trends and citations

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.

中文简介正在准备中。当前显示英语简介。

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

Analyze bulk RNA-seq counts in Python to find genes whose expression differs between conditions. Prepare data, account for batch effects, adjust statistical results for multiple testing, and export tables with volcano or MA plots.

中文简介正在准备中。当前显示英语简介。

• Comparing gene expression between treatment and control
• Accounting for batch effects or age in expression analysis
• Moving R-based DESeq2 workflows to Python

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.

中文简介正在准备中。当前显示英语简介。

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

Work with DICOM, a standard medical imaging format, in Python. Read and edit scan metadata, extract image pixels, anonymize patient information, convert scans to common image formats, and process compressed files or image series.

中文简介正在准备中。当前显示英语简介。

• Extracting and editing DICOM metadata
• Anonymizing scans for research sharing
• Converting DICOM images to PNG or JPEG

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.

中文简介正在准备中。当前显示英语简介。

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

Build and train reinforcement learning agents, which learn actions through rewards. The skill guides custom environment creation, parallel simulation tuning, integration with existing environments, and policy development for image or sequential observations.

中文简介正在准备中。当前显示英语简介。

• Train agents in existing reinforcement learning environments
• Create custom simulation environments
• Tune parallel simulations for higher throughput

Use pymoo in Python to optimize competing goals such as cost and performance under constraints. Find and visualize trade-off solutions, compare algorithms, and select candidates according to preferred priorities.

中文简介正在准备中。当前显示英语简介。

• Comparing designs with competing cost and performance goals
• Finding solutions that satisfy constraints
• Comparing algorithms on standard benchmark problems

Analyze propositional formulas and arguments using truth tables, deduction rules, and branching proof trees. Classify formulas as always true, always false, or dependent on their inputs, and check whether an argument follows from its premises.

中文简介正在准备中。当前显示英语简介。

• Classifying formulas with truth tables
• Checking whether a formula can be true
• Verifying arguments with deduction rules

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.

中文简介正在准备中。当前显示英语简介。

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

Write and edit Prowler documentation using consistent language and formatting. The skill covers feature guides, tutorials, API references, and release notes, with rules for terminology, headings, inclusive wording, search visibility, and reusable MDX documentation components.

中文简介正在准备中。当前显示英语简介。

• Writing Prowler feature documentation
• Standardizing language in tutorials
• Editing API and SDK references