Results for “code models”

Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the IEDB tools, and EL-mode MHC presentation. Encodes the load-bearing asymmetry that T-cell epitope prediction is mature (it reduces to MHC presentation, AUC>0.9) while B-cell prediction is unreliable (linear predictors ~AUC 0.6 because ~90% of real epitopes are conformational) — so structure-based DiscoTope-3.0 on AlphaFold models is the only defensible B-cell path, propensity scales are obsolete, and NetChop is largely redundant on EL-trained models. Use when mapping epitopes or selecting vaccine antigens. MHC binding lives in mhc-binding-prediction.

The English summary is being prepared. Showing the original description.

Detect positive (diversifying / episodic / pervasive) selection using codon dN/dS frameworks. Implements PAML codeml site models (M0/M1a/M2a/M7/M8/M8a), branch models, branch-site model A (Zhang 2005), and HyPhy methods (BUSTED, BUSTED-S, BUSTED-MH, BUSTED-PH, MEME, FEL, FUBAR, aBSREL, SLAC, RELAX, GARD, FUBAR-MH). Includes McDonald-Kreitman framework (asymptotic alpha, impMKT, polyDFE, DFE-alpha, GRAPES) for within-species + divergence inference, RERconverge for trait-correlated rate shifts, CSUBST for convergent substitution, and PhyloAcc for accelerated noncoding evolution. Use when testing adaptive evolution at codons, branches, or full gene; running GARD recombination pre-screen; controlling alignment-error and gBGC false positives; reconciling PAML vs HyPhy results; or performing genome-scale selection scans.

The English summary is being prepared. Showing the original description.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

The English summary is being prepared. Showing the original description.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

The English summary is being prepared. Showing the original description.

Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the IEDB tools, and EL-mode MHC presentation. Encodes the load-bearing asymmetry that T-cell epitope prediction is mature (it reduces to MHC presentation, AUC>0.9) while B-cell prediction is unreliable (linear predictors ~AUC 0.6 because ~90% of real epitopes are conformational) — so structure-based DiscoTope-3.0 on AlphaFold models is the only defensible B-cell path, propensity scales are obsolete, and NetChop is largely redundant on EL-trained models. Use when mapping epitopes or selecting vaccine antigens. MHC binding lives in mhc-binding-prediction.

The English summary is being prepared. Showing the original description.

Detect positive (diversifying / episodic / pervasive) selection using codon dN/dS frameworks. Implements PAML codeml site models (M0/M1a/M2a/M7/M8/M8a), branch models, branch-site model A (Zhang 2005), and HyPhy methods (BUSTED, BUSTED-S, BUSTED-MH, BUSTED-PH, MEME, FEL, FUBAR, aBSREL, SLAC, RELAX, GARD, FUBAR-MH). Includes McDonald-Kreitman framework (asymptotic alpha, impMKT, polyDFE, DFE-alpha, GRAPES) for within-species + divergence inference, RERconverge for trait-correlated rate shifts, CSUBST for convergent substitution, and PhyloAcc for accelerated noncoding evolution. Use when testing adaptive evolution at codons, branches, or full gene; running GARD recombination pre-screen; controlling alignment-error and gBGC false positives; reconciling PAML vs HyPhy results; or performing genome-scale selection scans.

The English summary is being prepared. Showing the original description.

Design and review Prisma database code for TypeScript backends. Use examples for schemas, queries, transactions, pagination, migrations, and connection management to identify common pitfalls in bulk operations and serverless deployments.

• Designing database models and relationships with Prisma
• Reviewing queries and pagination
• Investigating transaction and bulk update problems

Build and review Laravel web applications and APIs with clear separation of responsibilities. Covers Eloquent database models, input validation, consistent API responses, background jobs, events, and caching, helping organize application logic and data access.

• Separating controller code into services and actions
• Reviewing Eloquent relationships and unnecessary database queries
• Standardizing API responses, pagination, and input validation

Add an external API integration that follows the project's existing structure. Use current connectors as models for configuration, authentication, error handling, registration, and tests, so the new integration fits the surrounding code.

• Adding a Jira connector to an existing project
• Building a Slack provider using current project conventions
• Completing integration registration and tests

Create financial Excel workbooks with Python, using formulas, color-coded inputs, source comments, and consistency checks. Build models that reviewers can trace and users can adjust by changing assumptions.

• Build a financial model with traceable inputs
• Compare valuations under different assumptions
• Prepare a workbook for another person's review

Compare Claude, GPT, and Gemini on the same skill or prompt. Get a table of response times, token usage, and costs, with optional AI scoring to help choose a model for the task.

• Choosing a model for a specific skill
• Comparing response times and costs
• Comparing output quality with optional AI scoring

Assess tasks before execution to identify transformations eligible to skip LLM calls. Report the eligible share, recommended models for remaining tasks, and estimated upper costs, then save the routing results for later cost reports.

• Assess similar tasks before a batch run
• Review LLM spending on simple code transformations
• Check the share eligible for Agent Booster

Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.

• Serving an AI model through a web API
• Running model training or fine-tuning on cloud GPUs
• Processing independent batch inputs in parallel

Implement and debug astronomical data analysis with Astropy in Python. Work with physical units, celestial coordinates, observation files, tables, precise time conversions, and cosmological models to prepare data and calculate astronomical quantities.

• Convert celestial coordinates and physical units
• Read and edit FITS observation files
• Match objects across astronomical catalogs

Implement Python services for Azure Cosmos DB NoSQL with guidance for authentication, data models, database operations, and tests. Separate business logic from storage access, validate data access permissions, and use reusable templates for consistent implementation.

• Adding Cosmos DB storage to a FastAPI application
• Separating database access from business logic
• Configuring Azure and local emulator authentication

Convert human-written CLAUDE.md instructions into a structured label format for AI agents. Use it to review lengthy rules, reduce instruction overhead, and prepare prompts for migration between AI tools while preserving the intended rules.

• Restructuring a lengthy CLAUDE.md
• Reviewing instruction token usage
• Preparing rules for migration between AI tools

Understand and extend GitNexus taint analysis, which tracks data from input sources to potentially dangerous operations. Use its implementation guidance to investigate missed or incorrect findings, add detection models, and validate analysis changes.

• Investigating missed or incorrect data-flow findings
• Adding input sources, dangerous operations, or sanitizers
• Reviewing analysis that follows data across functions

Guide code that consumes PSL parser output by choosing the right syntax tree layer. Use typed AST classes for structure and navigation helpers for positions, while avoiding text parsing shortcuts and direct access to internal storage.

• Read models and fields from PSL parser output
• Find syntax elements at a language server cursor position
• Review tree access in interpreters and formatters

Build and review ViewModels, objects that manage screen state and actions, with CommunityToolkit.Mvvm. Use attributes to generate change notifications and commands, add input validation, and handle asynchronous operations, cancellation, and command availability.

• Add properties that notify the screen when values change
• Create asynchronous commands with cancellation
• Validate registration forms and settings

Rewrite lengthy prompts, tool descriptions, and agent instructions into compact text while preserving requirements, exceptions, and exact values. The process records removed content and compares token counts, the units models use to measure text length.

• Shortening system prompts
• Compressing tool documentation and skill bodies
• Reducing text length for model input

Develop Azure Functions with guidance for .NET, Python, and Node.js. Covers asynchronous processing, Durable Functions for coordinating tasks, startup delay optimization, and production concerns such as timeouts, HTTP client reuse, and monitoring configuration.

• Choose an execution model for a new .NET function
• Coordinate asynchronous tasks with Durable Functions
• Review startup delays and timeout settings

Apply consistent architecture and coding conventions when building cross-platform apps with Avalonia UI and Zafiro. The skill guides separation of interface and logic, reactive data handling, explicit error results, and reuse of existing helpers.

• Standardizing Avalonia UI and Zafiro implementation
• Keeping ViewModels independent of Avalonia
• Reviewing error handling with Result types

Generate or modify images through the Luma AI API using Photon models. The skill gathers image descriptions and options, supports reference images for visual guidance, and uses a bundled Python script to wait for completion and download results.

• Creating a landscape image for a website
• Generating square product images
• Guiding image style or composition with a reference

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback