1.2K skills · sorted by relevance
Apply simple code changes across files without calling an LLM, using agent-booster's local transformation engine. The skill checks a confidence score before saving results and records outcomes for cost tracking and future routing decisions.
Build text tokenizers that split multilingual text into small units for AI models. Learn how to train SentencePiece on raw text, configure BPE or Unigram splitting methods, and convert text to token IDs and back.
Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.
Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.
Build text, image, and audio features in JavaScript using machine learning models that run in browsers or server runtimes. Covers model selection, execution settings, caching, and memory cleanup without requiring a Python server.
Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.
Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.
Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.
Learn Apache Beam's core concepts through Java and Python examples. Understand distributed datasets, processing steps, pipeline execution, and time windows, with guidance on aggregation, late data, error handling, and sharing processing steps across languages.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.
Spillover compensation and data transformation for flow cytometry. Covers compensation matrix calculation, application, and biexponential/arcsinh transforms. Use when correcting spectral overlap between fluorophores or transforming data for analysis.
The English summary is being prepared. Showing the original description.
Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI. Use when upgrading language versions, migrating AWS SDKs, migrating frameworks (Angular, Vue.js, Spring Boot, React), upgrading libraries, optimizing performance, migrating x86 to Graviton, analyzing codebases / generating documentation, or defining custom transformations with natural language. Runs locally on a few repositories or at scale across hundreds via AWS Batch/Fargate.
The English summary is being prepared. Showing the original description.
Migrate, modernize, and upgrade codebases to AWS. Run analysis on repos for tech debt, security vulnerabilities, and modernization opportunities. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. Use when the user says "migrate .NET to AWS", "upgrade Java to 17/21", "modernize COBOL", "modernize mainframe", "move VMware to EC2", "convert SQL Server to Aurora", "upgrade Python version", "migrate AWS SDK", "transform this codebase", "analyze for issues", "find tech debt", "what tech debt", "security vulnerabilities", "CVEs", "what's wrong with my code", "assess my repos", "where do I start", "find what's outdated", "analyze my repos", "AWS Transform - continuous modernization", "continuous modernization" or "continuous-modernization". Don't use for infrastructure provisioning, CI/CD pipelines, or general coding tasks.
The English summary is being prepared. Showing the original description.
Generates code that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR/RLAIF, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.
The English summary is being prepared. Showing the original description.
Writes, improves, or rewrites Seedance 2.0 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch. Use whenever a real clip is the starting point and they want to: add a VFX element (set a head or hair on fire, transform a hand, make a limb invisible), swap the environment around a preserved subject (desert, clouds, lava, a neon city), drop a giant photoreal creature behind or onto a subject/landmark, relight or regrade so subject and added elements read as one shot, sync a crash-zoom or push-in to a spoken line or timecode, or generate a matching transformed start frame to animate from. Also use when they paste such a prompt and ask to change its lighting, timing, creature, or runtime, or say 'make a Seedance prompt for this video' with a clip attached. This is the video-to-video specialization; for a brand-new scene from image references with no source clip to preserve, higgsfield-seedance applies instead.
The English summary is being prepared. Showing the original description.
Generate before-and-after transformation video prompts for Seedance 2.0 on Higgsfield. Use for transformation reveals, glow-ups, makeovers, renovation reveals, fitness transformations, design before-after, business growth visuals, or any content showing dramatic change. Triggers on before after, transformation, reveal, glow up, makeover, renovation, redesign, progress, results.
The English summary is being prepared. Showing the original description.
Spillover compensation and data transformation for flow cytometry. Covers compensation matrix calculation, application, and biexponential/arcsinh transforms. Use when correcting spectral overlap between fluorophores or transforming data for analysis.
The English summary is being prepared. Showing the original description.
Execute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention head. Demonstrates that transformer attention + FF layers can implement a working computer. Use when user mentions "llm-as-computer", "lac", "stack machine", "compiled transformer", "percepta", "parabolic attention", "execute program", or asks to run/trace programs on the transformer executor.
The English summary is being prepared. Showing the original description.
Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN, Graphormer) through a common transformer API with caching and parallelism. Use this skill to convert SMILES into model-ready feature matrices for QSAR, virtual screening, and molecular ML, and to choose between featurizer families. Also trigger on molfeat, MoleculeTransformer, FPVecTransformer, PretrainedHFTransformer, molfeat model store, or featurizer selection.
The English summary is being prepared. Showing the original description.
Four-stage alchemical code transmutation — nigredo (decomposition), albedo (purification), citrinitas (illumination), rubedo (synthesis) — with meditate and heal checkpoints between stages. Transforms tangled or legacy code into optimized, well-structured output through systematic material analysis. Use when transforming legacy code into modern equivalents, refactoring deeply tangled modules where incremental fixes keep failing, converting a codebase between paradigms, or when simpler refactoring approaches have stalled and a full-cycle transformation is needed.
The English summary is being prepared. Showing the original description.
Fornece orientação para pesquisa de interpretabilidade mecanística usando TransformerLens para inspecionar e manipular internals de transformers via HookPoints e caching de ativações. Use ao fazer engenharia reversa de algoritmos de modelos, estudar padrões de atenção ou realizar experimentos de activation patching.
The English summary is being prepared. Showing the original description.
Create an Estuary derivation for stateless filtering, field selection, and per-document field transformation. Use for WHERE clauses, projecting fields, computing new fields from existing ones, or data cleansing. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this (renaming alone is usually a projection, not a derivation). Use when user says "filter-transform derivation", "derivation to filter by status", "transformation with WHERE clause", "derive computed fields", "cleanse data with a derivation", or "stateless derivation".
The English summary is being prepared. Showing the original description.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.
Create an HTML presentation outlining digital transformation for an established insurer. Organize the diagnosis, sequence of initiatives, and operating rhythm for executive decisions, using a warm paper palette and a consistent, restrained editorial design.