Results for “selective-recomputation”

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Builds Retrieval-Augmented Generation pipelines with vector stores, chunking strategies, and reranking

Derive selection thresholds from market data instead of hardcoding. Trigger when: (1) reviewing hardcoded parameters, (2) volume/price thresholds seem arbitrary, (3) selection returns too many/few candidates.

Optimizes hot-path scalar loops in .NET 8+ with cross-platform Vector128/Vector256/Vector512 SIMD intrinsics, or replaces manual math loops with single TensorPrimitives API calls.

Guides scaling Qdrant vector search with time-based data rotation using shard rotation, collection rotation, or filter-and-delete strategies.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Matryoshka Representation Learning

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Identify command-and-control beaconing patterns in network traffic by applying statistical frequency analysis, jitter calculation, and coefficient of variation scoring to detect periodic callbacks from compromised endpoints.

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

Cross-validation only estimates generalization if the split mimics the gap between

Scaling Vision with Sparse Mixture of Experts

Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.

Reads and preprocesses 5-minute stock candlestick CSV data, then clusters the time series using tslearn's TimeSeriesKMeans, including data cleaning, percentage change calculation, model training, saving, and representative sample extraction.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

Partial Indexes

Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/. Use when a query is fuzzy or cross-file ("how did we fix X", "what did we decide about Y", "which skill handles Z"). Complements grep (exact) and Serena (code symbols). If the user asks a recall question that doesn't map to a specific known file, reach here first.

This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities. Use this skill for probabilistic modeling, batch correction, dimensionality reduction, differential expression, cell type annotation, multimodal integration, and spatial analysis tasks.

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

GPU-accelerated correlation matrix computation with persistent SQLite caching to eliminate bottleneck at correlation calculation during symbol selection

Layer 4 of the keyword research pipeline. Spawns a "skeptical SEO" adversarial sub-agent to argue against every survivor of Layers 1-3. Catches mechanical-classifier blind spots — wrong SERP intent, hidden link-graph gauntlets, AIO trajectory shifts, vanity-rank metrics. Same pattern as quality-check's adversarial draft read, applied to keyword selection.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Build a scalable outbound B2B sales machine with specialized SDR, AE, and CSM roles, using Cold Calling 2.0, referral emails, ANUM qualification, and pipeline math to generate predictable revenue.

Data-Centric Artificial Intelligence: A Survey