Results for “bat”

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Analyzes dependencies between stories, code modules, tickets, or specs to compute an optimal implementation order with parallel batches, cycle detection, and critical path analysis.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Optimize GSAP animations for smooth 60fps by preferring transforms, avoiding layout thrashing, using will-change, batching reads and writes, and following best practices for stagger, quickTo, and ScrollTrigger performance.

Generates images using multiple AI providers including OpenAI, Google, Azure, and others. Supports text-to-image, reference images, aspect ratios, and batch generation from prompt files.

Predict 3D binding poses of small molecule ligands to protein targets using diffusion-based molecular docking, supporting single complexes, batch processing, and virtual screening.

Rapidly classify malware samples against known family signatures using YARA rules, covering rule writing, scanning, and integration with analysis pipelines.

Add a batteries-included agent component to React/Next.js apps with runtime, streaming, human-in-the-loop approvals, and client-side tools.

Writes Apex that calls Field Service Lightning scheduling APIs to book, schedule, grade, or optimize service appointments programmatically, including transaction-splitting patterns to avoid callout-DML conflicts.

Audits Claude skills and commands for quality, offering Quick Scan for changed skills and Full Stocktake modes with sequential subagent batch evaluation.

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.

Power management and performance optimization for Zephyr RTOS. Covers system power states (Idle, Suspend, Off), device-level power management, residency hooks, and code/data relocation for speed efficiency. Trigger when optimizing battery life, reducing latency, or managing memory constraints.

Access microscopy images and metadata via the OMERO Python API: retrieve datasets, analyze pixels, manage ROIs and annotations, and batch-process for high-content screening workflows.

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

Scrape and crawl websites for AI with Firecrawl — scrape single URLs to clean Markdown/HTML, crawl entire sites with depth/path filters, extract structured data with LLM schema, use map to discover all URLs, and batch scrape multiple pages in parallel.

CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.

Comprehensive competitor analysis, competitive intelligence, and comparison page creation. Use when analyzing competitive landscape, creating competitor comparison pages (alternative pages, vs pages, competitor A vs B pages), performing market research, building SWOT analysis, creating feature matrices, pricing comparisons, competitor teardowns, battle cards, or positioning maps. Covers research workflows, SEO-optimized comparison content, data-grounded reports with citations, 7-layer analysis framework, review mining, and sales enablement. Triggers include competitor analysis, competitive analysis, competitor teardown, vs page, alternative page, competitor comparison, market research, competitive intelligence, SWOT analysis, battle card, competitor pricing, market landscape, feature comparison, positioning map.

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.

Use when the superpowers-evaluator returned REWORK on a batch, when fixing rework items from an evaluation report, or when receiving any code review feedback on superpowers output. Requires technical rigor and verification instead of performative agreement or blind implementation.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Manage scheduled cron job pipelines — review overnight runs, detect missed jobs (machine-sleep pattern), run catch-up batches with proper spacing, and integrate results into the morning briefing. Covers the overnight maintenance pipeline common on macOS machines that sleep at night.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Batch-converts UI design screenshots into Vue 3 Composition API components using Vant, Element Plus, or Ant Design Vue, with router wiring and shared component extraction.

Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in small batches, and produces structured reading notes — avoiding context window crashes and shallow comprehension.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Bluetooth Low Energy (BLE) integration for Zephyr RTOS. Covers GATT Services/Characteristics, GAP advertising, connection parameters, power optimization strategies, and the professional Send-When-Idle design pattern. Trigger when adding BLE connectivity, optimizing battery life for wireless devices, or implementing custom GATT profiles.