472 个 · 按相关度排序
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
中文简介正在准备中。当前显示英语简介。
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.
中文简介正在准备中。当前显示英语简介。
Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.
中文简介正在准备中。当前显示英语简介。
Integrate Flash Attention into transformer models to reduce processing time and GPU memory use for long sequences. Covers PyTorch integration, advanced attention options, and benchmarks that compare speed, memory use, and output accuracy.
中文简介正在准备中。当前显示英语简介。
Analyze SaaS sales opportunities, revenue forecast errors, and sales and marketing efficiency. Generates reports on stalled deals, pipeline risks, prediction bias, and customer acquisition economics for weekly sales reviews and quarterly business assessments.
中文简介正在准备中。当前显示英语简介。
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
中文简介正在准备中。当前显示英语简介。
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
中文简介正在准备中。当前显示英语简介。
Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.
中文简介正在准备中。当前显示英语简介。
Design and improve prompts for language models, then test their accuracy and consistency. Create reusable templates, JSON output schemas that define response structure, evaluation criteria, and test cases while considering token use and model differences.
中文简介正在准备中。当前显示英语简介。
Independently review release note drafts against scanned change data. Check factual accuracy, missing items, tone, links, and clear coverage of breaking changes and security updates, then return a verdict with recommended revisions.
中文简介正在准备中。当前显示英语简介。
Review legal essays using IRAC: issue, rule, application, and conclusion. Get feedback on missed issues, rule accuracy, reasoning, and organization, plus recurring patterns across practice sessions, without rewritten essays or model answers.
中文简介正在准备中。当前显示英语简介。
NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local NIM containers for confidential or proprietary sequences. Run a complete protein structure prediction pipeline using NVIDIA BioNeMo NIMs: search for MSA alignments with MSA-Search (ColabFold), then predict the structure with OpenFold3 using the retrieved alignments. Use this skill whenever the user wants to predict a protein structure with maximum accuracy using MSA context, run the full AlphaFold3-style pipeline, generate MSA-informed structure predictions, or improve structure prediction accuracy by providing evolutionary information. Triggers on: MSA structure prediction pipeline, structure prediction pipeline, MSA-informed prediction, OpenFold3, ColabFold MSA, AlphaFold3 pipeline, protein structure, homology search, a3m alignment, UniRef30, NIM microservice. This pipeline chains MSA-Search and OpenFold3.
中文简介正在准备中。当前显示原文说明。
Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool. Use when Claude needs to assess the quality, risk of bias, or applicability of diagnostic accuracy studies (e.g., "Assess this paper using QUADAS-2").
中文简介正在准备中。当前显示原文说明。
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
中文简介正在准备中。当前显示原文说明。
Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.
中文简介正在准备中。当前显示原文说明。
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
中文简介正在准备中。当前显示原文说明。
No Inference / Source-Locked Verification. Forces Claude to answer ONLY from user-provided materials and/or online sources actually accessed — no inference, no assumptions, no gap-filling. Every factual, legal, numerical, or procedural claim must be anchored to a cited source. Use whenever Claude reviews documents, summarises evidence, checks accuracy, drafts submissions, creates timelines, extracts facts, checks citations, analyses rules, prepares legal arguments, compares documents, verifies claims, produces chronologies, works from uploaded materials, performs legal research, checks case status, or does anything where evidential fidelity matters. Also trigger on: 'source-locked', 'no inference', 'only from the materials', 'don't assume', 'stick to the evidence', 'verify this', 'check this is right', 'work from the documents'. Overrides Claude's default tendency to fill gaps. If evidential accuracy matters, use this skill.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".
中文简介正在准备中。当前显示原文说明。
Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage. Use when deals get stuck or forecast accuracy is poor.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "research", "fact-check", "check the history", "is this accurate", "research notes", "sources", "historical accuracy", "technical accuracy", "how would this really work", "verify a detail", "interview an expert", "plan a site visit", "expert review", or needs to investigate and record the real-world facts a story relies on and the chapters that use them.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Cognitive Scientist. Use when a task calls for Cognitive Scientist judgment. Reasons from Marr's levels of analysis, latent processes behind RT and accuracy, and strong inference through PsychoPy paradigms, signal-detection d-prime/criterion, sequential-sampling and ACT-R models, and crossed mixed-effects designs while treating speed-accuracy tradeoffs, criterion shifts, item confounds, and underpowered WEIRD samples as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data. Use when calling variants with DeepVariant deep learning caller or when highest germline calling accuracy is required.
中文简介正在准备中。当前显示原文说明。
Polish genome assemblies to reduce errors using short reads (Pilon), long reads (Racon), or ONT-specific tools (medaka). Essential for improving long-read assembly accuracy. Use when improving assembly accuracy with polishing tools.
中文简介正在准备中。当前显示原文说明。
Daily triage accuracy calibration — use during scheduled calibration runs to verify triage classification accuracy against few-shot examples and adjust confidence thresholds
中文简介正在准备中。当前显示原文说明。