Results for “data parallel”

Download large datasets from NCBI efficiently using EPost, history server, batching, rate limiting, and retry logic. Use when bulk-fetching tens of thousands of sequences, pulling all results of a large ESearch, designing reproducible pipelines, comparing E-utilities to NCBI Datasets v2 CLI, or implementing checksum-validated downloads. Encodes WebEnv TTL (~8h), EPost 200-ID limit, retmax caps, parallelization design, and integrity verification.

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

Download large datasets from NCBI efficiently using EPost, history server, batching, rate limiting, and retry logic. Use when bulk-fetching tens of thousands of sequences, pulling all results of a large ESearch, designing reproducible pipelines, comparing E-utilities to NCBI Datasets v2 CLI, or implementing checksum-validated downloads. Encodes WebEnv TTL (~8h), EPost 200-ID limit, retmax caps, parallelization design, and integrity verification.

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

Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query depth exploitation, and introspection abuse. Includes pagination exploitation for data exfiltration, webhook hijacking for SSRF and data interception, and resource exhaustion through algorithmic complexity attacks. Covers race conditions in API transactions using parallel request techniques. Provides comprehensive JWT manipulation including algorithm confusion, kid injection, jku/x5u abuse, and claim tampering. Details API key leakage detection across source repositories, client-side code, and error messages. Covers undocumented endpoint discovery through predictable naming, debug routes, and source map analysis. Tooling includes Arjun, ParamSpider, jwt_tool, and GraphQL Voyager. Designed for a...

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

Implement and debug large-model training with PyTorch FSDP, which splits training state across devices. Consult documentation and code patterns for sharding choices, mixed precision, and checkpoints when building or reviewing distributed training code.

• Implement distributed training for large models
• Compare FSDP wrapping and sharding patterns
• Review mixed-precision and checkpoint examples

Design mock APIs, simulated services that reproduce expected responses, authentication, errors, and delays. Define scenarios and repeatable test data to support frontend development, integration testing, and realistic demos before the real backend is ready.

• Developing a frontend before the backend is ready
• Simulating a partner or third-party API
• Preparing a demo with realistic API responses

Coordinate specialized agents in Claude Code to divide development and review tasks, pass findings between stages, and combine results into one report with prioritized recommendations and action items.

• Reviewing code from security, performance, and quality perspectives
• Coordinating frontend, backend, and database work
• Combining specialist findings into a prioritized report

Organize complex work into phases and save plans, findings, and progress in project files. Keep separate task records and, on supported hosts, automatically bring the selected plan back into the agent’s working context.

• Planning research with many tool calls
• Resuming tasks from saved project records
• Keeping records separate for parallel tasks

Organize complex work into phases and save plans, findings, and progress in project files. Keep separate task records and, on supported hosts, automatically bring the selected plan back into the agent’s working context.

• Planning research with many tool calls
• Resuming tasks from saved project records
• Keeping records separate for parallel tasks

Find people and assess identity matches using public information from social media, official records, and reverse lookups. The skill cross-checks independent sources, reports confidence levels, and requires at least three matching identifiers for a high-confidence result.

• Looking for an old friend or former coworker
• Checking public information about an unknown caller
• Finding public accounts linked to a username

Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.

• Test CUDA code without a local GPU
• Run model training or LoRA fine-tuning on cloud GPUs
• Deploy a model inference API or vLLM service

Research private companies with parallel agents covering business, finances, competition, governance, technology, and alternative evidence such as hiring trends. Combine findings into a valuation report that separates verified facts, estimates, conflicting sources, and unknowns.

• Researching a private company's business and risks
• Comparing funding valuations with estimated business value
• Finding operating signals in hiring and patent data

Add PyTorch FSDP2 to training scripts so model state can be split across GPUs. Covers distributed initialization, mixed precision, CPU offloading, and checkpoint saving and loading for models that exceed a single GPU's memory.

• Training a model that exceeds one GPU's memory
• Adding FSDP2 to an existing training script
• Configuring mixed precision and CPU offloading

Turn broad life sciences questions into focused research plans. Resolve names and identifiers for genes, diseases, or compounds, select relevant research skills, and combine evidence into a concise answer that explains uncertainty and useful follow-up analyses.

• Reviewing evidence linking a gene to a disease
• Combining evidence about a variant and its associated traits
• Researching protein structure, function, and drug interactions

Compare computing devices for a defined AI model workload using memory capacity, computing speed, data transfer, energy use, and cost. Build a comparison that separates predicted performance from measurements and identifies the constraints that determine the choice.

• Choosing hardware for a specific AI model
• Checking whether a model fits in device memory
• Explaining gaps between advertised and measured performance

Design studies that combine quantitative data, such as surveys, with qualitative evidence, such as interviews. It recommends a suitable design and outlines study phases, participant selection, timing, and ways to combine findings into an integrated interpretation.

• Plan follow-up interviews to explain survey results
• Develop survey measures from interview findings
• Compare quantitative and qualitative findings

Survey academic research on a topic by searching journals, working papers, and citation links. Combine findings into a structured report covering key papers, competing results, research gaps, and verified bibliography entries.

• Survey prior research on a new topic
• Find related studies through a key paper's citations
• Compare conflicting findings across studies

Choose and implement methods for estimating causal effects from observational data or policy changes. Guidance covers method assumptions, estimation, diagnostic checks, and robustness tests that examine whether findings hold under alternative analysis choices.

• Choosing a causal method for evaluating a policy change
• Analyzing policies introduced at different times across regions
• Checking instrumental variable strength and underlying assumptions

Estimate how an intervention affects outcomes using Bayesian causal analysis. The workflow confirms causal assumptions with the user, selects a suitable method, checks whether findings withstand challenges, and reports effects with uncertainty and limitations.

• Estimating the effect of a policy or intervention
• Mapping causal relationships before analysis
• Selecting a method for observational data

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

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

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

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

Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA search for complexes, PDB70 structural templates, hosted NVIDIA API calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (the recommended default fast path, ~14 min vs over 80 min for the built-in downloader); a plain docker run uses the slow built-in downloader.

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

YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective using ALL available data. Produces unfiltered Hard Truths report. After user types YOLO, autonomously runs the business for a day using /loop.

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

Functional programming helpers for Golang using samber/lo — 500+ type-safe generic functions for slices, maps, channels, strings, math, tuples, and concurrency (Map, Filter, Reduce, GroupBy, Chunk, Flatten, Find, Uniq, etc.). Core immutable package (lo), concurrent variants (lo/parallel aka lop), in-place mutations (lo/mutable aka lom), lazy iterators (lo/it aka loi for Go 1.23+), and experimental SIMD (lo/exp/simd). Apply when using or adopting samber/lo, when the codebase imports github.com/samber/lo, or when implementing functional-style data transformations in Go. Not for streaming pipelines (→ See `samber/cc-skills-golang@golang-samber-ro` skill).

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

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

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