Processament de dades

Transformació i anàlisi sintàctica de dades

Skills: 793–816 de 13415
NousResearch

grpo-rl-training

NousResearch

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Processament de dades 256,9 k fa 7 mesos
NousResearch

evaluating-llms-harness

NousResearch

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Eines de línia d’ordres 256,9 k fa 8 mesos
NousResearch

guidance

NousResearch

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Processament de dades 256,9 k fa 7 mesos
NousResearch

polymarket

NousResearch

Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

Desenvolupament d’API 256,9 k fa 7 mesos
NousResearch

godmode

NousResearch

"Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness."

Processament de dades 256,9 k fa 7 mesos
NousResearch

outlines

NousResearch

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Generació de codi 256,9 k fa 8 mesos
NousResearch

axolotl

NousResearch

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Desenvolupament d’API 256,9 k fa 8 mesos
NousResearch

nemo-curator

NousResearch

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Processament de dades 256,9 k fa 5 mesos
affaan-m

continuous-learning

affaan-m

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Autenticació 288,3 k fa 8 mesos
affaan-m

cpp-coding-standards

affaan-m

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.

Generació de codi 288,3 k fa 8 mesos
affaan-m

market-research

affaan-m

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Àmbit acadèmic 288,3 k fa 8 mesos
elie222

qa-run

elie222

Run browser QA flows and write a JSON report

Analítica 12,8 k fa 8 mesos
dair-ai

LLM Council

dair-ai

Orchestrate multiple open-weight LLMs via Fireworks AI to deliberate on queries. Models respond individually, rank each other's responses, then a Chairman synthesizes the final answer. Use this skill when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach inspired by Karpathy. Powered by fast, affordable open-weight models on Fireworks.

Processament de dades 617 fa 8 mesos
elie222

security

elie222

Security guidelines for API route development

Automatització 12,8 k fa 8 mesos
elie222

fullstack-workflow

elie222

Complete fullstack workflow combining GET API routes, server actions, SWR data fetching, and form handling. Use when building features that need both data fetching and mutations from API to UI.

Processament de dades 12,8 k fa 8 mesos
elie222

server-actions

elie222

Guidelines for implementing Next.js server actions

Processament de dades 12,8 k fa 8 mesos
elie222

llm

elie222

Guidelines for implementing LLM (Language Model) functionality in the application

Processament de dades 12,8 k fa 8 mesos
hhszzzz

divination

hhszzzz

Structured fortune-telling workflow skill using MCP tools. Use when users ask for divination, 八字/四柱, 六爻, 紫微斗数, 塔罗, 大运, 运势/流年, or want standardized解读流程 (e.g., 八字先看身强弱与喜用神再看大运流年). Enforce fixed analysis order, call the right MCP tool, and produce actionable interpretations.

Agents 679 fa 8 mesos
lyndonkl

d3-visualization

lyndonkl

Use when creating custom, interactive data visualizations with D3.js—building bar/line/scatter charts from scratch, creating network diagrams or geographic maps, binding changing data to visual elements, adding zoom/pan/brush interactions, animating chart transitions, or when chart libraries (Highcharts, Chart.js) don't support your specific visualization design and you need low-level control over data-driven DOM manipulation, scales, shapes, and layouts.

Analítica 186 fa 11 mesos
lyndonkl

heuristics-and-checklists

lyndonkl

Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions heuristics, rules of thumb, mental models, checklists, error prevention, cognitive biases, satisficing, or needs practical decision shortcuts and systematic error reduction.

Generació de codi 186 fa 11 mesos
lyndonkl

code-data-analysis-scaffolds

lyndonkl

Use when starting technical work requiring structured approach - writing tests before code (TDD), planning data exploration (EDA), designing statistical analysis, clarifying modeling objectives (causal vs predictive), or validating results. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", or when technical work needs systematic scaffolding before execution.

Generació de codi 186 fa 11 mesos
marketcalls

openalgo-chart-setup

marketcalls

Scaffold a working openalgo-charts chart in an existing project - detects the host (React, Next.js, Vue, vanilla bundler, or plain script tag), installs the right tiers, and writes a chart that renders real data. Use when the user asks to add a chart, set up openalgo-charts, or get a first chart running.

Processament de dades 175 fa 28 d
marketcalls

openalgo-chart-terminal

marketcalls

Build a full trading terminal on openalgo-charts - symbol search, interval switcher, chart-type picker, indicator menu, drawing rail with clipboard, live OpenAlgo REST plus WebSocket data behind a warm-load bar cache, on-chart order lines with drag-to-modify, market depth, a settings dialog and context menu, market replay, symbol comparison, a linked split view, and layout persistence. Use when the user asks for a trading terminal, a charting workstation, on-chart trading, a linked chart grid, or to wire orders onto a chart.

Processament de dades 175 fa 1 mes
lingxling

apify-ecommerce

lingxling

"Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool."

Processament de dades 319 fa 6 mesos