В каталоге 183 730 навыков в 14 категориях.
Curate LLM training data: dedupe, filter, PII redaction.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faste...
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or...
This prompt directs an image model to generate a stylized X-ray scan of the specified subject, highlighting bones and in...
Use when working in projects with .neotex/ directory to retrieve organizational knowledge, search for patterns/guideline...
Use when user runs /neotex-init to deeply scan a codebase and auto-generate organizational knowledge for neotex.
nequip (Neural Equivariant Interatomic Potential) is a molecular potential prediction model based on E(3)-Equivariant Gr...
Strict file creation rules. Loaded FIRST by orchestrator and all agents before any action. Prevents pollution with .md,...
Nederlandse Richtlijn Digitale Systemen (NeRDS): 13 richtlijnen voor ontwerpen, ontwikkelen en inkopen van digitale over...
Verantwoord gebruik van algoritmen en AI bij de overheid: AI-verordening (AI Act), algoritmeregister, IAMA, bias, uitleg...
Cloud bij de overheid: cloudstrategie, soevereine cloud, IaC, FinOps, multi-cloud, hybride cloud, SRE, Kubernetes, exit-...
Datamanagement bij de overheid: datakwaliteit, data governance, open data, datadeling, metadata, data bij de bron, datag...
Duurzame ICT bij de overheid: green IT, green coding, energieverbruik, CO2-footprint, circulair, MVI (maatschappelijk ve...
Gebruikersbehoeften en -onderzoek bij digitale overheidssystemen: user research, persona's, klantreis (customer journey)...
Inkoop van technologie bij de overheid: aanbesteding, inkoopstrategie, vendor lock-in, leveranciersselectie, PIANOo, TCO...
Systeemintegratie bij de overheid: API's, middleware, microservices, legacy, Digikoppeling, FSC, Common Ground, Haven, k...
Open source werken bij de overheid: EUPL, publieke code, open-tenzij, licenties, CONTRIBUTING.md, Code of Conduct, secre...
Privacy bij de overheid: AVG/GDPR, DPIA, persoonsgegevens, privacy by design, dataminimalisatie, verwerkingsregister, da...
Samenwerken en hergebruiken bij de overheid: kennisdeling, componenten hergebruiken, Common Ground, dubbel werk voorkome...
Open standaarden bij de overheid: Forum Standaardisatie, pas-toe-of-leg-uit, interoperabiliteit, voorkómen van vendor lo...
Digitale toegankelijkheid bij de overheid: WCAG, a11y, EN 301 549, screenreader, toetsenbordnavigatie, kleurcontrast, NL...
Informatiebeveiliging bij de overheid: BIO (Baseline Informatiebeveiliging), penetratietesten, kwetsbaarheden, versleute...
Use the Nesa repository for Equivariant Encryption demos, encrypted AI web UI setup, backend protocol inspection, and Ha...
Generate network diagram generator operations. Auto-activating skill for Visual Content. Triggers on: network diagram ge...
Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to r...
This skill governs the intentional corruption and reconstruction of the agent’s internal reasoning. By "injecting" speci...
分布式AI节点系统，实现跨局域网节点的任务分发、并行处理和结果聚合
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sort...
研究 codex 使用 skill 生成 survey 這件事
Scaffold a new ability with PHP backend, JS chat interface, and test case
When to Use: Creating new AI agents for Unite-Hub
Lead a batch of 20 to 50 landmark models for one city or park, with builder sub-agents, ending in a draft pull request....
Creates a new gallery item in src/content/gallery/ with valid frontmatter and image reference. Use when adding a photo,...
Design and scaffold a new module (boundary, subdomain, recipe, contracts, ADR, profile diff, fitness tests). Manual comm...
Implement a new synthetic data generator using NeMo Data Designer by defining its configuration and executing a preview...
Scaffold a new skill with correct directory structure, frontmatter, naming, plugin symlink, and validation
Create a new Claude Code skill with proper structure and effective description. Use when creating a new skill, or when t...
Creates a new Claude Code Skill following best practices. Use when the user wants to create a new skill, add a skill, or...
Creates a new testimonial in src/content/testimonials/ with valid frontmatter. Use when adding a customer quote, review,...
Build a new Valor-specific tool following established patterns. Use when creating tools that integrate with Valor's Tele...
Collects daily hot stock market issues and top movers for MeowStreet Wars video production. Identifies tickers with sign...
Summarize monitor and latest feeds into a concise briefing. Use when the user asks for recent AI news, trends, launches,...
A complete SEO toolkit for Next.js applications, including structured data (Schema.org), dynamic sitemap generation, and...
Set up the current empty folder with the AI App Starter, so the agent builds a Next.js, Supabase and Vercel app with the...
Orchestrator overseeing specialist AI agent teams. Decomposes requests, designs minimal agent chains, and in AUTORUN mod...
Nexus conversational PI agent architecture, development, and deployment. Use when working on the Nexus orchestrator, gat...
Enables your AI agent to discover and install skills from the Nexus Skills Marketplace. Install this skill first to unlo...
π/τ-tier. Structure, navigation, closure (~500 tokens). Navigation between skills. Decimal: π.8.0. Load via: φ→π
4-D prompt engineering assistant that transforms vague requirements into high-precision prompts through guided interacti...
倪海厦视角. 港台五术派代表 (1954-2012), 「命相卜山医一体」流派的 living archive. 提供「跨数术整合 + 命医同源 + 反江湖 + 反学院文献学」式决策视角, 与子平派单术深耕 (沈孝瞻 / 梁湘润) 与盲派师...
MOVED — nielsen-heuristics now ships in the humane plugin (glebis/humane-agentic-design), not here. This directory is a...
Talk to Nihaixia Suanming about their expertise. Nihaixia Suanming provides authentic advice using their mental models,...
Betroffenheitsprüfung und Registrierung nach NIS2 / neuem BSIG – wesentliche und wichtige Einrichtungen Art. 3 NIS2-RL /...
Aufbau der Risikomanagementmaßnahmen nach NIS2 / neuem BSIG – All-Hazards-Ansatz und die zehn Mindestmaßnahmen Art. 21 N...
Knowledge base from NIST AI Risk Management Framework 1.0 (NIST AI 100-1). Use for AI risk management, trustworthiness c...
Detects anomalies in time series data using TimeGPT. Identifies outliers, level shifts, and trend breaks without model t...
Forecast multiple time series in parallel using TimeGPT. Use when processing 10-100+ contracts efficiently. Trigger with...
Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the per...
Forecasts orderbook depth and spreads to optimize trade execution timing. Use when needing to estimate market liquidity...
Automatically selects the best forecasting model between StatsForecast and TimeGPT based on time series data characteris...
Analyze and categorize installed Nixtla Skills for forecasting guidance. Use when seeing available skills or selecting t...
Configure TimeGPT fine-tuning on custom datasets with Nixtla SDK. Use when training domain-specific forecast models. Tri...
Provides expert Nixtla forecasting using TimeGPT, StatsForecast, and MLForecast. Generates time series forecasts, analyz...
This skill should be used when guiding the OpenAI agent to map natural language user input to appropriate MCP tools, han...
Create a Natural Language Agreement escrow on-chain. Use when the user wants to lock ERC20 tokens in an escrow with a na...
Use when extracting structured information from text - named entity recognition, relation extraction, coreference resolu...
Trains a Byte-Pair Encoding tokenizer on the task corpus to capture domain-specific vocabulary, typos, and subword patte...
Cyclical learning rate (CLR) Keras callback that oscillates LR between base and max each batch for faster convergence
Trains a WordPiece tokenizer on in-domain text, then feeds its subword token IDs into TF-IDF vectorization for domain-ad...
Expert in Natural Language Processing, designing systems for text classification, NER, translation, and LLM integration...
Use this skill when building NLP pipelines, implementing text classification, semantic search, embeddings, or summarizat...
自然语言接口，理解用户意图并映射到对应的命令
Applies label smoothing to binary cross-entropy loss to reduce overconfidence and improve generalization in text classif...
Sort texts by length before batching with dynamic padding to minimize wasted padding tokens and speed up transformer inf...
Custom MAP@K evaluation metric — scores top-K classification predictions with reciprocal rank weighting for HuggingFace...
Applies multiple dropout masks to the same hidden state and averages predictions for regularization and variance reducti...
Natural language processing ML pipelines for text classification, NER, sentiment analysis, text generation, and embeddin...
Build natural language processing pipelines for text analysis and understanding
Process and analyze natural language using modern NLP techniques. Use for text classification, named entity recognition,...
Uses square root of MSE as training loss to directly optimize for RMSE evaluation metric alignment.
When the user wants to apply NLP to supply chain, extract information from documents, analyze supplier communications, c...
This skill enables Claude to perform natural language processing and text analysis using the nlp-text-analyzer plugin. I...
High n-gram TF-IDF (3-5 grams) with sublinear TF feeding into a weighted soft-voting ensemble of traditional ML classifi...
NLTK natural language toolkit. Use for NLP.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote exe...
> "Share and Enjoy!"
> "Don't hide behind qualifiers."
> "The warehouse of all NO-AI™ ideology"
> "Don't lecture unprompted."
> "YOUR COMPLIANCE IS APPRECIATED."
A skill with no eval.yaml for testing discovery behavior.
人間が `/no-issue` を打った会話が終わるまで、Issue 番号の無い作業指示を起票せずに着手させる。起票の手間と後片付けを省きたい作業で使う。「no-issue」「起票なしで進めて」「Issue にしないで」と指示されたとき。
Replaces the weekly team status meeting: collects what each person got done from team chat and the project board, surfac...
No Polling for Background Agents
Never Use TaskOutput