AI & ML

nilecui Skill

Parse PDF documents into markdown using MinerU API. Use when users need to extract text, tables, and formulas from PDFs for blog posts, team documentation, or content analysis. Handles task submission, status checking, and markdown retrieval. Supports OCR and VLM model for high accuracy.

nim-lang Bundle

Use for Nim symbol navigation, diagnostics, and type resolution. MANDATORY: Use specialized MCP tools (nimFindSymbols, nimFindReferences, nimListSymbols, nimCheckFile, nimCheckProject, nimFindTypeDefinition) first; fall back to grep only on error or user confirmation.

notnotype Bundle

A Chinese-prose rule library with two entry points. Before writing, emit the rules as writing constraints to load into a system prompt or style guide. After writing, lint the draft with static rule hits, neural AIGC heatmaps, contextual review, approved repair, and local learning notes. Use when drafting or rewriting Chinese prose and you want to avoid AI writing tells up front, when you need a wording/sentence-pattern constraint list or style preset for a writer, and when reviewing Markdown or plain text for AI writing tells, naturalness, repetitive patterns, lint rules, repair plans, or llmlint configuration.

nimbleway Skill

Durable cited web research via Nimble Agent runs.

nimotea Bundle

这是一个专用于生成 Gemini 提问文本的工具。只有当用户明确提到 '问 Gemini'、'Gemini 怎么说'、'整理发给 Gemini' 或类似的明确包含 'Gemini' 关键字的意图时，才应触发此 skill。不要在仅仅提到 '整理上下文' 或 '生成 prompt' 但未指定 Gemini 时触发。

nimrodfisher Bundle

Install Agent Think Map into this NanoClaw checkout — live skill/tool/MCP visualization over SSE. Additive copies only; never merge channels or providers.

ninghu Bundle

Run the Microsoft Foundry Agent Insights quality bug bash in Copilot CLI. Use when asked to set up, try, onboard, diagnose permissions for, generate a first result with, or review Agent Insights using the fixed Prompt or source-code Hosted sample in a prepared project, with an explicit scratch fallback.

nvandessel Skill

Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.

nvidia-bionemo Bundle

Build and run GPU-accelerated Quantitative Systems Pharmacology (QSP) and PBPK population ODE simulations with the nvQSP library, and differentiate them. nvQSP provides a sparse polynomial RODAS4 stiff solver (prebuilt) and a model-specialized dense adaptive TSIT5 solver, both with first-class gradients. Use this whenever the user wants to simulate compartmental PK/PBPK models, run virtual-population or batch patient simulations, do population PK variability studies, fit or train model parameters against data, solve stiff pharmacology ODEs on an NVIDIA GPU, or mentions nvQSP, `nvqsp`, `sparse.solve`, `gradients.solve`, `tsit5`, RODAS4, TSIT5, parameter sensitivities, or translating a pharmacology model into A0/A1/A2 coefficient form. Trigger this even when the user just describes a compartmental model ("two-compartment IV infusion across 1000 patients") without naming the library, since encoding the model into nvQSP's sparse-tensor form and getting the dosing/CSR conventions right is the hard part.

nvidia-bionemo Bundle

Replace attention in a PyTorch model with HyenaND from the nvSubquadratic library. Covers 1D / 2D / 3D hosts (ViT, U-Net, diffusion, causal LM, hierarchical encoders). Trigger when the user wants a subquadratic alternative to attention, ports a model to HyenaND, swaps `nn.MultiheadAttention` or `F.scaled_dot_product_attention` for a Hyena mixer, builds a striped Hyena LM, or asks "how do I use nvSubquadratic with my model." Phrases like "make my ViT subquadratic," "Hyena layer for my U-Net," "swap attention with FFT convolution," "subquadratic alternative for my 3D segmentation network," or "long-context model with O(L log L) scaling" should all activate this skill.

nvidia Bundle

Use for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. Not for unrelated ML code.

nomadamas Skill

Use BananaTape CLI to create, launch, inspect, and clean up local AI image editing projects from an agent.

ningzimu Skill

分析 Claude Code 会话的 trace。当用户提及 UUID 格式的 session ID（由数字与小写字母组成）、时间线索（"刚才"、"今天"、"最近一次"）、排查 Agent行为原因、希望查看某条claude code会话内容、对 trace 内容进行分析时，使用此 Skill。

nishantwrp Skill

Proposes new merges for different kinds of filters based on the user's request. This helps the users of this webapp to effectively search for organizations.

nishimoto265 Skill

Use when the user wants to run, document, or reuse an Anthropic-inspired Claude Code development loop, including planning interviews, Fixture/Invariant/Probe verification, main/sub-agent implementation, PR review evidence, and post-merge harness updates. Trigger on phrases like Anthropic DevLoop, Claude Code development loop, harness-driven development, evals, verification loop, or multi-agent implementation flow.

nomarj Bundle

Automated security auditing for AI agent code. Scans repos, packages, MCP servers, and installed skills for malicious patterns using eight-phase analysis: install hooks, dangerous code patterns, network exfiltration, credential access, obfuscation, provenance, prompt injection, and skill security. Use when: cloning repos, installing packages, reviewing MCP servers, auditing skills, scanning code before execution, or when asked to check if something is safe, audit code, scan for malware, review dependencies.

nomyfan Bundle

Use the skills-man `skill` CLI to install, sync, update, list, and uninstall AI agent skills from GitHub repositories. Use when a user asks how to manage skills with skills-man, configure global or local skill directories, install a skill or collection from a GitHub tree URL, set GitHub authentication for private repositories, inspect skills.toml state, or troubleshoot common skills-man CLI behavior.

non-lab Bundle

Comprehensive toolkit for spatial single-cell analysis in Python with MCP DeepWiki integration. Use this skill when users need to: (1) Build and analyze spatial neighbor graphs from spatial coordinates, (2) Compute spatial statistics for cell types and genes (Moran's I, co-occurrence, neighborhood enrichment), (3) Analyze tissue images and extract image features, (4) Identify spatial niches using neighborhood profiles, UTAG, or CellCharter algorithms, (5) Perform ligand-receptor interaction analysis, (6) Read spatial omics data from various platforms (Visium, MERFISH, CosMx, Xenium) using squidpy.read or spatialdata_io, or (7) Visualize spatial data and analysis results.

noobnooc Bundle

Configure or use Echobell notifications for long-running agent work. Use when the user wants an Echobell alert on completion or failure, wants to install or configure the Echobell skill, needs help choosing notification urgency, or needs a clean Echobell webhook payload for task results.

nuclearpasta Bundle

Automates mobile and simulator interactions for iOS and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, pinching, or extracting UI info on mobile devices or simulators.

nuitka Skill

Use when creating or updating Nuitka changelog entries (hotfix releases like 4.1.3 or upcoming releases) in the Nuitka website repository, by running update-changelog.py to generate the commit prompt and editing site/changelog/Changelog-next.rst.

nuke-on-rails Bundle

Full health and security audit for Rails apps, the review a principal engineer would do. Runs rubycritic, Brakeman, bundler-audit and ruby_audit, triages every finding with the LLM as judge, brings an OWASP Top 10 arsenal of checks for what scanners miss, and returns one impact-ranked action plan. Use for a Rails project audit, a security and health check, "nuke on rails", or a deep review of a vibecoded Rails app.

nukeop Skill

Reference sheet for the notation format used by musescore-mcp tools, and for reading get_overview output. Use when calling musescore-mcp tools.

nxdus Bundle

Enable efficient communication between Thai-language users and agents by translating Thai prompts into English in two modes and by preventing Thai text corruption in files. Use when the user writes in Thai, asks for Thai-to-English interpretation, wants token-efficient prompt rewriting, or reports mojibake/replacement-character issues such as U+FFFD in saved files.

nxus-systems Bundle

Use when a user asks Codex to add, migrate, prototype, or explain nxusKit SDK integrations, provider-agnostic LLM workflows, nxuskit-cli CLI/Bash workflows, CLIPS rules, Bayesian inference, solver/ZEN workflows, or hybrid LLM plus symbolic reasoning patterns.

niukesi Bundle

中文AI Agent专用多平台聚合搜索工具，开箱即用，国内网络友好，自动总结结果

njzjz Skill

Create new Agent Skills following the agentskills.io specification. Use when the user wants to create, scaffold, or design a new skill for AI agents. Handles SKILL.md generation, directory structure setup, and validation.

nunaught Bundle

Generate, revise, translate, and adapt song lyrics plus compact style prompts for Suno or similar AI music generators. Use when the user wants ready-to-paste AI music generation lyrics, lyric tags, Suno/Udio-style prompts, vocal direction, instrumentation, genre/style wording, song structure, multilingual singable lyrics, or a clarifying interview for an AI-generated song. Do not route general music theory, ordinary artist research, or non-generation songwriting discussion here unless the requested deliverable is lyrics or a generation-ready style prompt.

noone-hub Bundle

在使用 MCP 做前端 JavaScript 逆向时使用，适用于签名链路定位、页面观察取证、本地补环境复现、VMP 类插桩分析、AST 去混淆与证据化输出。

nooooocato Bundle

The foundational template for Self-Evolving Agent Skills (SEAS). Standardized for autonomous learning and safety.

nxxxsooo Bundle

麦当劳中国 MCP（mcd-mcp，https://mcp.mcd.cn）全能力操作手册：查活动日历、麦麦省领券、我的券/积分、餐品营养热量、附近门店、麦乐送/到店自取/得来速/企业团餐点餐全链路（选址→选店→菜单→算价→下单→查订单）、麦麦商城积分兑换餐品券与实物商品及其订单查询。当用户提到麦当劳、麦当劳点餐、麦乐送、麦当劳外送、金拱门、买麦当劳、点个麦当劳、麦当劳优惠券、麦麦省、领券、麦当劳积分、积分兑换、麦麦商城、麦当劳活动日历、麦当劳菜单、麦当劳热量/营养、得来速、Drive Through、麦当劳团餐、我的麦当劳订单、mcd、mcdonald、McDonald's、mcd-mcp 时使用。也负责该 MCP 的接入配置与 401/429 排障。不负责其他外卖平台（美团/饿了么）或非中国大陆麦当劳。

nyldn Bundle

Choose whether to keep or switch the current AI model and reasoning effort in ChatGPT, Codex, or Claude. Use when the user asks which model, effort, or AI should handle a task, whether the current model is enough, or whether another model should review it.

nurulislamkhan Bundle

Audit an Agent Skill folder for specification compliance, broken local references, portability risks, unfinished placeholders, overly broad tool access, and publish readiness. Use when reviewing, validating, packaging, or preparing a SKILL.md directory for release.

nutllwhy Bundle

视频动效模板系统。20个可复用动效模板，支持参数化修改、Agent 动效方案导入、本地批量渲染，以及纯色底 MP4、透明 MOV 与透明 WebM 导出。

nyxandro Bundle

Use when the user says "sparring", "run sparring with Claude", "do sparring with Claude", "do sparring with GPT-5", "sparring with Codex", "sparring my plan with Claude", "discuss this approach with Codex", "get a second opinion through sparring", "give me the sparring transcript", "read the long sparring answer", or asks to leave a sparring session running. Runs a model-vs-model sparring flow through the bundled sparctl harness for planning, brainstorming, second opinions, code review, architecture critique, or normal dialogue; uses one ask-session command that creates or continues provider-native state, and uses tmux only when explicitly needed for live/fallback sessions.

normlstudio Bundle

Install or set up MoonPress Chat on a WordPress site through a safe six-stage workflow: preflight, research, owner questions, connect, configure, and verify. Defaults to the shipped MoonPress Chat setup API with a local credential helper; keeps the guided WordPress-admin path as the documented fallback. Use when a site owner asks to install, plan, configure, review, or launch MoonPress Chat without exposing WordPress passwords or AI-provider keys to the agent.