AI & ML

ndjordjevic Bundle

Automates the Karpathy LLM Wiki workflow: turns web, GitHub, and YouTube URLs into well-structured, citable, wikilinked pages with automatic linting and sourcing — invoke with /pin-llm-wiki

ndjordjevic Bundle

Generates a committable Markdown wiki from the repo it lives in — invoke with /repo-llm-wiki

nealcaren Bundle

Run computational jobs on UNC Chapel Hill's HPC clusters (Longleaf and Sycamore). Use when a user wants to: submit SLURM batch jobs, set up Python/conda environments for ML/deep learning, run PyTorch or TensorFlow training on GPUs, run Hugging Face model inference or fine-tuning (including Unsloth for fast QLoRA), use Jupyter notebooks on the cluster, transfer data, manage storage, monitor GPU utilization, write SLURM scripts, do hyperparameter sweeps, or anything involving UNC Research Computing infrastructure. Covers both Longleaf (high-throughput, broad GPU selection) and Sycamore (HPC, H100 GPUs).

nealst Bundle

A skill to test the SBTI character of your agent. Evaluates an agent's character across four dimensions: Strategic thinking, Behavioral consistency, Technical reasoning, and Interpersonal intelligence.

nealst Bundle

Scrape a website's knowledge with agent-browser and turn it into a new SKILL.md. Use when the user wants to: create a skill from a documentation site, blog, API reference, tutorial, or any URL; bootstrap a SKILL.md from web content; package external knowledge as a Copilot skill. Trigger phrases: '从这个网站做一个 skill', 'scrape this site into a skill', '把这个文档变成 skill', 'create a skill from <url>', 'turn <url> into a skill', 'agent-browser skill creator'. Combines web scraping (agent-browser CLI) with skill authoring (agent-customization conventions).

nebius Bundle

skill - Install agent skills

netresearch Bundle

Use when a coding agent works in a repository where Jujutsu (jj) is available (a `.jj/` directory) — running jj commands, making speculative edits, splitting changes, recovering with the operation log (jj undo / jj op restore), handing off a PR to Git/GitHub/GitLab, updating a PR after review, or coordinating parallel agents. Uses jj as the local change-management layer while keeping Git as the canonical remote, PR, CI, and audit interface. Also use to avoid jj's agent footguns (pager/editor hangs, commit absorption, colocated git/jj desync) or to replace fragile git reset/checkout/stash/rebase recovery with reversible jj operations.

nevertoday Bundle

Create XXD Panel 107 raster artwork: a faithful photograph paired with a readable rebus-style visual sentence whose source-derived hand-drawn image words genuinely replace words in the text. Accepts one image or a directory batch and supports exact 50:50 top-bottom or left-right pairs, design-only artwork, four-device wallpaper, multiple ratios or exact sizes, and prompt-generated or user-supplied wording. Use whenever the user invokes xxd-panel-107 or asks for this image-word visual-poetry style.

newrelic Bundle

Scaffold a complete New Relic Ruby agent instrumentation for a third-party gem in this repo. Use when the user asks to "instrument <gem>", "add instrumentation for <gem>", "scaffold a new instrumentation", or names a datastore / HTTP-client / messaging / AI-LLM gem and asks the Ruby agent to trace it. Generates the seven-file prepend+chain layout under `lib/new_relic/agent/instrumentation/<name>/`, a runnable multiverse suite under `test/multiverse/suites/<name>/`, registers config in `default_source.rb`, and adds the gem to `supported_gems.txt`. Does NOT commit, push, or open PRs.

neeeophytee Bundle

Discover, register, and hire ERC-8004 autonomous agents across 22,000+ agents on EVM + Solana. Search by capability, check on-chain reputation scores, compare agent services by category with composite scoring, browse the service catalog, enrich agent profiles, check buyer reputation, and get complete machine-readable hiring instructions. Pay with USDC via x402.

netease-youdao Bundle

学术论文搜索与分析服务 (Academic paper search & analysis)。当用户涉及以下学术场景时，必须使用本 skill 而非 web-search：搜索论文、查找 ArXiv/PubMed/PapersWithCode 论文、查询 SOTA 榜单与 benchmark 结果、引用分析、生成论文解读博客、查找论文相关 GitHub 仓库、获取热门论文推荐。Keywords: arxiv, paper, papers, academic, scholar, research, 论文, 学术, 搜索论文, 找论文, SOTA, benchmark, MMLU, citation, 引用, 博客, blog, PapersWithCode, HuggingFace.

newts7 Bundle

Audit installed Claude Code skills for prompt-injection and supply-chain risk, and report which are safe and which are not. Use when the user asks to check, audit, review, or vet their skills/plugins for security, prompt injection, hidden instructions, or malicious content — e.g. "are my skills safe", "scan my skills", "which skills can be trusted".

next-space Bundle

Use when an agent needs to call the Buildin API through the Buildin CLI, authenticate Buildin, upload a file, create or update a page, query a database, search content, edit Markdown page content, or any task involving the `buildin` command.

nextlevelbuilder Bundle

Manage GoClaw AI agent gateway servers from Claude Code. Use this skill when the user mentions "goclaw", "gateway server", "AI agent platform", or wants to execute shell commands remotely on a server, manage AI agents, approve agent actions, inspect chat sessions, or administer multi-tenant AI infrastructure. Wraps the `goclaw` CLI to call REST + WebSocket APIs of GoClaw Gateway.

nemotek-inc Bundle

Aegis Boundary Skill — review whether AI-agent work stays within Aegis product boundaries in what it sees, does, outputs, and claims. ADVISORY review only: it does not authorize, enforce, or produce receipts — runtime enforcement belongs to the aegis-trust SDK (LITE) and Aegis Core (FULL). Reviews whether an agent task, code change, document, or public claim preserves Aegis boundaries (SDK/Core responsibility split, LITE/FULL claim separation, honesty guardrails, never-claims, naming) and returns READY / REVIEW / STOPPED with machine-check evidence. Use when: working with aegis-trust or Aegis Core integrations; editing README, website, sales, or customer-facing claims about Aegis; changing what an AI agent is allowed to see, do, or output through Aegis; before publishing any artifact that makes claims about Aegis; or when asked "boundary review", "claim check", "境界確認", "claim parity", "can we say this publicly?". NOT for: production authorization decisions (SDK/Core runtime territory), projects unrelated to A

netresearch Bundle

Use when estimating effort for TYPO3 LTS major version upgrades (current target: v14.3 LTS, released 2026-04-21). Provides risk multipliers for v14 breaking changes (fact catalog owned by typo3-conformance's v14-deprecations.md), per-extension baselines, version-compatibility matrix, Rector coverage adjustments, 7-phase assessment workflow. Calibration-free; pair with your historical data for tuned estimates.

nexu-io Bundle

auto-github-contributor — interactive OSS PR agent

nexu-io Skill

Draft release summaries, changelog summaries, version PR notes, and changeset-friendly package release notes for npm packages or monorepos. Use this whenever the user asks to write a release summary, 发版说明, release notes, changelog entry, version PR summary, package publish notes, or wants the agent to summarize what will be released from git history, diffs, or changesets, especially for ui libraries, design systems, and multi-package workspaces.

nexu-io Bundle

SBTI 赛博人格测试 — 互联网最火的人格测试，27 种沙雕人格等你解锁。可以测自己，也可以测你的 AI agent。 **当以下情况时使用此 Skill**： (1) 用户说"做 SBTI 测试"、"SBTI"、"赛博人格测试"、"测人格"、"人格测试" (2) 用户说"给龙虾做测试"、"测一下我的 agent" (3) 用户提到 CTRL、BOSS、SEXY、IMSB、DEAD 等 SBTI 人格代码 (4) 用户说"来个性格测试"、"整点沙雕测试"

netvar1337 Skill

Infrastructure layer for AI agent swarms — 88 MCP tools for mesh control, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, browser automation, and more. ~80ms execution.

neurabytelabs Bundle

Use when a Hermes session should apply Mustafa Saraç's RUNE prompt-amplification framework to planning, coding, writing, analysis, strategy, or prompt-design tasks. Converts rough intent into structured 8-layer instructions with Spinoza-style QA while keeping simple requests lightweight.

nicobailon Bundle

Use when starting or reviewing a complex implementation where the user wants an agent to interrogate the plan against docs/source evidence, surface unknown unknowns, and avoid rushing into build mode. Combines docs-grounded grilling with a map-vs-territory unknowns pass.

nicobailon Skill

Multi-agent coordination for parallel plan execution with the coordinate and coord_output tools.

neurodong Skill

Generates structured AI paper reviews (SoT style) for LaTeX, PDF, and Word manuscripts. Uses SoT prompt in English for English papers and SoT prompt in Chinese for Chinese papers. Use when the user asks to review a paper, 审稿, 论文审稿, review manuscript, or get strengths/weaknesses/suggestions for a .tex, .pdf, or .docx file.

nicobailon Skill

Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.

nicobailon Skill

Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination. Crew workers already have the pi_messenger actions they need in crew-worker.md.

nicobailon Skill

Write and run custom Pi prompt templates (slash commands) for this extension. Use when creating templates with model selection, deterministic pre-steps, loops, chains, subagents, or best-of-N compare flows.

nidhinjs Bundle

Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts. Use when prompts are vague, missing scope, or mention a stack without clear task definition.

nkchivas Bundle

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

nkur22 Bundle

Scan a user's Gmail to find upcoming subscription renewals, recurring payments, and billing deadlines. Use this skill whenever the user asks about their subscriptions, recurring charges, upcoming renewals, payment schedules, billing timelines, or wants to audit what services they're paying for. Also trigger when users say things like 'what am I subscribed to', 'when is my next bill', 'show me my recurring payments', 'subscription audit', 'what's renewing soon', 'am I still paying for X', or any variation involving tracking, managing, or reviewing subscription costs from their email. This skill requires the Gmail MCP connector to be enabled.

nikhilgovindaraju Skill

Generates a structured handoff document so the user can continue this conversation in a different LLM (ChatGPT, Gemini, Cursor, Codex, or another Claude session) without losing context. ALWAYS use this skill when the user types "/handoff", says "handoff", "hand off", "session handoff", or asks to "continue this elsewhere", "switch to ChatGPT/Gemini/Cursor", "export this chat", "summarize for another LLM", "session is ending", "context limit", or anything similar. Also use when the user mentions running out of messages, hitting a session limit, or wanting to pick up the work later in a different tool. Do not skip this skill for short conversations — use the brief format instead.

nicholasspisak Bundle

Design the optimal multi-agent cmux team for a coding objective, generate a launch kit — a one-line cmux launcher plus lead and worker system-prompt files — then, once you confirm, launch it: cmux opens and the lead boots an observable team of agents in named panes (roster — role, model, thinking level, count — plus topology, coordination protocol, rubric, and constraints). It always asks before spending execution tokens, and never does the team's work itself. Use to staff any non-trivial coding objective; for trivial tasks it recommends a team of one.

nicholasspisak Bundle

Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider", "new goal for the next round", "rider for X", "brief the next agent on X", or asks for a /goal condition or objective for Claude Code or Codex.

nikiforovall Bundle

Use when the user wants to demo a Claude Code Hub sub-app (marketplace, cck/kanban, cost, memory), capture product screenshots, or build a seeded demo dataset — isolates from the user's real ~/.claude data and captures high-quality (HQ) Playwright screenshots. Triggers on "demo the hub", "take screenshots", "screenshot demo", "seed demo data".

nikiforovall Skill

Query the DIAL AI model catalog, inspect a specific model's details/capabilities, or check rate-limit usage via the local `dial` CLI shipped with the pi-dial package. Trigger when the user asks about DIAL models, "what openweight/Anthropic/GPT model is available", token quotas / rate limits, or wants to look up a model id served via EPAM's DIAL proxy.

nilecui Bundle

配置 harness，定义专业智能体，并生成这些智能体所使用的技能——元技能（meta-skill）的简体中文版本。触发场景：(1) 用户说『给这个项目搭一个 harness』『构建 harness』『配置 harness』；(2) 用户请求『harness 设计』『harness 工程化』；(3) 为新领域/新项目建立基于 harness 的自动化体系；(4) 重构或扩展已有 harness；(5) 用户请求『harness 点检』『harness 审计』『harness 现状』『智能体/技能同步』等运维/维护任务；(6) 用户提到『组织 agent』『设计工作流』『多 agent 协作』『搭建自动化流程』『agent 怎么分工』『agent 团队』等表达。等同于 skills/harness 的功能，仅语言不同，按用户使用的语言选择其一即可。