AI & ML

chainreactors Bundle

通过 IoM C2 MCP 工具进行自主渗透测试。覆盖完整攻击链：态势概览、信息收集、权限提升、 凭据获取、横向移动、持久化。基于 OODA 循环驱动 — 每阶段分析结果后再决定下一步。 触发条件：用户提到 "pentest"、"提权"、"横向"、"信息收集"、"凭据"、"持久化"、 "自动化测试"、"红队"、"后渗透"、"summary"、"态势" 时使用此 skill。

clickhouse Skill

Guides users through setting up the ClickHouse MCP server connection bundled with this plugin. Use when the user first installs the plugin or has trouble connecting to ClickHouse.

cobosteven Bundle

Create and manage agentic wallets with Cobo. Use for autonomous onchain operations via the caw CLI: token transfers, contract calls, pact creation and approval, DeFi execution (Uniswap, Aave, Jupiter), and wallet onboarding on EVM chains and Solana. Triggers on requests involving caw, MPC wallet, TSS node, agent wallet, Cobo, pact, or any crypto wallet operation for AI agents. NOT for fiat payments or bank transfers.

sumanth077 Bundle

Fetches articles from 92 Karpathy-curated RSS feeds, scores them with an LLM, selects the top 3, and delivers a formatted digest to Telegram every morning.

abzhaw Skill

Human-in-the-Loop Zitatverwaltung. Kein Paper wird zitiert ohne explizite menschliche Freigabe. Verwaltet BibLaTeX und den Genehmigungsworkflow.

hamza-ali-shahjahan Skill

Decide where attention goes today across the 10-product portfolio. The "if you had 4 hours to work on the portfolio, do this" agent.

nyldn Skill

Use when choosing native or multi-LLM handling for init, review, or security requests

aradotso Skill

Generate images and videos with AI using MeiGen MCP server for Claude Code, Cursor, and other AI coding tools

nzettodess Skill

Use when writing, reviewing, or optimizing batch data classification prompts. Enforces the strict structural anatomy, taxonomy rules, input/output formats, and few-shot requirements necessary for high-accuracy data classification at scale.

calesthio Bundle

Produce speech and clone voices with Fish Audio — its hosted TTS API (S2.1-Pro / S2-Pro / S1 model lineup, REST + WebSocket streaming, instant and persistent voice cloning) and its open-weight OpenAudio S1-mini / Fish-Speech models for self-hosting. Use this skill when an agent must generate narration or dialogue through Fish Audio, choose between Fish Audio's hosted models and open weights, clone a voice from reference audio, author emotion/tone/special markers for expressive delivery, estimate cost from UTF-8 bytes, wire real-time streaming for a voice agent, decide whether self-hosting beats the API, or review Fish Audio TTS output for production. Do not use it to pick a different provider — it covers Fish Audio specifically.

calesthio Bundle

Direct ByteDance Dreamina Seedance 2.0 Standard, Fast, and Mini video production across BytePlus ModelArk and verified gateways. Use for text/image/reference-to-video, native synchronized audio and dialogue, multimodal image-video-audio reference, first/last-frame animation, video editing or extension, model/gateway selection, prompt construction, async task handling, failure recovery, QA, and rights-safe production.

ruvnet Skill

Initialize a new Ruflo project with MCP tools, hooks, and agent configuration. Use when setting up Ruflo in a fresh repo, or when the user says "init ruflo", "set up ruflo", or asks how to bootstrap the MCP server, hooks, and agent configs from scratch.

robomotionio Skill

Configure, extend, or contribute to Hermes Agent.

12ff54e Bundle

Write, refactor, or review C++ and CUDA C++ in QZhong's personal style, inferred from BSplineInterpolation, mct/libmeq, clap.h, and the cuMES coding guide. Use for C++ implementation in QZhong's projects or requests to code like QZhong; preserve the target project's compatibility and local conventions.

255h Skill

Instructs how to use ABAP MCP tools correctly. Use when asked to work with ABAP objects, or when planning to call ABAP_MCP tools.

7ohnson Bundle

用 Blender 白模(greybox)给 AI 视频生成做机位、空间和切点的预演层——建房间、摆机位、导出参考视频喂进生成模型的 video 通道，再用规范化的 prompt 补齐表演与材质。当任务涉及「白模/greybox/previs/分镜预演」、要让同一场景的多个镜头保持空间一致、要精确控制硬切时刻、或要在花钱出片之前先验证机位和遮挡时使用。

aikong2024 Bundle

Translate a local text-based PDF through bounded JSON batches while preserving the source layout workflow. Use when the host can access local files, read and write UTF-8 files, run Python and shell commands, and the active chat model must perform the translation without provider APIs or model subprocesses.

aiwithhassan Bundle

Build an immersive scroll-scrubbed "fly through the world" landing page for any industry or brand using Higgsfield. As the visitor scrolls, a pre-rendered camera flies from outside each scene into its interior, then flows on to the next scene with NO cuts — one continuous connected flight (Emons-style isometric diorama world, or any art direction you pick). The skill interviews the user for the topic, the story beats/sections, and brand kit, then generates cohesive scenes + seamless camera clips with Higgsfield (or the user's own tools, via a prompt + conditioning-frame handoff) and wires a portable, framework-agnostic scroll-scrub engine. The video chain renders through Monid by default (Seedance 2.0, pay-per-clip USD — capability re-checked each build, see Step 4) with Higgsfield credits as the fallback biller. Use when the user wants a "3D world" / "browse-through-the-industry" hero, a scroll cinematic, a diorama landing, or to turn a business into a scrollable world.

arahim3 Bundle

Keep the Anthropic prompt cache warm by firing a tiny heartbeat only after N minutes of true session inactivity (any exchange resets the clock), so the next real turn reads the conversation at cached price / cached quota instead of a full uncached re-read. Use when the session may sit idle (training runs, CI, downloads, the user stepping away) longer than the cache TTL. Args - idle threshold in minutes (default 50), optional max hours (default 8), or "stop".

agent-nova-107 Skill

Finds and compares installed agent skills through the read-only skill-router MCP. Use when the user asks which skill to use or when a task is ambiguous, unfamiliar, multi-domain, or requires a multi-step workflow.

agustingonidev Bundle

Instala un LLM Wiki (knowledge base markdown interconectado, estilo Carpati/Obsidian) en cualquier proyecto y lo puebla con el contexto del negocio mediante una entrevista corta. Genera la carpeta del wiki con schema operativo, índice, bitácora y registro de fuentes, más el slash command (ingest | query | lint) y la configuración de Foam para VSCode; después entrevista al usuario sobre su negocio y escribe los documentos de contexto. Usá este skill cuando el usuario diga "instalá el cerebro", "quiero un wiki LLM", "configurá el sistema de memoria", "armá el brain", "montá el knowledge base", "cargá el contexto de mi negocio", o cuando pida un sistema de conocimiento acumulativo mantenido por Claude.

alexiaqaq Bundle

EIDE 工程构建工具，用于操作 EIDE（Embedded IDE）管理的嵌入式工程，支持 build/rebuild/clean/flash/reload/add-src-dir/check 子命令。通过 EIDE MCP Server（默认 http://127.0.0.1:8940/mcp）与 EIDE 扩展交互。当用户提到 EIDE、 Embedded IDE、编译 EIDE、EIDE 构建、EIDE 烧录、EIDE 重建时自动触发，也兼容 /eide 显式调用。即使用户只是说"用 EIDE 编译一下"或"EIDE 烧录"，只要上下文 涉及 EIDE 管理工程的构建或烧录就应触发此 skill。

amal-david Bundle

Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Silicon. Use when the user asks to run, port, convert, inspect, quantize, benchmark, or fix a model (LLM, VLM, audio/TTS/ASR, diffusion, SSM, MoE) for MLX, MLX-LM, MLX-VLM, MLX-Audio, or a Mac - e.g. "port this HF model to my Mac", "inspect this MLX app", "run Qwen on Apple Silicon", "convert these safetensors to MLX", "make this faster on my M3", "fix NaN in my MLX port", "speed up prefill / KV cache / speculative decoding", "publish an MLX checkpoint". Also use mid-task when a config.json, safetensors index, weight-shape or tokenizer mismatch, or Metal kernel question appears. Do not use for CUDA-only optimization, non-Apple hardware targets, or general PyTorch/ML questions with no MLX or Apple Silicon connection.

biosickqiuence Bundle

Convert one Chinese or English textbook PDF through PaddleOCR-VL and forced-OCR MinerU MCP, compare both outputs against original-page visuals, review scientific claims, and publish an auditable corrected Markdown edition plus a clean book-only edition. Use for end-to-end dual-OCR textbook digitization, OCR discrepancy review, errata production, chapter merging, figure normalization, or resuming a previously interrupted book run.

bytedtsinghua-sia Bundle

You are a PyTorch and CUDA expert. Accelerate the given PyTorch Model by creating a high-performance CUDA C++ extension, targeting the best possible performance with a minimum requirement of 5% faster than torch.compile baseline.

camilomartinezm Bundle

Convert scientific, academic, scanned, two-column, and math-heavy PDFs into provenance-rich Markdown with CUDA Docling, PyMuPDF4LLM, native geometry, GROBID, MinerU, span-preserving PP-StructureV3 region rescue, and benchmark-gated VLM evidence. Use when extraction quality matters, especially for interleaved columns, glued words, headers/footers, watermark fragments, broken section order, empty grids, missing sections, or corrupt equations, tables, figures, and captions. Treat every automated output as a quality-gated draft that requires direct native-PDF inspection and manual Markdown postprocessing before final use.

camjampng Bundle

Use when an agent is processing complex information, planning multi-step tasks, maintaining state, comparing alternatives, repeatedly manipulating information, or drafting text that shows signs of AI-generated writing. Apply whenever natural-language reasoning introduces linguistic overhead, repetition, ambiguity, or verbosity, or when output needs to read as human-written — factual, specific, and free of promotional filler, inflated significance, and formulaic phrasing.

cheshiremew Bundle

通过统一配置启动外部 Agent CLI，完整传递任务并调用一个指定 Skill；也用于按已配置路由委派写作等任务。

crowdstrike Skill

Set up the CrowdStrike Falcon MCP server. Checks for required credentials, runs mcp-server-setup.sh to detect the correct regional URL and write .mcp.json, then confirms successful installation.

cuizxuan Bundle

Maintain project working context for coding agents. Use when Codex starts work inside a project folder, initializes a new project, edits code, runs or deploys local/test services, debugs environment issues, reviews a repository, discovers stable project facts, or needs to create missing project-local agent instructions such as AGENTS.md and docs/*. This skill makes Codex find, read, create, and maintain project-local documentation for structure, direction, environments, pitfalls, commands, and operational notes.

djstarcom Bundle

Generate and iterate on images, videos, 3D meshes, textures, rigs and Roblox-ready assets through the Customuse MCP server (node-editor workflows, CustoCoins credits). Use when: "generate an image/video", "make a 3D model of this", "turn this image into a mesh", "make a game asset / prop / character reference", "retexture this model", "rig this mesh", "decimate / UV-unwrap this mesh", "make a Roblox accessory or clothing item", "how many Customuse credits do I have", "open my Customuse workflow", "extract assets from this image", or the user names Customuse, customuse.com, CustoCoins, the nodes editor, or a model hosted there (Nano Banana, FLUX, GPT Image, Kling, Seedance, Tripo, Meshy, Hunyuan 3D, Hi3D). NOT for: local/offline image or mesh editing (use file tools, Blender, ffmpeg), inspecting an already-downloaded asset, non-Customuse generation APIs, or Unreal/engine-side import work — Customuse ends at the produced asset URL.

dantespeak85 Bundle

Multi-model advisory board using OpenAI Codex CLI and Google Antigravity CLI (agy) to provide second opinions on code reviews, architecture plans, debugging, and general engineering decisions. Invoke when the user requests a "council" review, wants a second opinion from other AI models, asks for multi-model consensus, or says "ask the council". Also invoke proactively when making high-stakes architectural decisions or when a code review checkpoint is reached.

erpmcp Bundle

Fast ERP question clarification and live MCP Apps dashboard. Use when customers ask for new-listing counts, listing prices, ERP summary numbers, filters, or clickable drilldowns. Ask only result-changing questions first, return a verified summary through the bundled proxy, and never preload full records.

eximagent Bundle

Trade-intelligence CLI for AI agents — find real buyers, importers & distributors from customs trade data, then enrich and reach them. Contact enrichment, cold outreach with stage tracking, tariff + HS-code + corridor + country lookups, OFAC sanctions screening, per-company negotiation memory, company-profile extraction from any website, raw-markdown crawl, product/facility image extraction for multimodal hosts, bulk processing with auto-pick. Use whenever the user mentions eximagent/this CLI/the trade CLI, or asks: find buyers / importers / distributors, look up tariffs, what HS code, sanctions check, draft cold outreach, tell me about this company website, enrich N companies, crawl these websites, show/list/manage saved collections or corridors or templates or knowledge base, or any export/import/international-trade task. Invoke `eximagent <cmd>` for every step; auth via OAuth device flow or PAT. Also a hosted MCP connector needing no sandbox change.

oimiragieo Skill

Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Runs headless Gemini CLI via a Node script (no MCP). Triggers on "use Gemini", "ask Gemini", "analyze with Gemini", "large file", "sandbox", "brainstorm with Gemini".

raphaelmansuy Skill

Use this skill to create new Agent Skills for GitHub Copilot. It guides you through the process of setting up the directory structure and the SKILL.md file.