Docker

byterover

JunSuzuki1973

ByteRover CLI for context engineering - manage project knowledge, decisions, and patterns with AI coding agents.

next-best-practices

Jackiexiao

（中文）Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

nextjs-best-practices

jcastillotx

Next.js App Router development standards. Triggers when working with Next.js applications, Server Components, Server Actions, or App Router patterns.

dockerignore-generator

ehtbanton

Generate .dockerignore files to exclude unnecessary files from Docker builds. Triggers on "create dockerignore", "generate docker ignore", "dockerignore for", "docker exclude files".

media-understand

InfQuest

使用 AI 理解和分析多媒体内容（图片、视频、音频）。Use when user wants to 理解图片, 分析视频, 音频转文字, 视频问答, understand media, analyze video, transcribe audio, describe image, what is in this video/image/audio.

performance

Dsantiagomj

Web performance optimization and Core Web Vitals. Covers LCP, FID, CLS, code splitting, lazy loading, caching strategies, image optimization, and performance monitoring. Trigger: When optimizing performance, when improving Core Web Vitals, when implementing code splitting, when optimizing images, when setting up caching.

shopify-liquid-templates

skomskiy

Liquid template best practices for Shopify themes - snippets, logic, image handling, and SVG usage. Use when writing or modifying Liquid templates in Shopify themes.

ai-image-generation

Jackiexiao

"Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image"

learn

Nomik94

Use when: 문제 해결 후, 디버깅 성공, 패턴 발견, 기억해둘 것, 나중에 또 나올 수 있는, 해결했다, 찾았다, root cause 발견. NOT for: 일반 지식, 공식 문서에 있는 내용, 단순 오타.

media-processing

brixtonpham

"Video/audio/image processing with FFmpeg and ImageMagick. Tools: FFmpeg (video/audio), ImageMagick (images). Capabilities: format conversion, encoding (H.264/H.265/VP9/AV1), streaming (HLS/DASH), filters, effects, thumbnails, watermarks, batch processing, hardware acceleration (NVENC/QSV). Actions: convert, encode, resize, crop, compress, extract, merge, stream, transcode media. Keywords: FFmpeg, ImageMagick, video encoding, audio extraction, image resize, thumbnail, watermark, HLS, DASH, H.264, H.265, VP9, AV1, codec, bitrate, framerate, resolution, aspect ratio, filter, overlay, concat, trim, fade, batch processing. Use when: converting video/audio formats, encoding with specific codecs, generating thumbnails, creating streaming manifests, extracting audio from video, batch processing images, adding watermarks, optimizing file sizes."

fastapi

Nomik94

FastAPI 프로젝트 고유 설정 및 패턴 레퍼런스. Use when: 프로젝트 구조 잡기, 폴더 구조, 디렉토리 구조, 초기 세팅, 새 프로젝트 시작, 파일 분리, 파일이 너무 커, 폴더로 변환, 파일 비대, 모듈 분리, 패키지 분리, DI 패턴 선택, 의존성 주입, Depends vs Container vs Dishka, Ruff 설정, mypy 설정, 린터 세팅, 포맷터 세팅, pre-commit 설정, import-linter, App Factory, create_app, lifespan, pydantic-settings, 환경변수 설정, config 구조, 레이어 분리, controllers/service/repository 구조, 도메인 레이어 도입 기준. NOT for: 단순 FastAPI 문법 질문 (Claude가 이미 앎), 일반적인 Ruff/mypy 사용법.

deepworkplan-addon-devcontainer

DailybotHQ

Optional DeepWorkPlan addon that gives a repository a reproducible dev container through devcontainer-kit (the dck command, DailybotHQ/devcontainer-kit pinned at v0.1.4, interface 1) - a vendor-neutral thin integrator that detects the kit with dck doctor --json, offers dck init (which reconciles an existing layout and never clobbers it), maps the detected stack to a base-image flavour and the opt-in layers (agents through coding-agents-kit, the editor, Dailybot only when that addon asks), optionally registers the container as a Herdr machine, and validates the result. Opt-in, never required, never a conformance gate.

next-best-practices

Jackiexiao

（中文）Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

component-builder

atovk

生成 UI 组件代码，支持 React、Vue、Svelte 等框架

dupe

dupe-com

Uses dupe.com APIs in order to find similar products for the product found in the input URL given by the user.

markdown-syntax-fundamentals

arielperez82

Use when writing or editing markdown files. Covers headings, text formatting, lists, links, images, code blocks, and blockquotes.

slack-gif-creator

TheWatcher01

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

obtain-screenshot-android

linmx0130

Capture screenshots from Android devices using ADB (Android Debug Bridge). Use when Kimi needs to obtain screenshots from connected Android devices, emulators, or physical devices for debugging, testing, documentation, or visual verification purposes.

context-android

ShotaIuchi

Android development context. Apply when working with Android modules, .kt files under android/, build.gradle.kts with Hilt/Compose dependencies, ViewModel, Jetpack Compose, MVVM/UDF patterns.

T2I-Studio-Premium

CatfishW

🎨 Generate stunning, state-of-the-art AI images directly from your terminal or Agent. Powered by Z-Image-Turbo.

docker-compose

DonArtkins

"Docker Compose v2 for the Griot local topology (api + sqlserver + postgres + redis + mcp): service definitions, volumes, networks, health checks, port isolation (gtp-*)."

locate-anything

8-Sync-Dev

Fast open-vocabulary VISUAL GROUNDING via NVIDIA LocateAnything-3B (run through the mudler/locate-anything.cpp ggml port, no Python). Turns an image + a text description into labeled bounding boxes + click-center coordinates. Use when you need EXACT PIXEL COORDINATES from an image — GUI element grounding (to click a button/field precisely), OCR/text localization, open-set object detection — rather than a prose description. Invoked as 8sync locate <image> "<target>". Complements a native VLM / zai-vision (which describe) and the browser tool (which clicks).

MarketPlace - Full-Stack E-Commerce Platform

Ashutosh5hukla

baoyu-compress-image

siatwangmin

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.