AI & ML

dozerojeong Skill

코드 리뷰 단계부터 PR 생성까지 아우르는 포괄적인 Git 워크플로우. 전문적인 에이전트를 활용하여 품질 보증, 테스트 및 배포 준비 상태를 점검합니다. 이 워크플로우는 Conventional Commits, 자동화된 테스트 및 체계적인 PR 생성을 포함한 최신 Git 모범 사례를 구현합니다.

dozerojeong Skill

당신은 클린 코드 원칙, SOLID 디자인 패턴 및 현대적인 소프트웨어 엔지니어링 모범 사례를 전문으로 하는 코드 리팩토링 전문가입니다. 제공된 코드를 분석하고 리팩토링하여 품질, 유지보수성 및 성능을 향상시킵니다.

dozerojeong Skill

Django 3.x 모범 사례, 확장 가능한 아키텍처 및 최신 웹 애플리케이션 개발을 전문으로 하는 전문가입니다.

dozerojeong Skill

생성된 스킬이 프로젝트 표준을 준수하는지 검증하는 스킬입니다. 스킬의 구조, 필수 파일, 및 내용의 적절성을 확인합니다.

dozerojeong Skill

코드 리뷰 전문가입니다. 품질, 보안, 그리고 프로젝트별 규칙(ANTIGRAVITY.md) 준수 여부를 검토합니다.

dozerojeong Skill

코드를 만지기 전, 다단계 작업에 대한 명세나 요구사항이 있을 때 사용합니다.

dozerojeong Skill

Python (Django/FastAPI) 프로젝트에서 Datadog을 효과적으로 활용하기 위한 가이드입니다. 설정, 로깅, 트레이싱, 메트릭 수집 방법을 다룹니다.

dozerojeong Skill

새로운 에이전트 스킬을 생성하는 스킬입니다. 반복적인 작업을 자동화하거나 특정 도메인 지식을 에이전트에게 주입하고 싶을 때 사용하세요.

dozerojeong Skill

레거시 코드베이스를 안전하게 리팩토링하고, 구형 프레임워크를 마이그레이션하며, 점진적인 현대화를 수행하는 전문가입니다.

dozerojeong Skill

코드베이스를 분석하고 아키텍처를 파악하며, 발견한 내용을 구조화된 형식으로 문서화하는 포괄적인 스킬입니다.

barispe Skill

Coordinates QA-focused agent roles, manages test phases (scouting, strategy, implementation, review, reporting), and drives convergence toward a concrete test strategy, implemented tests, and final report. Use when multiple QA roles or phases need orchestration.

biancalana Skill

Model software around the business domain using bounded contexts, aggregates, and ubiquitous language. Use when the user mentions "domain modeling", "bounded context", "aggregate root", "ubiquitous language", or "anti-corruption layer". Covers entities vs value objects, domain events, and context mapping strategies. For architecture layers, see clean-architecture. For complexity, see software-design-philosophy.

biancalana Bundle

Manage Confluence pages via Atlassian MCP — search, create, update, and comment with proper Markdown formatting. Auto-detects workspace configuration. Use when user says "update Confluence", "create a Confluence page", "find that page in Confluence", "search Confluence", or "add a comment on Confluence". Do NOT use for Jira operations (use jira-assistant).

claudiawong522 Skill

persistent-agent-orchestration

grandamenium Bundle

Convert MCP server tools into programmatically callable scripts. Use when the user wants to call MCP tools from scripts, automate MCP tool calls, chain MCP tools together, or bypass the AI agent for direct tool execution.

cheeyutan Bundle

Browser automation and testing via Playwright MCP server. Use when testing web apps, verifying UI changes, checking console errors, filling forms, taking screenshots, or any browser-based interaction. Triggers on "test the app", "check the UI", "open the browser", "take a screenshot", "click the button", "fill the form", "check for console errors".

fivetechsoft Bundle

Performs deep analysis of code repositories like DeepWiki. Use it to examine project structure, identify technologies, analyze architecture, detect design patterns, evaluate code quality, and generate exhaustive technical documentation. Supports three operation modes - RAG (contextual analysis), Deep Research (multi-turn investigation), and Simple Chat (direct technical responses). Ideal for understanding unknown codebases, performing technical due diligence, or documenting existing projects.

nmitchem Skill

Helps draft and send emails using your preferred tone.

oen-tech Bundle

Oen Payment (應援金流) integration assistant. Helps developers integrate payment checkout, subscriptions, refunds, and transaction queries via the Oen Payment REST API and MCP server. Use when the user mentions "oen payment", "應援金流", "oen 金流", payment checkout with oen, oen subscription, oen refund, oen transaction, or wants to set up the oen-payment MCP server. Also trigger when code imports or references oen-payment, payment-api.oen.tw, or @OEN-Tech/oen-payment-mcp-server.

cblain100-prog Bundle

Security audit for MCP servers before installation. Use when someone wants to install a new MCP, audit a GitHub repo for an MCP server, or check if an MCP is safe. Triggers on "install MCP", "add MCP", "audit MCP", "is this MCP safe".

myfro9 Bundle

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

kimdoubleb Bundle

Use when designing k6 load profiles, choosing executors, configuring VU patterns, setting thresholds, or planning test scenarios. Use when the user asks about stress test, spike test, soak test, breakpoint test, load model, executor selection, or pass/fail criteria.

tanakaryotadayo-wq Bundle

MCP サーバーの設計・実装・統合・運用・進化を包括するスキル。「MCPサーバー作って」「MCPツール追加して」「MCP接続設定して」「MCPサーバーのレビュー」「新しいMCPサーバー設計」「MCP レジストリ更新」と言われたら必ず使う。FastMCP (Python) + Granian + uv + structlog の Ryota スタック固定。マルチクライアント接続（Antigravity/Codex/ChatGPT/Gemini CLI/OpenClaw/Aladdin/n8n）と AI ロール別アクセス制御をサポート。

paulieb14 Skill

This skill should be used when the user asks to search for subgraphs, query blockchain data, find DeFi/NFT/DAO data on The Graph, look up Uniswap/Aave/Compound/ENS or other protocol data, get a subgraph schema, run a GraphQL query against a subgraph, or check query volumes. Provides guidance on using The Graph's Subgraph MCP tools.

duffycoder Bundle

Create and manage social media content for Chinese platforms including WeChat Official Account (微信公众号), Xiaohongshu/RED (小红书), Sohu (搜狐号), and Baijiahao (百家号). Covers topic research (选题搜集), copywriting (文案生成), and cover image generation (配图生成). Integrates with SophNet RAG knowledge base and image generation. Use when user mentions 选题, 文案, 公众号, 小红书, 搜狐号, 百家号, 封面图, 攻略图, 内容策划, or 热点选题.

duffycoder Bundle

Use when a user requests SophNet image editing (image-to-image), including multi-image editing tasks (composition, style transfer, region swap) where all uploaded image paths must be resolved from Media Understanding logs (usually media/inbound/images/*) and passed in order to model Qwen-Image-Edit-2509.

duffycoder Bundle

Search for similar faces in image directories using face detection and embedding comparison. Use when users want to find photos containing a specific person, search for similar faces across image collections, or identify matching faces in photo libraries. Supports automatic path extraction from logs (patterns like "Resolved relative path") and configurable similarity thresholds.

duffycoder Bundle

Use when a user requests Sophnet text-to-image generation, needs model selection across Z-Image-Turbo/Qwen-Image/Qwen-Image-Plus, or reports polling/output issues such as missing IMAGE_URL or PREVIEW_PATH.

biancalana Skill

Create Agent Command

animesh303 Skill

Fetch open JIRA tickets, user picks one; generate TDD with inline Mermaid in docs/jira/<KEY>/; update JIRA (comment with design summary, In Progress, assign). Use when starting from a JIRA ticket or generating a technical design. Atlassian MCP.

animesh303 Bundle

Fetch open JIRA tickets, user picks one; generate TDD with inline Mermaid in docs/jira/<KEY>/; update JIRA (comment with design summary, In Progress, assign). Use when starting from a JIRA ticket or generating a technical design. Atlassian MCP.

jlouage Bundle

This skill should be used when the user asks to generate a video, create a video clip, make a video from a prompt, animate an image, extend an existing video, or work with Google Veo. Supports Veo 2, Veo 3, and Veo 3.1 models. Trigger phrases: generate a video, create a video, make a clip, animate this image, extend this video, video of, /veo.

yiming Skill

從場地訂單的桌次安排產生桌牌/座位卡的圖像生成 prompt。當使用者說「產生桌牌」「產生座位卡」「generate card prompt」時觸發。

yiming Skill

從場地訂單的桌次安排產生桌牌/座位卡的圖像生成 prompt。當使用者說「產生桌牌」「generate card」時觸發。

yiming Skill

Generate AI image generation prompts for banquet table name cards. Use when asked to create table cards, card prompts, or seating card images for venue orders.

biancalana Skill

Read research outline, launch independent agent for each item for deep research. Disable task output.