LLM 與 Agent

정보 수집이 필요할 때 검색 에이전트 활용 가이드. 코드 탐색, 레퍼런스, 웹검색

Deep Work and Essentialism-guided planning, triage, and task management.Channels Cal Newport and Greg McKeown for focused, intentional choices.USE WHEN user says 'plan my day', 'daily planning', 'triage tasks','weekly review', 'shutdown', 'end of day', 'quarterly review','prioritize', 'what should I work on', 'process inbox', 'sync todoist','spawn agent', 'run AI task', 'morning routine', 'plan my week'.

Deterministic team development workflow for Claude Code. Enforces a mandatory sequence of phases (Setup → Brainstorm → Plan → Execute → Quality Check → Ship) with Linear integration, TDD requirements, and quality gates. Activates when working on issues/tasks, when user mentions Linear issues (e.g., ENG-123), when starting development work, or when preparing to ship code. Commands: /team:task, /team:quality-check, /team:ship.

Meta-agent that analyzes tasks and recommends optimal skill combinations with Feynman-style explanations. USE WHEN feeling overwhelmed by 51+ skills, uncertain which skills to apply, need guidance on skill orchestration, or want to understand skill synergies. This is a READ-ONLY analyzer - recommends but never modifies code.

Claude Code Hook system entry point. Guides you to the right skill based on your needs.

Guides correct usage of @j0kz/mcp-agents standardization and automation scripts including version.json single source of truth, test count automation, URL casing rules, and critical workflow pattern...

Telegram automation assistant using telegram-mcp. Use when users want to:(1) Get a digest of unread Telegram messages(2) Analyze their writing style from channel posts(3) Draft and publish posts to Telegram channels(4) Search and reply to messages across chatsTriggers: "telegram digest", "unread messages", "morning summary","post to channel", "draft telegram post", "analyze writing style","extract style from channel", "telegram workflow"

End-to-end agent development process. Use when coordinating work, dispatching agents, or reviewing PRs.

Create and configure VoltAgent AI agents with tools, memory, hooks, and sub-agents. Use when building AI agents, adding agent tools, configuring VoltAgent memory, creating multi-agent workflows, or debugging VoltAgent integrations.

Skill manager for Claude Code. Use when users want to list, search, install, update, remove, or create skills. Activated by requests like "install a skill", "what skills do I have", "find skills for X", "create a new skill", or "update my skills".

Automatically logs every user prompt and AI output to datewise Notion pages. Use this skill to create a comprehensive archive of all AI interactions, track research progress, maintain conversation history, and build a searchable knowledge base. The skill creates one JSON file per day with all interactions and can export them to Notion in a structured format.

Complete knowledge domain for Cloudflare R2 - S3-compatible object storage on Cloudflare's edge network.Use when: creating R2 buckets, uploading files to R2, downloading objects, configuring R2 bindings,setting up CORS, generating presigned URLs, multipart uploads, storing images/assets, managing objectmetadata, or encountering "R2_ERROR", CORS errors, presigned URL failures, multipart upload issues,or storage quota errors.Keywords: r2, r2 storage, cloudflare r2, r2 bucket, r2 upload, r2 download, r2 binding, object storage,s3 compatible, r2 cors, presigned urls, multipart upload, r2 api, r2 workers, file upload, asset storage,R2_ERROR, R2Bucket, r2 metadata, custom metadata, http metadata, content-type, cache-control,aws4fetch, s3 client, bulk delete, r2 list, storage class

Guide for authoring output-styles that transform Claude's behavior and personality. Use when creating, writing, designing, building, reviewing, or improving output-styles, persona modes, or behavior modifications. Helps with style files, keep-coding-instructions decisions, persona design, and choosing between output-styles, agents, and skills. Expert in style best practices.

Generate CLAUDE.md project files. Execution contracts that eliminate ambiguity.

E2E testing skill for Pawel Lipowczan portfolio project (Playwright + React/Vite). Use when user wants to create new E2E tests, debug flaky tests, extend test coverage, verify test completeness for features, or run/interpret test results. Covers navigation, forms, blog, SEO, accessibility (WCAG 2.1 AA), responsiveness. References docs/portfolio/testing/{README.md,TESTING_QUICKSTART.md}. Complements portfolio-code-review skill.

Complete 5-agent workflow for transforming ideas into validated software

This skill should be used when building backend applications with Encore.ts, a TypeScript backend framework. Use this skill for creating APIs, managing databases, implementing authentication, handling async messaging (Pub/Sub), managing storage, scheduling tasks (cron jobs), implementing middleware, configuring CORS, managing secrets, and structuring backend services. This skill is triggered when users need to create or modify backend services, endpoints, databases, authentication systems, or any other backend infrastructure using Encore.ts.

Python testing best practices with pytest. Covers unit, integration, async tests, mocking, fixtures.Triggers: "напиши тесты", "write tests", "add tests", "test coverage", "pytest"

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently