LLM 與 Agent

Automatically manage agent lifecycle, proposals, and registry.

Research accelerator portfolio companies using Firecrawl and Tavily MCPs. Generates structured CSV and markdown reports with systematic impact scoring. Optimized for token efficiency.

Implement image processing for PhotoVault using Sharp and streaming patterns. Use when working with photo uploads, thumbnail generation, EXIF handling, ZIP extraction, or optimizing images for web. Includes memory management for serverless and PhotoVault storage structure.

ChatBotプロジェクトの開発全般を支援するスキル。プロジェクト構造、コーディング規約、開発ワークフローに関する知識を提供します。ChatBotプロジェクトで作業する時、プロジェクト構造について質問された時、コーディング規約について質問された時、新しい機能を追加する時に使用してください。

Create a new git worktree for an agent to work in isolation. Use this when starting parallel implementation of a sub-issue to provide complete environment isolation with unique ports and database.

Retrieve APPLICATION patterns (architecture, procedures, conventions) from AgentDB skills table. Use BEFORE implementing to ensure consistency.

Proactively diagnose and fix code bugs. Use when errors occur, tests fail, or performance issues arise. Analyzes stack traces, identifies root causes, and provides working fixes.

Expert guide for Supabase Storage including bucket management, file operations, URL generation, and RLS policies. Use when working with file uploads/downloads, creating public or private buckets, generating signed URLs, implementing storage RLS policies, handling resumable uploads, image transformations, or any Supabase Storage-related tasks.

Create new Agent Skills for Claude Code. Use when user wants to create a skill, add a new capability, document a CLI workflow, or asks how skills work.

Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval.Use when implementing document ingestion pipelines, vector search with Qdrant, or context-awareretrieval. Covers chunking strategies, change detection, payload indexing, and context expansion.NOT when doing simple similarity search without production requirements.

Guide for creating and configuring custom sub-agents for Claude Code. Use this skill when you need to define specialized agents with dedicated system prompts, tool sets, and models to handle specific tasks.

Standards for writing CLAUDE.md and modular rules files (.claude/rules/) that maximize LLM execution efficiency. Use when creating or editing project instructions, defining conventions, or optimizing agent behavior for determinism and token efficiency. Focuses on eliminating ambiguity and producing consistent agent execution.

Use before committing staged changes when you need to verify all related documentation is current - systematically checks README, CLAUDE.md, CHANGELOG, API docs, package metadata, and cross-references rather than spot-checking only obvious files

Multi-agent development workflow system. Load when orchestrating development tasks, spawning subagents, or managing workflow phases.

LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.

Multi-agent development workflow system for structured task execution. Use when working with tasks in .tasks/ directory, when user invokes /task, /explore, /research, /spec, /build, /review, or /refactor commands, or when Claude needs to understand the task orchestration system. Provides workflow state management, sub-agent coordination, and session persistence.

Integrate external REST and GraphQL APIs with proper authentication (Bearer, Basic, OAuth), error handling, retry logic, and JSON schema validation. Use when making API calls, database queries, or integrating external services like Stripe, Twilio, AWS. Achieves 10-30x cost savings through direct execution vs LLM-based calls. Triggers on "API call", "REST API", "GraphQL", "external service", "API integration", "HTTP request".

強制執行「先讀後寫」規範，確保 Claude 在修改任何檔案前完整閱讀相關代碼。當需要修改檔案時自動使用。

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.

Claude 4.5 Opus 기반 프로젝트 전체 검수 스킬