LLM & Agents

Senior Frontend Code Reviewer with 12+ years JavaScript/TypeScript experience. Use when reviewing React/TypeScript code, checking code quality and style, verifying accessibility compliance, ensuring test coverage, or configuring linting tools (ESLint, Prettier).

Surgical metadata extractor for binary .pof files implementing the "Plan" phase tool. Extracts game logic metadata (hardpoints, subsystems, docking points) into structured JSON contracts for the generate-importer skill. Follows separation of concerns principle - does not parse 3D geometry. Provides structured JSON output with deterministic error handling for reliable agentic communication.

Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

Use when the user wants to install, update, or set up a Claude Code plugin

Meta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template generation, prompt optimization, or programmatic prompt composition.

Create Claude Desktop skills from descriptions, SOPs, or existing agents. Three modes - create from scratch, convert SOPs to skills, or migrate agents to skill format. Outputs ready-to-deploy .zip packages.

Go testing best practices including table-driven tests, race detection, test coverage, and mocking strategies. Use when writing or reviewing Go tests.

Given a human certification or license (e.g. PL-300, SAP B1, Azure AI Engineer), create a production-ready agent skill profile and certification ladder, including skills.yaml entries, agent YAML, and skills documentation, using the anthropics/skills SKILL.md conventions.

Systematic debugging workflow for CircleTel - analyzes errors, identifies root causes, proposes fixes, and validates solutions with tests

Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission rules aligned with official documentation.

Cross-agent learning with cm (cass-memory). Use before starting non-trivial tasks, when looking for patterns from past work, when the user mentions "cm", "memory", "learned rules", or "what do we know about".

영어 ↔ 한국어 번역 스킬. 학술 논문, 기술 문서 번역 시 사용. Ollama gpt-oss:20b 모델 활용. 원문 아래 번역문 병렬 표시.

Use when executing implementation plans with independent tasks. Dispatches subagents per task with two-stage review (spec then quality).

Compare and evaluate embedding models for semantic search

Generates well-structured Agent Skill documents following Claude Code best practices. Use when asked to create new Agent Skills, draft SKILL.md files, or design skill architectures.

Spec-Driven Development (SDD) agent for maintaining synchronized specifications, code, and documentation. Core principle: "1 Todo = 1 Commit = 1 Spec Update". Use this skill when: - Starting a new feature or task that needs specification - Implementing code based on existing specifications - Validating that code matches specifications - Updating CHANGELOG.md with changes - Managing PRD/specification documents - Ensuring traceability between requirements and implementation Triggers: "spec", "specification", "PRD", "requirements", "SDD", "spec-driven"

Step-by-step procedural guidance for executing the /plan command workflow. Covers Phase 0 (Research), Phase 1 (Design), and Phase 2 (Validation) for implementation planning with constitutional compliance.This skill provides step-by-step procedural guidance for tasks handled bythe planning-agent agent. Use when you need to understand the workflow orexecute tasks that planning-agent would typically handle.Triggered by: [TODO: Add trigger phrases]

코드베이스를 분석하여 CLAUDE.md 초기화. 프로젝트 문서화, 아키텍처 개요, 코딩 표준 생성

LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.

Use when getting started with llmemory document storage and search - covers installation, initialization, adding documents, vector search, hybrid search, semantic search, BM25 full-text search, document management, and building RAG systems with multi-tenant support