Comprehensive code review orchestrator. Runs multiple focused review analyses (bugs, types, maintainability, simplicity, coverage, docs, AGENTS.md) and consolidates findings. Use before PR or after implementation. Triggers: review, code review, review my changes, PR review.

Git-native session lifecycle management for software development. Use when starting/resuming coding sessions, creating checkpoints, tracking objectives and blockers, generating handoffs between sessions, or needing context preservation across work sessions. Provides intelligent onboarding for AI coding agents by loading comprehensive project context.

Exa.ai deep research and answer generation with citations. Use when building research automation, implementing Answer API for Q&A with sources, creating research reports, or using deep search with summaries. Triggers on: Exa Answer, answer endpoint, exa.answer, deep search, research API, Exa Research, async research, research report, citation extraction, summarization with sources, fact verification, streaming answers, research tasks.

Prometheus, Grafana, logging, alerting, and data pipeline observability

SQL 쿼리 최적화, 인덱스 전략 및 EXPLAIN 분석을 마스터하여 데이터베이스 성능을 획기적으로 향상시키고 느린 쿼리를 제거합니다. 느린 쿼리 디버깅, 데이터베이스 스키마 설계 또는 애플리케이션 성능 최적화 시 사용하세요.

Build voice-enabled AI applications with speech recognition, text-to-speech, and voice-based interactions. Supports multiple voice providers and real-time processing. Use when creating voice assistants, voice-controlled applications, audio interfaces, or hands-free AI systems.

This skill automates splitting large changes into logical commits using git-sequential-stage to stage hunks and prepare commits before PRs.

Storybook 8 for React component documentation and testing. Use for creating stories, documenting components with Controls/Actions, visual testing, and MDX documentation. Triggers on requests for Storybook stories, component documentation, visual testing, or interactive component demos.

Collaboration workflows for team-based Git development. Covers pull request workflows, merge vs rebase strategies, conflict resolution, code review practices, and branch protection. Helps AI agents follow team conventions and collaborate effectively.

This skill posts text, images, videos, and long-form articles to X using real Chrome, bypassing anti-automation for reliable publishing.

This skill helps you add focused backend tests to verify invariants, endpoint behavior, and retries across services.

Plan and track projects with timelines, resources, and risk management

This skill helps you create and maintain Architecture Decision Records in Confluence to document architectural decisions and design choices.

This skill drafts GDPR-compliant privacy policies, terms, and DPA documents, ensuring regulatory coverage and clear language for your technology business.

Access and interact with Large Language Models from the command line using Simon Willison's llm CLI tool. Supports OpenAI, Anthropic, Gemini, Llama, and dozens of other models via plugins. Features include chat sessions, embeddings, structured data extraction with schemas, prompt templates, conversation logging, and tool use. This skill is triggered when the user says things like "run a prompt with llm", "use the llm command", "call an LLM from the command line", "set up llm API keys", "install llm plugins", "create embeddings", or "extract structured data from text".

Build scalable lists with keyed rows and per-item updates

Mind mapping and exploration state tracking for workshops. Use to maintain awareness of explored vs uncharted territory, implement backtracking, and ensure comprehensive coverage or documented gaps.

Master machine learning, data engineering, AI engineering, MLOps, and prompt engineering. Build intelligent systems from data pipelines to production AI applications with LLMs, agents, and modern frameworks.

This skill helps you implement secure development practices aligned with OWASP Top 10, testing, and compliance to protect systems.

Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective.

Execute transaction builds and submits. Manual invoke only—requires explicit confirmation before submit.