LLM & Agents

Expert Git workflow management for Claude Code sessions with branch naming conventions, push retry logic, conflict resolution, and PR automation specifically designed for AI-assisted development workflows.

Use this skill when the user needs help managing configuration storage in the Config Hive including secrets, D&R rules, YARA rules, lookups, and cloud sensors.

Enforce elite code quality standards for F3 Workout Builder. Use when writing code, reviewing changes, fixing bugs, or creating new features. Keywords: code quality, TypeScript, testing, coverage, lint, types.

Intelligent, conversational interface for managing Linear workspace operations (issues, projects, teams, reporting)

Guide for creating Agent Skills with progressive disclosure, SKILL.md structure, and best practices

This skill should be used when generating detailed experimental procedures from LA-Bench format JSONL files. It orchestrates multiple subagents to parse input data, fetch reference materials, generate procedures, validate outputs, refine results, and produce final formatted outputs. Triggered by requests to process LA-Bench data or generate experimental protocols from data/public_test.jsonl or data/private_test_input.jsonl files.

Guide for authoring, creating, writing, building, reviewing, or improving slash commands that delegate to agents or skills. Use when designing /commands for user shortcuts, fixing existing commands, or learning command best practices. Helps design simple command files, choose delegation targets, handle arguments, and decide when to use commands vs skills. Also triggers when asking how to create commands, whether to use a command vs skill, or understanding command patterns. Expert in command patterns, best practices, and keeping commands focused.

Use when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests. Accepts green-mirage-audit reports, general instructions, or can run tests and fix failures automatically. Lighter-weight than implement-feature, focused on test remediation.

Use PROACTIVELY when creating releases after PR merges to main, or when user asks about versioning strategy. Automated git tagging agent that analyzes repository state, parses conventional commits, calculates semantic versions, and creates annotated git tags with GitHub releases. Supports monorepo namespaced tags with @ separator convention. Not for changelog generation or pre-release/alpha versioning.

Spawn a Claude worker to handle a GitHub issue. Fetches issue details, creates a feature branch, and works autonomously. Use when you want to delegate an issue to a worker.

Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.

Performance optimization patterns for Mem0 memory operations including query optimization, caching strategies, embedding efficiency, database tuning, batch operations, and cost reduction for both Platform and OSS deployments. Use when optimizing memory performance, reducing costs, improving query speed, implementing caching, tuning database performance, analyzing bottlenecks, or when user mentions memory optimization, performance tuning, cost reduction, slow queries, caching, or Mem0 optimization.

RAG (Retrieval Augmented Generation) implementation patterns including document chunking, embedding generation, vector database integration, semantic search, and RAG pipelines. Use when building RAG systems, implementing semantic search, creating knowledge bases, or when user mentions RAG, embeddings, vector database, retrieval, document chunking, or knowledge retrieval.

테스트 생성 전체 워크플로우. "00 테스트 만들어줘", "새 테스트 추가해줘" 요청 시 자동 실행. 2개 Agent 순차 호출로 2중 검증.

Expertise for using OpenCode (an open-source AI coding agent) and building client applications that interact with the OpenCode HTTP server. Use this skill when the user asks about OpenCode features, how to use it, or how to build tools/clients that integrate with the OpenCode server API.

Plan, orchestrate, and validate deep research for nonfiction books. Use when an author has completed book architecture and needs to fill research gaps before outlining chapters. Triggers include requests to plan research, generate research prompts, validate research quality, or prepare for drafting. This skill does everything around deep research—planning, prompting, validating, synthesizing—but the actual research execution happens externally via Claude and Gemini deep research. Requires upstream documents from book-architect (Research Gaps Document, Master Architecture Document, Section Blueprints) and book-ideation (Book Concept Document).

Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.

Skill describing modern iOS testing patterns: Swift Testing vs XCTest, XCUITest best practices, and OS 4.1 expectations for coverage and flakiness.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Guide for creating new Claude skills. Use this when creating a new skill, updating existing skills, or learning best practices for skill development.