LLM & Agents

Multi-agent debate with 3-phase workflow (Individual → Discussion → Synthesis)

Git and GitHub workflow automation skills for OpenCode agents

Testing conventions, test runner configurations, coverage requirements, and failure interpretation for the Klassenzeit monorepo.

Use this skill whenever important information is learned during a task or when the user explicitly asks to store something. Use when users ask to remember. Triggers on "remember this", "update memory", "share" or any persistent storage request.

Retrieval-Augmented Generation (RAG) for grounding LLM responses with external knowledge. Covers document chunking, embeddings, vector stores (pandas, ChromaDB), similarity search, and conversational RAG pipelines.

Agent-optimized Test-Driven Development workflow based on research from Codex, CodeT, Self-Debugging, TICoder, and SWE-bench Verified. Use when fixing bugs (generate fail-to-pass test first), implementing new features (acceptance tests first), or when user requests "TDD", "test-first", or "test-driven" approach. Provides high-confidence code changes with comprehensive test coverage.

Personal assistant for daily routines, task management, and productivity

Vitest testing conventions and patterns for @j0kz/mcp-agents including test organization, naming, assertion patterns, mocking strategies, and coverage targets (75%). Use when writing tests, organiz...

Asistente especializado en investigación académica, redacción científica, ACD, metodología cualitativa y análisis de datos con prevención de plagio

PROACTIVELY USED when reviewing a PR, branch, or Jira story. Claude-only PR reviewer with 6 specialized reviewers - no external LLM dependencies.

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

Validates LangGraph implementations for correctness, consistency, and integration readiness. Use this skill when implementing, reviewing, or debugging any LangGraph code - agents, nodes, subgraphs, state schemas, or graph compositions. Prevents common LangGraph failures including orphaned nodes, state key mismatches, broken conditional edges, and integration incompatibilities. Triggers on LangGraph development tasks, code reviews, or when debugging graph execution issues.

Emerging technologies (prompt engineering, AI agents, red teaming) and leadership roles (product manager, engineering manager, DevRel).

Manage game assets with Kenney-ONLY approach. Search 36,000+ Kenney CC0 assets. If asset not found, ask user to find/generate manually. Ensure style consistency with flat/vector Kenney aesthetic. Auto-triggers on asset requests.

Coordinator workflow for orchestrating dockeragents through fix-review-iterate-present loop. Use when delegating any task that produces code changes. Ensures agents achieve 10/10 quality before presenting to human.

Create custom Claude Code slash commands with `/command-name` syntax

A TypeScript-first skill for generating Office documents (DOCX, XLSX, PDF) that works everywhere - Claude Code CLI, Cloudflare Workers, and browsers. Simpler and more portable than Anthropic's officia

Writes a comprehensive, feature-by-feature product description with specs and benefits that can serve as a universal prompt for downstream content generation.

Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents

Creates, analyzes, updates, and improves Claude Code agent skills including YAML frontmatter, allowed-tools field, progressive disclosure, and skill authoring workflows. Use when user asks how skills work, what agent skills are, explaining skill concepts, understanding SKILL.md structure, describing .md files organization, skill authoring process, asked to create a new skill, evaluate existing skills for improvements, optimize skills for AI/Claude effectiveness, suggest converting current logic into a skill, update outdated skill information, or when user mentions skill validation, best practices, supporting files, skill security, API integration, or technical architecture.