LLM & Agents

Fast code operations using Serena MCP (1-3s) for symbol search, memory read/write, and basic code editing in LoRAIro project

Multi-agent collaboration. Use when working with other Claude Code sessions, coordinating work, or needing to communicate with teammates.

Hybrid cognitive architecture combining Darwinian evolution with Gödel Machine self-improvement for maximum reasoning power. Use for: complex coding problems, multi-step reasoning, architecture design, debugging hard problems, any task requiring exhaustive solution exploration with formal verification. Activates when user needs "powerful reasoning", "best possible solution", "explore all options", or faces problems where first-attempt solutions typically fail.

Weaves custom Skills for Claude following official best practices including proper structure, metadata, progressive disclosure, and security guidelines. Use when creating new skills, building custom workflows, or when user mentions skill creation, skill development, custom skill authoring, weaving skills, or crafting skills.

Manage requirement traceability - generate matrix, check coverage, find orphans, trace requirements

Synchronize skills between project repository and user's Claude Code skills directory (~/.claude/skills/). Bidirectional sync with conflict detection, dry-run preview, and selective sync. Activated when users mention "sync skill", "skill sync", "update skills", or need to copy skills between locations.

Creates ergonomic slash commands (/command) that provide fast, unambiguous access to micro-skills, cascades, and agents. Enhanced with auto-discovery, intelligent routing, parameter validation, and command chaining. Generates comprehensive command catalogs for all installed skills with multi-model integration.

Use this skill in the scenario of writing git commit messages.

Migrate and sync vector database collections across environments

@effect/ai integration patterns for categorical AI composition, typed error handling, and production prompt pipelines. Use when building AI applications with Effect-TS, composing LLM calls with typed errors, creating tool-augmented AI systems, or integrating multiple AI providers.

Convert Claude Code slash commands to OpenCode commands format. Use when migrating from Claude Code to OpenCode or when you have existing slash command definitions to port.

Inter-agent communication for multi-agent workflows. Use when multiple agents need to coordinate, share information, or reserve resources.

ユーザーの責任範囲定義から、Agentのマークダウンファイルを生成する。エージェント作成時、プラグイン要素生成時、またはユーザーがエージェント定義、責任範囲、Agent生成、エージェントドキュメントに言及した際に使用する。

AI agent with tools (search, calculator) using LangGraph and AI SDK.

Use this skill to create new Agent Skills for GitHub Copilot. It guides you through the process of setting up the directory structure and the SKILL.md file.

Automated feature verification using Playwright MCP and Claude Code CLI. Use when verifying UI features, running acceptance tests, checking feature completion status, or validating features.json verification steps. Integrates with agentic-development workflow for progress tracking.

This skill should be used when the user asks "refactor code", "improve code quality", "use refactor plugin", "run /refactor", or needs guidance on automated iterative code refactoring with test coverage, architecture review, and clean code improvements.

Guides creation of effective Agent Skills with proper structure and validation.Use when users want to create a new skill, update an existing skill, or needguidance on skill design patterns, SKILL.md format, or verify.py implementation.NOT when just using existing skills (use those skills directly).

Automatically applies when adding logging and observability. Ensures structured logging, OpenTelemetry tracing, LLM-specific metrics (tokens, cost, latency), and proper log correlation.

Store ClickHouse Cloud credentials in Doppler + 1Password for gapless-crypto-clickhouse. Use when setting up new services, rotating credentials, or backing up authentication material. Covers API keys, connection details, and database password storage.