LLM & Agents

三点セットログを出力する

Remove a git worktree after agent completes work. Use this after merging a sub-issue PR or on failure to cleanup all associated resources including Docker containers, volumes, and git metadata.

Spawn a Claude worker to address PR feedback, fix CI failures, or continue work on a pull request. Use when a PR needs updates based on review comments or failing checks.

指定したプラグインを無効化する。「プラグインを無効化」「〇〇をオフにして」「〇〇を無効にして」「プラグインを無効に」「〇〇を止めて」「プラグインをオフに」「〇〇を無効化して」などで起動。claude plugin disable コマンドを使用して無効化。

Guide for the inter-host agent API system. Use when adding capabilities to hosts, writing handlers, understanding the GC protocol, or debugging agent call issues.

Create, validate, and query WSC world entities (polities, agents, regions, forces, locales, holdings). Use when working with entity JSON files, checking entity consistency, or finding entities by type, tag, or relationship.

This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Scaffolds new frontend pages/features with TDD approach, following established UI patterns from BuildProject/Baker pages. Generates page component, test file, updates routing, and maintains 90%+ test coverage before implementing production code. Use this when creating new pages or features in the Bucket app.

Tavily AI search API integration via curl. Use this skill to perform live web search and RAG-style retrieval.

Automates TEST_CATALOG updates after test execution. Records test metrics, pass/fail status, coverage data, and execution time. Maintains single source of truth for all test files and their health status.

Comprehensive security specialist that performs vulnerability assessments, secure code reviews, dependency audits, and provides remediation guidance following OWASP, CWE, and industry security standards

SmartACE (Agentic Context Engineering) workflow engine with MCP-B (Master Client Bridge) and AMUM-QCI-ETHIC module. Dual database architecture using DuckDB (analytics) + SurrealDB (graph). Uses Blender 5.0 (bpy) and UE5 Remote Control. Use when (1) MCP-B agent-to-agent communication (INQC protocol), (2) AMUM 3→6→9 progressive alignment, (3) QCI quantum coherence states, (4) ETHIC principles enforcement (Marcel/Anthropic/EU AI Act), (5) SurrealDB graph relationships, (6) DuckDB SQL workflows, (7) ML inference with infera/vss, (8) Blender 5.0 headless processing, (9) UE5 scene control, (10) DuckLake time travel.

Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

This skill should be used when the user asks to "add unit tests", "write tests", "set up Vitest", "create a utility function", "add test coverage", or mentions TDD, test-driven development, or testing utilities. Provides guidance for unit testing with Vitest in TypeScript/Next.js projects using TDD approach.

DevOps expertise for deployment, CI/CD, infrastructure, and automation

Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.

Guide for adding new AI providers to ClaudeBar using TDD patterns. Use this skill when:(1) Adding a new AI assistant provider (like Antigravity, Cursor, etc.)(2) Creating a usage probe for a CLI tool or local API(3) Following TDD to implement provider integration(4) User asks "how do I add a new provider" or "create a provider for X"