multi-compare
Run the same prompt with Claude, OpenAI, and Gemini in parallel, then return back exact replies you got back without modifying the results one bit.
Skills correspondant au nom, à la description ou à l’auteur GitHub.
Run the same prompt with Claude, OpenAI, and Gemini in parallel, then return back exact replies you got back without modifying the results one bit.
Coordinate with other AI agents running in tmux panes. Use this skill when you need to delegate tasks, request reviews, or collaborate with agents like Codex, Gemini, or other Claude instances.
Communicate with other AI agents in tmux panes. Use when you need to talk to codex, claude, gemini, or other agents.
SOP for creating new Claude Code skills. Use when adding a new skill to any project or globally.
ユーザと対話してCLAUDE.mdを初期化・更新する
This skill should be used when the user asks to "create a session hook", "add a temporary hook", "create a hook for this session", "set up a hook that activates immediately", "configure a one-time hook", or men...
Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context assembly for Kiro, Claude Code, Codex, Charm, or other agents.
Maps and documents codebases of any size by orchestrating parallel subagents. Creates docs/CODEBASE_MAP.md with architecture, file purposes, dependencies, and navigation guides. Updates CLAUDE.md with a summary...
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 to...
Project-agnostic guidance for continuing work across Claude sessions. Ensures context recovery, task resumption, and state reconciliation.
Query Claude Code conversation history and session data using SQL with cc-query. Use when analyzing past conversations, token usage, tool patterns, agent activity, or extracting insights from session logs. Trig...
カスタムClaude Codeスラッシュコマンド(/command-name構文)を作成します。ユーザーが明示的にトリガーするワークフローを実装し、新鮮なコンテキストで実行します。頻繁に使うワークフローのショートカット、明示的なユーザ...
Claude間のパイプライン用に最適化されたメタプロンプトを作成します。リサーチ、計画、実行の各段階を含む多段階ワークフローを設計します。複雑なタスクの段階的処理、Claude間の連携、構造化されたワークフローが必要な場合...
現在のClaudeセッション内でクイックレビューを実施します。コンテキストを保持したまま即座にコード品質、セキュリティ、パフォーマンスを評価します。
Claude Codeのイベント駆動型自動化とバリデーション用のhooksを作成します。tool呼び出し、ユーザーメッセージ、コミット前チェックなどのイベントに反応するhooksを実装します。自動化ワークフロー、バリデーション、イベン...
Spawner selection, cost optimization, and HeadlessSpawner patterns for coordinating multiple AI models (Codex, Gemini, Copilot, Claude).
Use when working on long-running projects or needing context across sessions. Covers memory architecture, privacy controls, efficient retrieval, and integration with claude-mem plugin. Apply when building featu...
Delegate tasks to remote Claude Code agent containers for parallel execution, long-running analysis, or resource-intensive operations.
Generate comprehensive Product Requirements Documents with interactive discovery, progress tracking, and True Ralph Loop support for autonomous implementation. Use when user wants to (1) create a PRD for a new...
Analyzes design docs and existing projects to create detailed, actionable implementation plans for Claude Code. Use when the user asks to create an implementation plan, analyze a feature, or break down tasks.
Expert knowledge about xling CLI tool for managing AI tools (Claude Code, Codex, Gemini) and executing AI prompts with multi-provider support. Use when user asks about xling commands, configuration, or workflow...
Prompt engineering guidance for Claude (Anthropic) model. Use when crafting prompts for Claude to leverage XML-style tags, long-context capabilities, extended thinking, and strong instruction following.
Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Addi...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.