Interact with all Google Workspace APIs via the gws CLI. Use when managing Drive files, sending/reading Gmail, creating Calendar events, reading/writing Sheets/Docs/Slides, managing Chat spaces, contacts, Admin users/groups, Vault eDiscovery, Classroom, Apps Script, Workspace Events, or configuring the gws MCP server. Triggers on Google Workspace, gws, Drive, Gmail, Calendar, Sheets, Docs, Slides, Chat, Tasks, Meet, Forms, Keep, Admin, People, Vault, Classroom, Apps Script, Cloud Identity, Alert Center, Groups Settings, Licensing, Reseller, Model Armor, gws CLI, gws mcp, Google API, Workspace automation, npx skills add.

## Overview

Enables an AI agent to expertly create declarative YAML filters for `snip`, a CLI proxy designed to reduce LLM token consumption by intelligently filtering shell output.

Transform messy prompts into structured, effective prompts — single, multi-agent, or reverse-engineered from great outputs. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags, "reprompter teams", "repromptverse", "run with quality", "smart run", "smart agents", "campaign swarm", "engineering swarm", "ops swarm", "research swarm", multi-agent tasks, audits, parallel work, "reverse reprompt", "reprompt from example", "learn from this", "extract prompt from", "prompt dna", "prompt genome", reverse-engineering prompts from exemplar outputs. Don't use for simple Q&A, pure chat, or immediate execution-only tasks (see "Don't Use When" section). Outputs: structured XML/Markdown prompt, before/after quality score, optional team brief + per-agent sub-prompts, Agent Cards, Extraction Card (reverse mode). Target quality score: Single ≥ 7/10; Repromptverse per-agent ≥ 8/10; Reverse ≥ 7/10.

세션 종료 시 Memory, Handoff를 자동 정리. /pack

Main entry point for hierarchical task execution. Orchestrates layer-by-layer implementation of PRD tasks with parallel worktree execution.

Collection of agent skills for Helios video engine. Use when working with programmatic video creation, browser-native animations, or Helios compositions. Install individual skills by path for specific capabilities.

Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.

This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit. Guide users through executable specification workflows for both new projects (greenfield) and existing codebases (brownfield). After any SDD command generates artifacts, automatically provide structured 10-point summaries with feature status tracking, enabling natural language feature management and keeping users engaged throughout the process.

Enables an autonomous work mode for AI agents, allowing continuous operation without user interruption. It includes a pre-flight risk assessment and intelligent blocker handling to maximize productivity.

Use this skill when the user wants to test a business idea, strategy, or initiative against real-world risk. Triggers include: 'test my idea', 'what are the riskiest assumptions', 'help me validate this', 'run EMT on this', 'extract assumptions', 'assumption mapping', 'what could go wrong with this plan', 'pressure test this', 'validate this plan', 'what could go wrong with this strategy', 'identify hidden risk in this idea', or any request to pressure-test a business decision before committing resources. Runs a guided Extract → Map → Test system based on David J. Bland's Precoil methodology.

Use when executing implementation plans phase-by-phase with strict enforcement of quality gates, tests, and Definition of Done. Triggers on "build this plan", "execute plan", "implement phases", or when user provides a plan document to execute.

Sensei is an AI agent skill that iteratively improves the frontmatter compliance of other AI agent skills, ensuring they meet quality standards and pass their tests.

ERNE — Test-driven development workflow with Jest and React Native Testing Library

A CLI tool for AI agents to manage hierarchical teams of other AI agents, enabling structured task assignment, context management, and workflow automation.

Enhance Claude Code's capabilities with a three-layer memory system for cross-session knowledge extraction, storage, and loading, designed for persistent context retention.

Automates sending personalized Chinese New Year greetings via the Mac WeChat client, featuring state memory, duplicate prevention, and AI-driven template selection based on chat context.

This guide explains the architecture of Claude AI agent skills, demonstrating how to extend Claude CLI capabilities with new, modular actions like direct job applications.

Generates a structured Pull Request (PR) summary, including the PR title, a list of changes, an optional test plan, and linked issue numbers. It streamlines the creation of consistent and comprehensive PR descriptions.

This skill guides an AI assistant through the process of setting up VibeCollab in a user's project, including installation, initialization, and initial documentation generation.

Mint is an auto-routing orchestrator for AI coding agents, designed to streamline disciplined agentic development. It automatically detects and invokes the most appropriate mode (quick, plan, research, ship, verify) for any coding task.

This AI skill transforms your agent into a friendly landing page design mentor. It guides beginners through planning and designing a conceptual blueprint for their landing page or personal portfolio.