发现 Skills

Guides Claude Code plugin skill creation covering SKILL.md structure, description optimization, and progressive disclosure. USE WHEN the user asks to "build a skill", "write a SKILL.md", "create a Claude Code skill", "improve a skill description", "optimize skill content", "design skill instructions", or works with skill authoring patterns or plugin directory structure. DO NOT USE for application code or general prompt engineering.

Use when discussing, expanding, or designing any subsystem in SPEC.md. Use when user asks about goals, API shape, edge cases, or configuration for HTTP, Router, ORM, Queue, Mail, Views, or other framework subsystems.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.

Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.

Open Chrome browser and post to the TikTok website. Log in to make sure that the user is logged in, and then click New Video. Provide some details about the file, and that's it.

Creates new Claude Code skills with proper structure and best practices. Use when a user wants to create a skill, update an existing skill, add a new command, scaffold a workflow, define skill hooks, or asks "how do I make a skill".

Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use when the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Returns LLM-optimized markdown.

Dispatches a composed set of assignment envelopes to domain-expert subagents in parallel, in a single message with multiple Agent tool calls. Enforces the no-pingpong gate via the pingpong-detector agent before any dispatch fires. Use when invoked by the coliseum-orchestrator as Phase 3; when envelopes are already composed and the next step is parallel execution; or when the user asks to "fan out" or "dispatch in parallel." Produces a dispatch log capturing what was sent, when, and where returns land.

Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols.

Guides understanding and working with Apache Beam's CI/CD system using GitHub Actions. Use when debugging CI failures, understanding test workflows, or modifying CI configuration.

Create Spring Boot projects with Java 25 and Spring Boot 4. Use when user wants to create, build, scaffold, setup, or initialize a new Spring Boot application, microservice, REST API, or backend service; asks for project structure recommendations; mentions Java 25 or Spring Boot 4 features (RestTestClient, HTTP Service Clients, API versioning, JSpecify null-safety, modularization); needs architecture guidance (layered, package-by-module, modular monolith, tomato, DDD+hexagonal); or requests Spring Initializr setup. Also triggers on discussions about Spring Boot architecture patterns, Value Objects, CQRS, or domain-driven design.

Review a GitHub pull request for a Rust codebase. Focuses on security, performance, test coverage, and Rust idioms. Runs in GitHub Actions and posts comments directly to the PR.

Shared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates, and framework detection patterns used across multiple setup commands.

SSH into a Home Assistant host and access config files, logs, and system commands. Use when the user asks to connect to HA over SSH, inspect host-level files, or debug the underlying OS.

Build modular Agentic RAG systems with LangGraph, featuring hierarchical indexing, conversation memory, and multi-agent query processing

Install and use World2Agent (W2A) sensors to give AI agents structured, real-time perception of the real world

Expert in analyzing the leaked Claude Code TypeScript source and architecture

CloudCLI (Claude Code UI) - web and mobile interface for managing Claude Code, Cursor CLI, Codex, and Gemini CLI sessions remotely

```markdown

OAuth authentication plugin for OpenCode that enables GPT-5.x and Codex model access via ChatGPT Plus/Pro subscriptions

ETL pipeline and analytics application for Harvard Art Museums API with SQL storage and Streamlit visualization

Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox