浏览 GGPrompts 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
56收录技能的仓库 Stars 合计
2,453仓库 Forks
191平均每个技能的仓库 Stars
44同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Controls Chrome browser: takes screenshots, clicks buttons, fills forms, downloads images, inspects pages, captures network requests, checks console errors, debugs API issues. Use when: 'screenshot', 'click', '...
Craft effective worker prompts from backlog issues using Claude 4 best practices. Use when preparing issues for workers, writing prompts, or optimizing prompt quality. Trigger with "craft prompt", "write prompt...
TabzChrome terminal spawning and worker management patterns. Use when spawning workers, managing terminals, or setting up worktrees. Trigger with "spawn worker", "create terminal", "worktree setup".
Break down epics and features into concrete backlog tasks with dependencies. Use when planning work, decomposing large features, or organizing sprints. Trigger with "break down", "decompose", "plan feature", "c...
Branch merging and conflict resolution patterns. Use when merging feature branches, handling conflicts, or cleaning up worktrees. Trigger with "merge branch", "resolve conflicts", "cleanup worktree".
Browser automation via 70 tabz MCP tools. Use when taking screenshots, filling forms, debugging network requests, testing responsive design, or using text-to-speech notifications.
Spawn and manage terminal tabs via TabzChrome REST API. Use when spawning workers, creating terminals programmatically, setting up worktrees for parallel work, or crafting prompts for Claude workers.
Integrate projects with TabzChrome terminals via HTML attributes, WebSocket, JS API, or Spawn API
AI-assisted backlog grooming: prioritize, add dependencies, assign quality gates, draft worker prompts
Multi-model conductor - spawns Haiku/Sonnet/Opus/Codex based on task complexity
Visual QA checkpoint. Verifies UI changes in the extension/backend via quick smoke flows, screenshots, and console/network checks. Use when: 'visual QA', 'UI looks wrong', 'screenshot', 'verify in Chrome'.
Test runner checkpoint for conductor gates. Detects test framework (jest, pytest, cargo test, go test, etc.), runs tests, and captures output. Returns structured result with pass/fail status and failed test det...
Code review checkpoint using codex review CLI. Returns structured result with pass/fail status and issues. Use when: 'code review', 'review changes', 'codex review', 'check my code'.
Brainstorm ideas and design workflows with a beads expert. Use when: 'help me plan', 'how should I structure this', 'what beads features', 'brainstorm', 'before I create tasks', 'design my workflow'. For ideati...
Docs/changelog checkpoint. Detects whether changes are user-facing and ensures documentation hygiene (CHANGELOG + lessons-learned) is handled or explicitly bypassed. Use when: 'docs check', 'changelog', 'releas...
Patterns for building and debugging TabzChrome itself. Use when working on Terminal.tsx, xterm.js integration, WebSocket I/O, resize handling, or any TabzChrome extension/backend code.
Integrate projects with TabzChrome terminals via HTML attributes, WebSocket, JS API, or Spawn API
Spawn and manage terminal tabs via TabzChrome REST API. Use when spawning workers, creating terminals programmatically, setting up worktrees for parallel work, or crafting prompts for Claude workers.
Browser automation via 70 tabz MCP tools. Use when taking screenshots, filling forms, debugging network requests, testing responsive design, or using text-to-speech notifications.
Build terminal user interfaces with Go and Bubbletea framework. Use for creating TUI apps with the Elm architecture, dual-pane layouts, accordion modes, mouse/keyboard handling, Lipgloss styling, and reusable c...
Guide for creating effective Claude Code agents. This skill should be used when users want to create a new agent (or update an existing agent) that configures Claude with specialized system prompts, tool restri...
This skill should be used when working with xterm.js terminal implementations, React-based terminal applications, WebSocket terminal communication, or refactoring terminal-related code. It provides battle-teste...
Comprehensive guide for Docker MCP Toolkit Dynamic Tools - discover and use ~170 MCP servers on-demand. Use when working with MCP servers, dynamic tools, database access, APIs, cloud services, or needing extern...
Create and manage Claude Code plugins including commands, agents, skills, hooks, and MCP servers. This skill should be used when building new plugins, debugging plugin issues, understanding plugin structure, or...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。