task-breakdown
专业的任务拆解器,将复杂需求拆分成"独立可运行与可演示"的最小闭环任务卡。严格按照纵向切片、单一数据变化、单一入口原则,确保每张任务卡都能在单回合实现并验证。当用户说"帮我拆解一下任务"、"用任务拆解器分析"、"按规...
Discover Research skills, compare source repositories and read the instructions for each workflow.
专业的任务拆解器,将复杂需求拆分成"独立可运行与可演示"的最小闭环任务卡。严格按照纵向切片、单一数据变化、单一入口原则,确保每张任务卡都能在单回合实现并验证。当用户说"帮我拆解一下任务"、"用任务拆解器分析"、"按规...
AI驱动的设计系统构建器。基于项目特征智能推荐最合适的设计风格(从30+专业设计系统中选择),或使用用户指定的风格。自动应用完整的设计系统规范(颜色、字体、组件、动效等)来实现界面。
Executes OpenAI Codex CLI for code analysis, refactoring, and automated editing. Activates when users mention codex commands, code review requests, or automated code transformations requiring advanced reasoning...
This skill should be used when organizing and structuring Personal Knowledge Management (PKM) vaults, particularly Obsidian vaults using the Linking Your Thinking (LYT) methodology. Use this skill when the user...
Simple Pomodoro timer for focused work sessions with session tracking and productivity analytics. Use when users request focus timers, ask about productivity patterns, or want to track work sessions over time....
AI orchestration and task management platform. Use this skill when working in a Fulcrum task worktree, managing tasks/projects, or interacting with the Fulcrum server.
对 Twitter 采集产出进行二次清洗,自动获取完整推文内容并生成可筛选数据。
统一的推文内容获取技能。支持单条/批量推文提取,输出结构化数据。当用户提供 Twitter/X 链接并希望获取内容时自动触发。
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design,...
Automatically organize and clean up downloads folder by categorizing files, removing duplicates, and optimizing storage space
压缩桌面最新视频 - 使用 HandBrake 快速压缩桌面上最新的视频文件,采用快速失败策略
Generates images using Google's Gemini model. Prioritizes standard resolution to save quota. Automatically opens images on macOS.
将 Twitter 链接列表转换为 Grok 生成的结构化 JSON 数据。
Extract content from Twitter/X articles, summarize key points, and save as structured Obsidian notes. Use when user provides a Twitter/X URL and wants to save it as a note, or mentions "save to Obsidian", "crea...
用于同步 Alma 技能到斜杠命令(Prompts)列表。当用户新增技能、修改技能名称或需要清理无效的快捷指令时使用。
Automate Google NotebookLM - create notebooks, add sources, generate podcasts/videos/quizzes, download artifacts. Supports browser-based content extraction for anti-crawler platforms (Twitter/X, LinkedIn, etc.)...
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...
Emulates the AI Coding Toolkit's Claude Code command /progress (show progress through EXECUTION_PLAN.md by phase: completed vs remaining acceptance criteria, last completed task, next task). Triggers on "/progr...
Emulates the AI Coding Toolkit's Claude Code command /phase-checkpoint (run checkpoint criteria: tests, typecheck, lint, security scan, coverage; list manual verification steps; update .claude/phase-state.json...
Emulates the AI Coding Toolkit's Claude Code command /fresh-start (orient to project structure, validate directory, load AGENTS.md + specs + EXECUTION_PLAN.md, optionally set up git/feature branches). Triggers...
Emulates the AI Coding Toolkit's Claude Code command /phase-prep (checks prerequisites before starting a phase: pre-phase setup, prior phase completion, git status, tool availability). Triggers on "/phase-prep...
Emulates the AI Coding Toolkit's Claude Code command /verify-task (verify a specific task from EXECUTION_PLAN.md against acceptance criteria, enforce TDD expectations, fix failures with a limited retry loop)....
Emulates the AI Coding Toolkit's Claude Code command /populate-state (generate .claude/phase-state.json from EXECUTION_PLAN.md + git history to track phase/task status). Triggers on "/populate-state" or "popula...
Emulates the AI Coding Toolkit's Claude Code command /list-todos (analyze TODOS.md, prioritize items, and produce implementation guidance without guessing when requirements are unclear). Triggers on "/list-todo...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.