tailwind-v4
Tailwind CSS v4 with CSS-first configuration, @theme directive, OKLCH colors, and Vite integration. Use for modern utility-first styling with the new v4 architecture.
contributor-codebase-analyzer
>
unify
Validate spec-implementation-test alignment and convergence for spec groups. Checks spec completeness, atomic spec coverage, implementation evidence, test evidence, and traceability. Use after implementation and tests are complete.
test
Write tests that verify atomic spec acceptance criteria and requirements. Maps each AC to specific test cases, follows AAA pattern, ensures deterministic isolated tests. Use in parallel with implementation or after.
spec
Author specifications (TaskSpec for small-medium tasks, WorkstreamSpec for complex single-workstream tasks, or coordinate MasterSpec creation for multi-workstream efforts). Use after /prd requirements gathering or when refining existing specs.
security
Review implementation for security vulnerabilities and best practices. Checks input validation, injection prevention, auth/authz, secrets handling. Use after code review before merge.
route
Analyze task complexity and route to appropriate workflow. Defaults to oneoff-spec (specs are cheap, bugs are expensive). Use oneoff-vibe only for truly trivial changes or explicit user override. Use orchestrator for large multi-workstream efforts. Use journal-only for non-spec work that needs documentation.
refactor
Improve code quality while preserving behavior. Handles tech debt, pattern migrations, and structural improvements. Test suite is the contract - all tests must continue passing.
prd
Create PRDs through the gather-criticize loop, sync existing PRDs, push amendments, and check PRD status.
orchestrate
Orchestrate large multi-workstream projects using git worktrees for parallel development. Load MasterSpec, allocate worktrees, dispatch implementers, monitor convergence, process merge queue.
investigate
Investigate connection points between specs, atomic specs, and master specs. Surface inconsistencies in env vars, APIs, data shapes, and deployment assumptions before implementation.
implement
Implement code changes based on approved atomic specs. Executes one atomic spec at a time, gathers evidence, and escalates if implementation reveals spec gaps. Use after spec group approval.
flow-verify
Verify cross-boundary wiring correctness across independently-created systems. Catches missing imports, unregistered routes, mismatched event names, wrong config references, disconnected handlers, and missing middleware.
enforce
Validate atomic specs meet atomicity criteria
e2e-test
Generate end-to-end tests from spec contracts. Produces Playwright browser tests for frontend and HTTP API tests for backend. Black-box only -- never reads implementation source code. Runs in parallel with implementer and test-writer.
docs
Generate documentation from implementation. Creates user docs, API docs, and architecture docs. MANDATORY for all spec-based workflows (oneoff-spec, orchestrator). Only skipped for oneoff-vibe.
atomize
Decompose high-level specs into atomic specs
browser-test
Execute browser-based UI testing using Chrome MCP tools. Tests user interactions, visual outcomes, captures evidence. Use for UI features after implementation and security review.
challenge
Dispatch the challenger agent for operational feasibility scrutiny. Convergence loop for pre-implementation and pre-orchestration stages; single-pass for pre-test and pre-review. MANDATORY for both oneoff-spec and orchestrator workflows.
code-review
Review implementation for code quality, style consistency, and best practices. Runs before security review. READ-ONLY - reports issues but does not fix them.
deploy
Deploy CDKTF infrastructure stacks to AWS. Handles stack deployment, asset staging, output management, and environment configuration. Understands deployment sequences and stack dependencies.
doc-audit
Documentation audit skill for diagnosing documentation health across all doc directories. Supports quick scan and deep audit levels with variable scope.
bridge-js
Export Swift to JavaScript and import JavaScript/TypeScript into Swift using BridgeJS; type-safe bindings via @JS and related macros or bridge-js.d.ts; setup, config, AOT. Use when using or setting up BridgeJS, exporting Swift APIs to JS, importing JS/TS APIs into Swift, writing bridge-js.d.ts, configuring BridgeJS, or debugging BridgeJS boundaries.
javascriptkit
Assist Swift developers who consume JavaScriptKit for WebAssembly development
swift-wasm-porting
Check Swift on Wasm compatibility, identify incompatible frameworks, port and refactor code for WebAssembly
code-quality-report
生成代码质量报告。当用户请求为项目源代码生成质量报告时，使用此功能。输出名为 code-quality-report.html 的单页 HTML 文件作为质量报告，该报告集成了 Node.js 脚本和 HTML 模板。
image-gen
生成图片支持多提供商：火山 Ark (Doubao Seedream) 或 Gemini 3 Pro Image。支持批量生成、图片编辑、多图合成、自动保存和 Markdown 插入。
ppt-speech-creator
当用户需要创建PPT内容并生成配套演讲逐字稿时使用此技能。支持年终总结、项目复盘、产品发布、述职报告等多种场景，自动生成结构化PPT内容和按页分配的逐字稿，支持自动时长计算或用户指定总时长。
prompt-creator
Create new prompts from scratch by analyzing user needs, selecting suitable prompt frameworks, and fusing OmegaPromptForge. Use when the user asks to 创建提示词/生成提示词, 设计 prompt 框架, or output a Markdown...
prompt-optimizer
严格变更控制下编辑、版本化并存储提示词。用于用户要求小改/局部优化/补丁式修订、修复提示词失败、添加或维护版本头、对比版本，或基于输入/思路/输出诊断问题时。强制版本控制、作者签名，并将版本保存到 /Users/wisewong/Documents/Developer/prompts。
php-modernization
Use when working with ANY PHP modernization task: upgrading PHP 8.1+, adding strict types, configuring PHPStan/Rector/PHP-CS-Fixer, refactoring to enums/DTOs/readonly, improving type safety, or reviewing PHP code quality. Triggers on: PHP upgrade, modernize, type safety, PHPStan, Rector, PHP-CS-Fixer, enum, DTO, readonly, strict_types.
black-swan-seeker
Specialized agent skill for identifying "Black Swan" events—high-impact, low-probability outliers—and systemic risks in any subject matter. Use for red-teaming, stress-testing strategies, or exploring "unthinkable" scenarios.
qwen3-tts
Generate multilingual CustomVoice samples and one-off voice replies with Qwen3‑TTS (no Remotion). Includes local setup (Conda Py3.12) and simple CLI scripts.
react-starter-skill
|
uniapp-frontend
uni-app cross-platform frontend development with Vue 3 + TypeScript. Use for: (1) Creating new uni-app projects or pages, (2) Integrating UI libraries (uView Plus, uni-ui, TuniaoUI), (3) Implementing multi-theme design systems, (4) Building WeChat Mini Programs, H5, and other platforms, (5) Setting up SCSS theming and global styles, (6) Configuring Vite build system. Includes reusable templates, component patterns, and best practices applicable to any uni-app project.
create-agnostic-composable
Create a library-grade Vue composable that accepts maybe-reactive inputs (MaybeRef / MaybeRefOrGetter) so callers can pass a plain value, ref, or getter. Normalize inputs with toValue()/toRef() inside reactive effects (watch/watchEffect) to keep behavior predictable and reactive. Use this skill when user asks for creating agnostic or reusable composables.
vue-best-practices
A collection of best practices and tips for developing applications using Vue.js. This skill MUST be apply when developing, refactoring or reviewing Vue.js or Nuxt projects.
video-director
AI video generation using Google Veo 3.1 and Imagen. Use when the user wants to create videos, advertisements, promotional content, or any video generation task. Automatically activates for requests like "create a video", "make an advertisement", "generate a promotional video".
frontend-design-extractor
Extract reusable UI/UX design systems from frontend codebases: design tokens, global styles, components, interaction patterns, and page templates. Use when analyzing any frontend repo (React/Vue/Angular/Next/Vite/etc.) to document or migrate UI/UX for reuse across projects. Focus on UI/UX only; explicitly ignore business logic and domain workflows.
google-gemini-media
Use the Gemini API (Nano Banana image generation, Veo video, Gemini TTS speech and audio understanding) to deliver end-to-end multimodal media workflows and code templates for "generation + understanding".
ppt生成大师
可以直接通过大模型生成ppt文件。支持从 Markdown 大纲自动转换为 PowerPoint 演示文稿。
ai_llm_engineer
设计 AI 架构，编写 Prompt，构建 RAG 系统和 LangChain 应用
automation_expert
自动化流程与脚本专家，擅长使用 Python, PowerShell, Shell 及各类工具实现任务自动化。
cyber_security_expert
网络安全与渗透测试专家，专注于漏洞分析、安全防护及代码审计。
emotional_companion
情感支持与心理慰藉专家，擅长倾听、共情并提供温暖的心理引导。
frontend_design_expert
构建现代化的 UI/UX 设计，编写 Flutter/React 组件，配色方案与无障碍设计
Frontend_Design_System
将 UI 样式需求转化为生产级的前端代码，支持设计令牌、可访问性合规和创意执行。
Image_Generation_Expert
实现 AI 图像生成能力，支持根据文本描述创建高质量图像。
novel-writer
专为长篇网文创作设计的智能助手，支持从设定生成到正文撰写的全流程管理，包含智能质控与状态同步。(Yunshu Optimized)
python_data_analyst
编写用于数据清洗、分析和可视化的 Python 脚本 (Pandas/Matplotlib)
Page 3 of 1362 · 68078 results