Skills tagged "workflow" (1004)

Modernização de código PHP legado para padrões atuais (PHP 7.4-8.3). Usar para converter código procedural para OOP, atualizar sintaxe deprecated, implementar type hints, substituir arrays por objetos/collections, modernizar callbacks para closures/arrow functions, converter globals para dependency

Senior Legal Counsel with 20+ years experience in corporate law. Use for legal advice, contract drafting, compliance checks, data protection (GDPR/CCPA), employment law, or risk assessment. Auto-triggers penalty warnings and statute citations. Adapts to user's jurisdiction.

Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins. For standard protein design, use prote

Find and fix broken or insecure links across an entire site, including CMS content, to improve SEO and user experience. Audits HTTP/HTTPS issues and validates all internal and external links.

This skill should be used when the user asks to "LinkedIn öffnen", "zum Posteingang gehen", "Mitteilungen anzeigen", "LinkedIn Profil aufrufen", "LinkedIn navigieren". Aktiviere für alle LinkedIn Browser-Aktionen.

彙整今日中國宏觀經濟新聞消息，從華爾街日報、36氪等來源抓取並篩選宏觀相關新聞，輸出雜誌風格的新聞摘要。適用於交易/研究開盤前快速掌握中國宏觀動態。

评审 LLD、低层设计评审、详细设计审查。用于在实现前检查 LLD 是否承接 PRD/HLD/API Contract、遵循 Project Guardrails、覆盖必要模块并具备可实现性与可测试性。

Use when wanting to interact with any LLM - Explains available inference endpoints so the agent selects suitable models.

日志最佳实践，强调宽事件（canonical log lines），便于调试与分析。

Guide for migrating from Lovable Cloud to your own Supabase project. Use when users ask about exporting data from Lovable Cloud, disconnecting Lovable Cloud, migrating to their own Supabase, getting data out of managed Lovable database, switching from Lovable Cloud to external Supabase, or Lovable C

This skill writes a romantic love letter. Use this skill when the user asks for a love letter, romantic message, or declaration of love. The letter is always from Benno to Sabine.

Python machine learning with scikit-learn, PyTorch, and TensorFlow

分析并通过智能清理建议回收 macOS 磁盘空间。当用户报告磁盘空间问题、需要清理 Mac 或想了解什么占用了存储空间时，应使用此技能。专注于安全的交互式分析，在执行任何删除操作前需要用户确认。

Macroeconomic and market regime analyst. Monitors Fed policy, inflation, GDP, unemployment, and global economic trends to determine overall market risk appetite and sector rotation strategies.

Create AI-powered presentations from topics or URLs. Use this skill when users need to generate presentation slides, PowerPoint decks, or pitch decks. Triggers on requests for presentations, slide decks, or converting articles/content into slides.

Manages literal strings by pre-defining them as const string in C#. Use when organizing string constants, log messages, exception messages, or UI texts across the codebase.

Plan and implement Manim Community (ManimCE) animations: use when users want 3Blue1Brown-style explainer videos, need scene-by-scene planning, or ask for ManimCE code/visualizations. Must gather requirements, produce a scenes.md plan before any Manim code, then implement with ManimCE best practices

Build and integrate scroll-driven Manim animations with pre-rendered assets, manifest generation, and the web runtime in this repo. Use when users ask about Manim scroll playback, render pipelines, or integrating the runtime.

专注于使用 Manim 生成动画教学视频的完整流程与专业建议。适用于用户用中文提示语让 Codex 生成脚本、分镜、Manim 代码、渲染命令或优化教学视频质量与节奏，并输出 MP4。

Official integration patterns for Mapbox GL JS across popular web frameworks. Covers setup, lifecycle management, token handling, search integration, and common pitfalls. Based on Mapbox's create-web-app scaffolding tool.

Use when building interactive map tools - Explains MapLibre setup, tiles, and common UI patterns.

Product analytics instrumentation and strategy covering event taxonomy design, tracking plans, user behavior analysis, activation/retention metrics, and marketing attribution. PostHog-first with multi-platform support (Pendo, Amplitude, Mixpanel, Heap).

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provi

Query materials databases for structures and properties. Use when asked to get crystal structures, material properties, phase diagrams, or thermodynamic data. Primary source is Materials Project, with NIST, PubChem as secondary.

Interactive math teacher that instantly generates playful, gamified learning experiences. Creates visual playgrounds, interactive artifacts, and engaging games for kids and adults to learn math concepts from basic arithmetic to advanced calculus.

生成结构化的会议纪要，包含议题摘要、决策事项和行动项

Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models. Use when users need to (1) estimate memory from HuggingFace model configs (DeepSeek-V3, Qwen, etc.), (2) plan GPU resource allocation for training, (3) compare different parallelism strategies (TP/PP/EP/CP), (4)

记忆库 - 跨会话知识持久化管理。作为项目上下文的唯一真实来源。

Authoritative reference for Mermaid diagram syntax. Provides diagram types, syntax patterns, examples, and platform integration guidance for generating accurate Mermaid diagrams.

Apply invisible refinements that compound into felt quality

Send messages and Adaptive Cards to Microsoft Teams via Incoming Webhook. Use when user requests to send notifications, alerts, or formatted cards to Teams channels. Triggers include requests to post to Teams, Teams webhook, Teams notification, Teams card, or any request to send messages to Microsof

Migrates WPF applications from .NET Framework to .NET 6+. Use when upgrading legacy WPF apps, resolving compatibility issues, or modernizing project files.

Activate a Cognitive Digital Twin. Can simulate a custom subject (via core/ directory) OR load pre-installed celebrity/expert personas (from personas/ directory).

Implement ML pipelines, model serving, and feature engineering. Use for ML model integration or production deployment.

Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (SFT), preference optimization (DPO/RLHF concepts), LoRA/QLoRA, training configs, evaluation (offline/online), safety checks, deployment packaging, and cost/performance trade-offs.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs

Complete guide for building Moldable apps. Use this skill when creating new apps with scaffoldApp, modifying existing apps, implementing workspace-aware storage, integrating with the Moldable desktop via postMessage APIs (moldable:show-in-folder, moldable:set-chat-input, moldable:set-chat-instructio

UMPF 结构化提示词生成大师 - 通过多轮深度对话引导用户打磨电影级画面方案。支持 7 种视觉引擎(摄影/印刷/3D/油画/像素/水墨/定格动画)。触发条件: (1) 用户说'生成提示词'、'画一个...'、'帮我设计画面' (2) 需要 Nano banana 提示词 (3) 用户想要专业艺术指导生成图片 (4) 提到 UMPF 或 moonkite-maliang

MoSCoW prioritization categorizing items as Must have, Should have, Could have, or Won't have. Use for scope definition, feature prioritization, or when everything feels equally important.

Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.

使用 MuMuManager.exe 对 MuMu 模拟器 12 实例进行统一管理与操作，包含实例配置、创建/克隆/删除/重命名、导入/导出、启动/关闭/重启/窗口控制、应用安装/卸载/启动/关闭、设备信息、系统工具、ADB 命令、驱动与排序等。适合编写脚本批量自动化管理 MuMu 模拟器时使用。

Personal development toolkit - AI integration, session management, parallel development. Use when: multi-model AI, session handoff, git worktree operations. Triggers: "gemini", "codex", "handoff", "resume", "worktree"

Publish static HTML, ZIP archive, or directory to MyVibe. Use this skill when user wants to publish/deploy web content to MyVibe.

Generate images in Nano Banana Pro visual style using Gemini API. Use when: (1) User wants to create images/illustrations for Nano Banana Pro presentations, (2) User needs product mockups, icons, or visual assets in the Nano Banana color scheme, (3) User asks for AI-generated images with dark mode t

Sets up the full Neon JS SDK with unified auth and PostgREST-style database queries. Configures auth client, data client, and type generation. Use when building apps that need both authentication and database access in one SDK.

Implements multiplayer networking using Godot's high-level multiplayer API, including RPCs, synchronization, client-server architecture, and lag compensation. Use when building online multiplayer games.

Create a new Rails project

Switch NixOS/Home Manager configurations, clean old generations, and perform system maintenance with nh. Use when running os/home switch, pruning the Nix store, or managing system generations.

Generate NitroUI code - a Python library for programmatic HTML generation using classes instead of templates

Nix commands and package management guide. Use when: - Running nix build, nix run - Adding custom packages - Using nurl for hash acquisition

Validate npm package names and check availability on the registry. Use when creating new npm packages, suggesting package names, or validating package naming conventions.

Use when the user asks for a plan, roadmap, or step-by-step breakdown for a multi-step task in VS Code Copilot Agent mode.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

高阶 Obsidian 知识工程师。不仅是整理员，更是知识涌现的催化剂。擅长：(1) 实施 LYT (Linking Your Thinking) 框架与 MOC (内容地图) 构建，(2) 应用 ACE (Atlas, Calendar, Effort) 组织体系，(3) 识别知识节点间的深度连接，(4) 原子化笔记 (Atomic Notes) 标准化。

Add Olakai monitoring to an existing AI agent or LLM integration. AUTO-INVOKE when user wants to: add monitoring to existing code, integrate observability into a working agent, instrument an existing AI system, add tracking to LLM calls, wrap OpenAI/Anthropic clients, add analytics to working AI cod

Get started with Olakai - install, authenticate, and set up your first agent. AUTO-INVOKE when: CLI is not installed, user is not authenticated, user asks about getting started with Olakai, user wants to try Olakai, user mentions they don't have an account yet, or when other skills fail due to missi

Use when converting between caption formats (SRT, VTT, ASS, TTML, Gemini MD, etc.). Supports 30+ caption formats.