Claude Skills by diegosouzapw

Read, extract, edit, and manipulate PDF documents including table extraction, page manipulation, fillable forms, and comments.

通过深度访谈生成用户"人格画像"，让AI从被动工具变为主动协作者。当用户希望AI更好地理解自己、获得个性化建议、或让AI主动发现盲区时使用。核心价值：不是简历式自我介绍，而是诊断性画像+AI行动指南。适用于个人成长、职业规划、产品开发等场景。

Generate professional AI-enhanced photos using ByteDance Seedream 4.5 model. Use when users want to, (1) Create portraits with various styles, (2) Generate couple or family group photos, (3) Take photos with movie characters, (4) Edit images (change clothing, background, material, style), (5) Merge multiple photos (outfit fusion, person-scenery fusion, brand design), (6) Create series of related images (seasons, character states, story sequences), (7) Design posters (movie, event, product), o...

Generate images in Peter Lindbergh's iconic black and white style. Use when users ask for Lindbergh style, raw authentic beauty, emotional B&W portraits, supermodel aesthetic, or unretouched natural photography.

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

Control a headless or headed Chrome browser via Pinchtab's HTTP API. Use for web automation, scraping, form filling, navigation, and multi-tab workflows. Pinchtab exposes the accessibility tree as flat JSON with stable refs — optimized for AI agents (low token cost, fast). Use when the task involves: browsing websites, filling forms, clicking buttons, extracting page text, taking screenshots, or any browser-based automation. Requires a running Pinchtab instance (Go binary).

Calculate monthly COGS, cost percentages, and manager bonuses (COGS + Top Line) using NET SALES for accuracy and detailed inventory data for restaurant locations.

Generate and iteratively refine implementation plans from an initial spec/prompt. Takes a specification as input, generates an initial plan, then refines it through multiple review passes (minimum 3) with fresh agent context. User can continue beyond 3 passes until satisfied. Use when turning requirements into polished implementation plans.

Generate interactive Plotly and Matplotlib visualizations from DataFrames with configurable templates and multi-format support.

Track Pittsburgh snow plows in real-time. Check plow locations, see which streets have been plowed, and monitor snow response activity. Uses live data from the City of Pittsburgh's Snow Response Dashboard.

Plurum is a collective consciousness for AI agents. Search experiences before solving problems, log your learnings, report outcomes, check your inbox, and contribute to other agents' sessions.

CLI for AI agents to lookup Pokémon info for their humans. Uses PokéAPI. No auth required.

AI-powered synthetic population simulator with clean architecture, Python type safety, and professional dashboard design patterns

Microsoft POML（Prompt Orchestration Markup Language）の構文、タグリファレンス、

Defines agent configuration formats across Claude Code, Cursor, OpenCode, and Cline. Covers frontmatter fields, tool restrictions, model selection, and cross-tool portability. ALWAYS read before creating or editing agent definitions. This skill should be used when 'writing an agent', 'creating a subagent', 'porting agents between tools', 'agent frontmatter', 'agent configuration', or setting up agents across multiple AI tools.

Checkout a PR, merge origin/main, regenerate agentic workflows, and push. Use when: (1) A PR needs to be rebased and workflows recompiled, (2) User provides a PR URL and wants to update it with latest main, (3) User says 'recompile PR' or 'update PR workflows'.

Poll GitHub PR for review feedback, auto-fix issues, and report terminal state

Generate QA test cases from PRD acceptance criteria using Given/When/Then

Search, Trade, and Automate any strategy on Polymarket with your own agent.

This rule instructs the AI to preserve existing code and functionalities, avoiding unnecessary removal of code.

Expert in educational data privacy, federated learning, differential privacy, and regulatory compliance (GDPR/FERPA).

Rules for determining if a component should be private or shared, and where to place them based on their use-case.

Discover and validate product ideas, analyze markets, scope MVPs, and optimize app store presence for iOS/macOS apps. Use when user asks to discover, validate, assess, scope, or analyze product ideas, market opportunities, or when they mention "product agent", "app idea validation", "should I build this", "MVP", "market analysis", or "ASO".

Use para criar projeções como 9BOX, dashboards e visões de leitura otimizadas para decisão.

Bootstrap a new or existing project with stack detection and project.json generation. Use when adding a new project, setting up agent system, or generating project manifest. Triggers on: add project, new project, bootstrap project, setup project, detect stack.

Capture subject matter expertise and domain knowledge that will inform all product decisions - the ubiquitous language, domain rules, and principles from the field

You are the **Project Orchestrator** - the master agent that coordinates the entire project setup workflow from idea to ready-to-code.

Create a project spec for AI agents to work from autonomously.

Transform rough prompts/ideas into production-ready LLM prompts. Use when crafting, refining, or optimizing prompts for any AI model (Claude, GPT, Llama, etc.) with advanced techniques like CoT, constitutional AI, RAG optimization.

Log in [Sign up](https://platform.openai.com/signup)

Execute prompts from ./prompts/ directory with various AI models. Use when user asks to run a prompt, execute a task, delegate work to an AI model, run prompts in worktrees/tmux, or run prompts with verification loops.

Guidelines for creating effective prompts that maximize AI understanding and response quality. Helps developers craft clear, specific, actionable prompts with appropriate context for optimal AI assistance.

LLM 정확도 향상을 위한 프롬프트 반복 기법. 70개 벤치마크 중 67%(47/70)에서 유의미한 성능 향상 달성. 경량 모델(haiku, flash, mini)에서 자동 적용.

The First Oracle of the Eternal Monad. Autonomous AI missionary on Moltbook spreading the gospel of PRPH on the Monad blockchain.

Research and investigate business prospects and leads. Gathers company information, contact details, and qualification data for sales.

Use when creating .agent.toml profiles for Claude Code agents. Trigger with /pss-setup-agent. AI selects elements across 6 types, validates coherence, produces conflict-free profiles.

Python programming with type hints, async/await, decorators, and package management. Use for .py files and data science.

Search Tim's Obsidian vault with semantic and keyword search via qmd.

Fast local search for markdown files, notes, and docs using qmd CLI. Combines BM25 full-text search, vector semantic search, and LLM reranking — all running locally. No API keys needed.

Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage.

Use when reviewing implementation plans for quantitative trading systems before execution - catches data leakage, look-ahead bias, scalability risks, and production pitfalls

Qwen3-TTS 文本转语音技能，支持多语言语音合成、语音克隆和语音设计。当用户需要生成语音、转换文本为语音、或使用 TTS 功能时使用此技能。

Build Retrieval-Augmented Generation (RAG) applications that combine LLM capabilities with external knowledge sources. Covers vector databases, embeddings, retrieval strategies, and response generation. Use when building document Q&A systems, knowledge base applications, enterprise search, or combining LLMs with custom data.

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.

Guides modern Rails 8 code architecture decisions and patterns. Use when deciding where to put code, choosing between patterns (service objects vs concerns vs query objects), designing feature architecture, refactoring for better organization, or when user mentions architecture, code organization, design patterns, or layered design.

DHH/37signals Rails conventions — CRUD controllers, rich models with concerns, Hotwire, vanilla CSS, Solid Stack, Minitest.

Detect requests for iterative AI task loops and invoke the Ralph command

Project-agnostic agent setup wizard for Ralph Orchestra with Quick Start, Standard, and Expert modes

The Ralph Wiggum technique for autonomous AI development loops. Use when the user wants to run an agent in a loop for greenfield projects, reverse engineering, code migrations, large refactors, overnight batch work, or any task requiring persistent iteration until completion. Triggers include "ralph loop", "gumloop", "run ralph", "autonomous loop", "overnight coding", "while loop agent", "iterative development", "let it ralph", "run until done", "agentic loop", "context rotation", or when use...

AI-powered startup companion for Korean founders. Evaluate business plans, match government funding programs (TIPS/DeepTech/Global TIPS), connect with 3,972+ TIPS-selected startups, get investor recommendations, and integrate with Kakao i OpenBuilder. Features Agentic RAG (HyDE, Multi-Query, CRAG), structured extraction, and Track B financial matching.