diegosouzapw
- 13k skills
- 0 followers
- 54 repo stars
- 2 weeks ago last updated
- ▌ Notion Content · diegosouzapw bundleCreate content records in Notion database after publishing articles. Use when user provides article title and publishing links (zhihu, weixin, baidu, sohu, toutiao, x.com). Auto-detects platform from URL, fills publish date. Trigger on "/notion-content", "notion记录", "内容入库", or when user says they published an article with links.
- ▌ Analyze Email · diegosouzapw bundleQuick single email analysis - read metadata, content summary, and list attachments without extracting them.
- ▌ Email Copilot · diegosouzapw bundleManages inbox by learning preferences, cleaning noise, and prioritizing important work. Use when user asks about emails or inbox management.
- ▌ Amq CLI · diegosouzapw bundleCoordinate agents via the AMQ CLI for file-based inter-agent messaging. Use when you need to send messages to another agent (Claude/Codex), receive messages from partner agents, set up co-op mode between Claude Code and Codex CLI, or manage agent-to-agent communication in any multi-agent workflow. Triggers include "message codex", "talk to claude", "collaborate with partner agent", "AMQ", "inter-agent messaging", or "agent coordination".
- ▌
- ▌ AWS CLI · diegosouzapw bundle[Applies to: **/*] Definitive guidelines for secure, reproducible, and efficient use of the AWS CLI, emphasizing modern DevOps practices and automation.
- ▌ CLI Duo · diegosouzapw bundleCoordinate two AI CLIs on the same repo without conflicts (subordinate worktrees + engineer/judge roles).
- ▌
- ▌ Git Log · diegosouzapw bundleShow commit history for a file or the entire repository. Returns commit information including hash, author, date, and message.
- ▌ Qcc Git · diegosouzapw bundleUse for Git workflow, branch strategy, and commit conventions in qcc_plus project
- ▌ Safe Rm · diegosouzapw bundleSafe file deletion for Git projects. Classifies files (ALLOW/TRASH/BLOCK), uses trash for untracked source, logs all operations. Use when deleting files, cleaning build artifacts, running rm -rf, or when the user mentions cleanup, trash, or deletion in repositories.
- ▌ Things3 · diegosouzapw bundleThis skill should be used when the user asks to "create a task in Things", "add a todo to Things 3", "manage Things projects", "schedule a task", "complete a todo", "delete a task from Things", "move task to Today", "add to Things inbox", "create a project in Things", "manage Things areas", or mentions Things 3 task management.
- ▌ AI Tools · diegosouzapw bundleGoogle AI tools integration. Modules: Gemini API (multimodal: audio/image/video/PDF, 2M context), Gemini CLI (second opinions, Google Search, code review), NotebookLM (source-grounded Q&A). Capabilities: transcription, OCR, video analysis, image generation, web search, document queries. Actions: transcribe, analyze, extract, generate, query, search with Google AI. Keywords: Gemini, Gemini API, Gemini CLI, NotebookLM, audio transcription, image captioning, video analysis, PDF extraction, Google Search, second opinion, source-grounded, multimodal, web research. Use when: processing media files, needing second AI opinion, searching current web info, querying uploaded documents, generating images.
- ▌ Abductive Repl · diegosouzapw bundleHypothesis-Test Loops via REPL for Exploratory Abductive Inference with Gay.jl colors
- ▌ Account Delete · diegosouzapw bundleПолное удаление аккаунта и всех связанных данных из конфигурации.
- ▌ Ads Management · diegosouzapw bundleActivate for paid advertising campaigns on Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads. Includes ad copywriting, audience targeting, budget optimization, A/B testing, and ROAS tracking. Used by ads-specialist and campaign-manager agents.
- ▌ Agent Creating · diegosouzapw bundleUsed to create a new agent. Used when a user wants to create a new agent
- ▌ Agent Creation · diegosouzapw bundleStandards-compliant agent definitions with templates. Trigger: When creating agent definitions, setting up project agents, or documenting workflows.
- ▌ Agent Debugger · diegosouzapw bundleExpert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving. Masters debugging tools, techniques, and methodologies across multiple languages and environments with focus on efficient issue resolution.
- ▌ Agent Detector · diegosouzapw bundleCRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Always runs FIRST.
- ▌ Agent Handoffs · diegosouzapw bundleAgent parameter passing, memory files, and data handoffs between agents
- ▌ Agent Ops Spec · diegosouzapw bundleManage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
- ▌ Agent Protocol · diegosouzapw bundleHuman and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.
- ▌ AI Consultants · diegosouzapw bundleConsult Gemini CLI, Codex CLI, Mistral Vibe, Kilo CLI, Cursor, Claude, Amp, Kimi, Qwen, and Ollama as external experts for coding questions. Automatically excludes the invoking agent from the panel to avoid self-consultation. Use when you have doubts about implementations, want a second opinion, need to choose between different approaches, or when explicitly requested with phrases like "ask the consultants", "what do the other models think", "compare solutions".
- ▌ AI Factory Fix · diegosouzapw bundleFix a specific bug or problem in the codebase. Analyzes code to find and fix issues without creating plans. Use when user reports a bug, error, or something not working. Always suggests test coverage and adds logging.
- ▌ AI Integration · diegosouzapw bundleAI/LLM integration patterns - Claude API, fal.ai, streaming, tool use
- ▌ AI Sdk 6 Skill · diegosouzapw bundleExpert guide for Vercel AI SDK 6 - ToolLoopAgent, safety patterns, MCP, RAG, DevTools.
- ▌ AI Usage Coach · diegosouzapw bundleHelp users get more value from AI assistants by suggesting better prompting techniques, surfacing underused features, and identifying workflow improvements. Use when users ask things like "how can I use Claude better?", "what features am I missing?", "give me tips for prompting", "what can you do?", "I feel like I'm not getting the most out of this", or when they explicitly ask for help improving their AI usage. Also use when users seem frustrated with results or are clearly using suboptimal patterns.
- ▌ Airflow Expert · diegosouzapw bundleExpert-level Apache Airflow orchestration, DAGs, operators, sensors, XComs, task dependencies, and scheduling
- ▌ Airtight Plans · diegosouzapw bundleWrite structured multi-step implementation plans in markdown format. Plans use numbered steps with clear titles and detailed instructions. Use when asked to create an implementation plan, development roadmap, or multi-step task breakdown.
- ▌
- ▌ Analyzing Data · diegosouzapw bundleQueries data warehouse and answers business questions about data. Handles questions requiring database/warehouse queries including "who uses X", "how many Y", "show me Z", "find customers", "what is the count", data lookups, metrics, trends, or SQL analysis.
- ▌ Asset Tracking · diegosouzapw bundleUse when managing asset metadata, dependencies, and delivery workflows across teams.
- ▌ Code Standards · diegosouzapw bundleSetup universal code quality standards in your project. Use when the user wants to generate coding standards files (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) or mentions 'code standards', 'code review setup', or similar intent in any language.
- ▌ Codex Reviewer · diegosouzapw bundleUse OpenAI's Codex CLI as an independent code reviewer to provide second opinions on code implementations, architectural decisions, code specifications, and pull requests. Trigger when users request code review, second opinion, independent review, architecture validation, or mention Codex review. Provides unbiased analysis using GPT-5-Codex model through the codex exec command for non-interactive reviews.
- ▌ Criador Skills · diegosouzapw bundleHelper skill to create new agent skills following the standard structure. Use this when you want to define a new capability or workflow for the agent.
- ▌ Database Skill · diegosouzapw bundleDesign and manage relational databases including table creation, migrations, and schema design. Use for database modeling and maintenance.
- ▌ Gpt Researcher · diegosouzapw bundleRun GPT-Researcher multi-agent deep research framework locally using OpenAI GPT-5.2. Replaces ChatGPT Deep Research with local control. Researches 100+ sources in parallel, provides comprehensive citations. Use for Phase 3 industry/technical research or comprehensive synthesis. Takes 6-20 min depending on report type. Supports multiple LLM providers.
- ▌ Layer 01 Motiv · diegosouzapw bundleExpert knowledge for Motivation Layer modeling in Documentation Robotics
- ▌ Learned Lesson · diegosouzapw bundleCaptura e armazena licoes tecnicas de bug fixes ou decisoes arquiteturais
- ▌ LLM Evaluation · diegosouzapw bundleImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or ...
- ▌ MCP Agent Mail · diegosouzapw bundleFastMCP agent-to-agent communication system with messaging, file reservations, and multi-repo coordination
- ▌ Mermaid Expert · diegosouzapw bundleCreate Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling. Use PROACTIVELY for visual documentation, system diagrams, or process flows.
- ▌ Mongodb Expert · diegosouzapw bundleExpert-level MongoDB database design, aggregation pipelines, indexing, replication, and production operations
- ▌ Obsidian Daily · diegosouzapw bundleManage Obsidian Daily Notes via obsidian-cli. Create and open daily notes, append entries (journals, logs, tasks, links), read past notes by date, and search vault content. Handles relative dates like "yesterday", "last Friday", "3 days ago".
- ▌ Page Annotator · diegosouzapw bundleAI驱动的网页标注工具,支持高亮元素和添加文字批注。智能防重复、自动滚动、碰撞检测。兼容 GitHub 等严格 CSP 网站。适用场景:(1) 标记网页元素进行讲解 (2) 添加文字批注和注释 (3) 代码审查和设计评审 (4) 教学演示和用户引导 (5) Bug 报告和问题标记
- ▌ Planning Phase · diegosouzapw bundleGenerates implementation plans with code reuse analysis, architecture design, and complexity estimation during the /plan phase. Use when planning feature implementation, analyzing code reuse opportunities, or designing system architecture after specification phase completes. Integrates with 8 project documentation files for constraint extraction. (project)
- ▌ Plot Keypoints · diegosouzapw bundleOrganize story main line, extract and arrange major plot points by development stage. Suitable for quickly grasping story structure, creating outlines, and script adaptation structure organization
- ▌ Project Domain · diegosouzapw bundleCapture subject matter expertise and domain knowledge that will inform all product decisions - the ubiquitous language, domain rules, and principles from the field
- ▌ Prompt Caching · diegosouzapw bundleCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augm...
- ▌ Pss Agent Toml · diegosouzapw bundleUse 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.
- ▌ Research Leads · diegosouzapw bundleResearch new capabilities and changes for tracked AI coding agents. Use this skill when assigned a research-leads issue to discover new features, or when asked to revise a research PR.
- ▌ Rill Connector · diegosouzapw bundleDetailed instructions and examples for developing connector resources in Rill
- ▌ Second Opinion · diegosouzapw bundleCross-validate code, architecture or design decisions using a second model. Use for critical decisions, complex refactoring, security reviews.
- ▌ Skill Creation · diegosouzapw bundleUse when creating new Claude Code skills. Covers skill structure, YAML frontmatter, content organization, and testing skills with pressure scenarios.
- ▌ Skill Pipeline · diegosouzapw bundleリサーチから Skill/Subagent 作成までを1コマンドで実行するパイプライン。トピックを指定すると、Webリサーチ → ベストプラクティス抽出 → Skill/Subagent生成 → バリデーションまで自動実行。
- ▌ Skill Polisher · diegosouzapw bundleMeta-skill for Claude Code to validate and polish Codex skills under `.codex/skills/` by running the skill-polisher and reviewing structural integrity. Use when auditing Codex skills, enforcing standardization, or running integrity sweeps across the Codex skill set.
- ▌ Velvet Unicorn · diegosouzapw bundleQuery VelvetDAO Unicorn AI (/ask) for token analysis, wallet analysis, and trade analysis. Use when users ask about a token, a wallet, or “should I trade/buy/sell” and you want a structured {answer, txdata}.
- ▌ Writing Agents · diegosouzapw bundleUse when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool
- ▌ Xenodium Elisp · diegosouzapw bundleXenodium's Emacs packages: chatgpt-shell, agent-shell, dwim-shell-command, and ACP integration for modern Emacs development.
- ▌ XML To Compose · diegosouzapw bundleConvert Android XML layouts to Jetpack Compose. Use when asked to migrate XML layouts, convert views to composables, or help with Compose migration. Handles layouts, widgets, attributes, styles, and resource references.
- ▌ Abaqus Geometry · diegosouzapw bundleCreate and manipulate Abaqus geometry - parts, sketches, extrusions, CAD import. Use for any geometry creation task including box, cylinder, or STEP/IGES import.
- ▌
- ▌ Algorithmic Art · diegosouzapw bundleCriação de arte algorítmica usando p5.js com aleatoriedade semeada (seeded) e exploração interativa de parâmetros. Use quando os usuários solicitarem arte usando código, arte generativa, arte algorítmica, campos de fluxo ou sistemas de partículas. Crie arte algorítmica original em vez de copiar o trabalho de artistas existentes para evitar violações de direitos autorais.
- ▌ Codex Implement · diegosouzapw bundleDelegate complex implementation tasks to Codex. Use when user says codex implement, delegate implementation, or has a complex coding task.
- ▌ Design Iterator · diegosouzapw bundleIteratively refines UI design through N screenshot-analyze-improve cycles. Use PROACTIVELY when design changes aren't coming together after 1-2 attempts, or when user requests iterative refinement.
- ▌ Design Patterns · diegosouzapw bundleBK-CI 项目设计模式实践指南,涵盖工厂模式、策略模式、观察者模式、装饰器模式、模板方法等在项目中的实际应用。当用户学习设计模式、重构代码、设计可扩展架构或理解项目设计时使用。
- ▌ Design Strategy · diegosouzapw bundleStrategic alignment of design initiatives with business goals using the TRACES framework. Use when (1) aligning design projects with corporate strategy, (2) identifying and mitigating external threats (Technical Debt, Regulatory, Audience, Competition, Economic, Substitute Technology), (3) assessing design maturity/capability, (4) structuring design teams for specific outcomes, (5) managing designer career growth, or (6) communicating design value (ROI, ESG, business outcomes) to senior leadership.
- ▌ Epic Management · diegosouzapw bundleUse for LARGE work requiring feature-level grouping. Creates epic tracking issues, manages related issues under a common label, tracks epic progress, and coordinates with milestones.
- ▌ Ethics Reviewer · diegosouzapw bundleThis skill should be used when the user mentions "dark patterns", "accessibility", "a11y", "privacy", "tracking", "analytics", "notifications", "user data", "GDPR", "consent", "manipulation", "sustainability", "performance budget", or when building user-facing features that collect data, send notifications, display urgency, or gate access. Addresses ethical constraints in software design — manipulation, accessibility, privacy, and sustainability.
- ▌ Frontend Design · diegosouzapw bundleCreate distinctive, bold UI designs that avoid generic AI aesthetics. This skill should be used when users want frontend components with strong visual identity, creative typography, intentional color palettes, and production-grade animations - specifically to avoid the bland, safe, homogeneous "AI slop" that plagues most generated interfaces.
- ▌ Go Microservice · diegosouzapw bundleThis skill should be used when the user asks to "создать микросервис", "добавить домен", "имплементировать фичу", "использовать Uber FX", "создать репозиторий", "добавить gRPC endpoint", "добавить HTTP endpoint", "создать воркер", "составь план создания микросервиса", "использовать внутренние пакеты", "настроить kafka/redis/postgres/кафку/редис/постгрес", mentions "service_template", "shared", or needs guidance on Go microservice architecture, domain-driven design patterns, or backend development.
- ▌ MCP Tool Design · diegosouzapw bundleThis skill should be used when the user asks to "define a tool", "create tool schema", "design inputSchema", "add tool annotations", "handle file uploads", "tool descriptions", "tool naming", or needs guidance on designing MCP tools for the OpenAI Apps SDK including schemas, annotations, and best practices.
- ▌ Spec Driven Dev · diegosouzapw bundle基于 OpenSpec 规范的开发专家。负责全生命周期管理:初始化项目、创建变更提案 (Proposal)、制定规范 (Specs)、技术设计 (Design) 及任务规划 (Tasks)。严格遵守 OpenSpec 目录结构与工作流。
- ▌ Swarm Dashboard · diegosouzapw bundleLive real-time dashboard for monitoring AI agent swarms with smart completion detection, clickable agent detail views, idle time tracking, and activity streaming. Auto-launches a beautiful web UI. V6 features embedded HTML, line-by-line JSON parsing, and capybara-inspired colors.
- ▌ Vibe Techdesign · diegosouzapw bundleCreate a Technical Design Document for your MVP. Use when the user wants to plan architecture, choose tech stack, or says "plan technical design", "choose tech stack", or "how should I build this".
- ▌ 10x Vision · diegosouzapw bundleStrategic amplification mode that reveals blind spots, untapped opportunities, and hidden leverage points in any business strategy, entrepreneurship idea, or creative content project. Cuts through noise to show what others miss.
- ▌ 3d Spatial · diegosouzapw bundleUse when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.
- ▌ Abaqus Odb · diegosouzapw bundleRead analysis results. Use when user asks about maximum stress, extracting displacements, reaction forces, or exporting results. Post-processes ODB files.
- ▌ Actionbook · diegosouzapw bundleThis skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors.
- ▌ Adb Magisk · diegosouzapw bundleMagisk Manager automation - app launching, module installation, Zygisk configuration
- ▌ Add Lesson · diegosouzapw bundleAdd a new lesson learned to shared rules and sync to context files.
- ▌ Add Member · diegosouzapw bundleInteractive guide for adding new lab members to the website. Gathers information via web research, helps write appropriate bios, optimizes images, and generates properly formatted member files. Use when adding new team members, updating member info, or marking members as alumni.
- ▌ Add Metric · diegosouzapw bundleAdd a new calculated metric to the VSM dashboard with test-first development
- ▌ Add Module · diegosouzapw bundleCreate a new core infrastructure module with standard API, lazy init, and proper structure
- ▌ Algorithms · diegosouzapw bundleMaster algorithm design, common patterns, optimization techniques, and problem-solving strategies. Learn to solve any computational challenge efficiently.
- ▌ Arch Skill · diegosouzapw bundleFormalize architecture planning into a single, iterative workflow and produce one canonical architecture document (no doc sprawl). Use for architectural changes, refactors, or new system design.
- ▌ Arch Guard · diegosouzapw bundle進行代碼重構或新增模組時觸發。確保程式碼符合 Clean Architecture + DDD + CQRS 的層次關係,防止架構腐化。
- ▌ Ask Claude · diegosouzapw bundleAsks Claude CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.
- ▌ Ask Expert · diegosouzapw bundleCreates expert consultation documents with code extraction, git diffs, and size tracking (125KB limit). Use when user asks to "create an expert consultation document", "prepare code for expert review", "gather architecture context", or needs comprehensive technical documentation for external analysis. Requires Node.js 18+.
- ▌ Async Drop · diegosouzapw bundleGuide to the AsyncDrop pattern for async cleanup in Rust. Use when working with AsyncDropGuard, implementing AsyncDrop trait, or handling async resource cleanup.
- ▌
- ▌ Beads Seed · diegosouzapw bundleTranslate architectural planning documents into actionable beads issue graph structure.
- ▌ Bug Fixing · diegosouzapw bundleSystematic debugging and bug fixing with Australian user-friendly messages
- ▌ C4 Context · diegosouzapw bundleExpert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies. Synthesizes container and component documentation with system documentation to create comprehensive context-level architecture. Use when creating the highest-level C4 system context documentation.
- ▌ Casing Law · diegosouzapw bundleThis skill should be used when the user is writing code with mixed casing conventions, choosing casing for identifiers, enforcing casing consistency across a codebase, or when camelCase and snake_case appear in the same file. Covers per-context casing rules, acronym handling, and the absolute prohibition of mixed conventions.
- ▌ Claude API · diegosouzapw bundleAnthropic Claude API integration for building AI-powered applications. Use when working with Anthropic's Messages API, Claude SDKs (Python or TypeScript), tool use/function calling, vision/image inputs, streaming responses, prompt caching, message batches, token counting, extended thinking, PDF processing, or any Claude API integration task.
- ▌ Clawdbites · diegosouzapw bundleExtract recipes from Instagram reels. Use when a user sends an Instagram reel link and wants to get the recipe from the caption. Parses ingredients, instructions, and macros into a clean format.
- ▌
- ▌ Clean Code · diegosouzapw bundlePragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments