@vodailoc/kilo-kit-mcp 1.1.0

package/skills/SKILLS_INDEX.md

@@ -0,0 +1,139 @@
+# Skills Index
+
+Lightweight index for agents. Load only the `SKILL.md` files relevant to the task.
+
+Total imported skills: 114
+
+## agent-frameworks
+- `claukit` -> `skills/agent-frameworks/claukit/SKILL.md`: Advanced Agentic Coding framework providing mission briefs, guardrails, and integration hints for complex tasks. This skill ensures high-quality output through disciplined automation and systematic workflows.
+
+## ai-media
+- `ai-multimodal` -> `skills/ai-media/ai-multimodal/SKILL.md`: Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
+- `geo-fundamentals` -> `skills/ai-media/geo-fundamentals/SKILL.md`: Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
+- `media-processing` -> `skills/ai-media/media-processing/SKILL.md`: Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
+- `screenshot` -> `skills/ai-media/screenshot/SKILL.md`: Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
+- `seo-fundamentals` -> `skills/ai-media/seo-fundamentals/SKILL.md`: SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
+- `sora` -> `skills/ai-media/sora/SKILL.md`: Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.
+
+## design
+- `aesthetic` -> `skills/design/aesthetic/SKILL.md`: Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.
+- `figma` -> `skills/design/figma/SKILL.md`: Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
+- `figma-implement-design` -> `skills/design/figma-implement-design/SKILL.md`: Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection.
+- `frontend-design` -> `skills/design/frontend-design/SKILL.md`: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
+- `mobile-design` -> `skills/design/mobile-design/SKILL.md`: Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.
+- `tailwind-patterns` -> `skills/design/tailwind-patterns/SKILL.md`: Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
+- `ui-styling` -> `skills/design/ui-styling/SKILL.md`: Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
+
+## engineering
+- `api-patterns` -> `skills/engineering/api-patterns/SKILL.md`: API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.
+- `app-builder` -> `skills/engineering/app-builder/SKILL.md`: Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
+- `architecture` -> `skills/engineering/architecture/SKILL.md`: Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
+- `aspnet-core` -> `skills/engineering/aspnet-core/SKILL.md`: Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.
+- `backend-development` -> `skills/engineering/backend-development/SKILL.md`: Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.
+- `better-auth` -> `skills/engineering/better-auth/SKILL.md`: Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.
+- `clean-code` -> `skills/engineering/clean-code/SKILL.md`: Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
+- `code-review` -> `skills/engineering/code-review/SKILL.md`: Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
+- `code-review-checklist` -> `skills/engineering/code-review-checklist/SKILL.md`: Code review guidelines covering code quality, security, and best practices.
+- `context-engineering` -> `skills/engineering/context-engineering/SKILL.md`: Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
+- `database-design` -> `skills/engineering/database-design/SKILL.md`: Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
+- `databases` -> `skills/engineering/databases/SKILL.md`: Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
+- `diagnose` -> `skills/engineering/diagnose/SKILL.md`: Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
+- `docs-seeker` -> `skills/engineering/docs-seeker/SKILL.md`: Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel
+- `frontend-dev-guidelines` -> `skills/engineering/frontend-development/SKILL.md`: Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
+- `i18n-localization` -> `skills/engineering/i18n-localization/SKILL.md`: Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
+- `improve-codebase-architecture` -> `skills/engineering/improve-codebase-architecture/SKILL.md`: Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
+- `lint-and-validate` -> `skills/engineering/lint-and-validate/SKILL.md`: Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
+- `nextjs-best-practices` -> `skills/engineering/nextjs-best-practices/SKILL.md`: Next.js App Router principles. Server Components, data fetching, routing patterns.
+- `nodejs-best-practices` -> `skills/engineering/nodejs-best-practices/SKILL.md`: Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.
+- `openai-docs` -> `skills/engineering/openai-docs/SKILL.md`: Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
+- `performance-profiling` -> `skills/engineering/performance-profiling/SKILL.md`: Performance profiling principles. Measurement, analysis, and optimization techniques.
+- `playwright` -> `skills/engineering/playwright/SKILL.md`: Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
+- `playwright-interactive` -> `skills/engineering/playwright-interactive/SKILL.md`: Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
+- `python-patterns` -> `skills/engineering/python-patterns/SKILL.md`: Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.
+- `react-patterns` -> `skills/engineering/react-patterns/SKILL.md`: Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
+- `render-deploy` -> `skills/engineering/render-deploy/SKILL.md`: Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.
+- `repomix` -> `skills/engineering/repomix/SKILL.md`: Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
+- `setup-matt-pocock-skills` -> `skills/engineering/setup-matt-pocock-skills/SKILL.md`: Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
+- `shopify` -> `skills/engineering/shopify/SKILL.md`: Build Shopify applications, extensions, and themes using GraphQL/REST APIs, Shopify CLI, Polaris UI components, and Liquid templating. Capabilities include app development with OAuth authentication, checkout UI extensions for customizing checkout flow, admin UI extensions for dashboard integration, POS extensions for retail, theme development with Liquid, webhook management, billing API integration, product/order/customer management. Use when building Shopify apps, implementing checkout customizations, creating admin interfaces, developing themes, integrating payment processing, managing store data via APIs, or extending Shopify functionality.
+- `tdd` -> `skills/engineering/tdd/SKILL.md`: Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
+- `tdd-workflow` -> `skills/engineering/tdd-workflow/SKILL.md`: Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.
+- `testing-patterns` -> `skills/engineering/testing-patterns/SKILL.md`: Testing patterns and principles. Unit, integration, mocking strategies.
+- `to-issues` -> `skills/engineering/to-issues/SKILL.md`: Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
+- `to-prd` -> `skills/engineering/to-prd/SKILL.md`: Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
+- `triage` -> `skills/engineering/triage/SKILL.md`: Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
+- `vulnerability-scanner` -> `skills/engineering/vulnerability-scanner/SKILL.md`: Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.
+- `webapp-testing` -> `skills/engineering/webapp-testing/SKILL.md`: Web application testing principles. E2E, Playwright, deep audit strategies.
+- `web-frameworks` -> `skills/engineering/web-frameworks/SKILL.md`: Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined/filled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.
+- `write-a-skill` -> `skills/engineering/write-a-skill/SKILL.md`: Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
+
+## games
+- `2d-games` -> `skills/games/2d-games/SKILL.md`: 2D game development principles. Sprites, tilemaps, physics, camera.
+- `3d-games` -> `skills/games/3d-games/SKILL.md`: 3D game development principles. Rendering, shaders, physics, cameras.
+- `game-art` -> `skills/games/game-art/SKILL.md`: Game art principles. Visual style selection, asset pipeline, animation workflow.
+- `game-audio` -> `skills/games/game-audio/SKILL.md`: Game audio principles. Sound design, music integration, adaptive audio systems.
+- `game-design` -> `skills/games/game-design/SKILL.md`: Game design principles. GDD structure, balancing, player psychology, progression.
+- `game-development` -> `skills/games/game-development/SKILL.md`: Game development orchestrator. Routes to platform-specific skills based on project needs.
+- `mobile-games` -> `skills/games/mobile-games/SKILL.md`: Mobile game development principles. Touch input, battery, performance, app stores.
+- `multiplayer` -> `skills/games/multiplayer/SKILL.md`: Multiplayer game development principles. Architecture, networking, synchronization.
+- `pc-games` -> `skills/games/pc-games/SKILL.md`: PC and console game development principles. Engine selection, platform features, optimization strategies.
+- `vr-ar` -> `skills/games/vr-ar/SKILL.md`: VR/AR development principles. Comfort, interaction, performance requirements.
+- `web-games` -> `skills/games/web-games/SKILL.md`: Web browser game development principles. Framework selection, WebGPU, optimization, PWA.
+
+## operations
+- `bash-linux` -> `skills/operations/bash-linux/SKILL.md`: Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
+- `chrome-devtools` -> `skills/operations/chrome-devtools/SKILL.md`: Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
+- `deployment-procedures` -> `skills/operations/deployment-procedures/SKILL.md`: Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
+- `devops` -> `skills/operations/devops/SKILL.md`: Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions, managing Docker containers and images, setting up CI/CD pipelines, optimizing cloud infrastructure costs, implementing global caching strategies, working with cloud databases, or building cloud-native applications.
+- `mcp-builder` -> `skills/operations/mcp-builder/SKILL.md`: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
+- `mcp-management` -> `skills/operations/mcp-management/SKILL.md`: Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
+- `powershell-windows` -> `skills/operations/powershell-windows/SKILL.md`: PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
+- `server-management` -> `skills/operations/server-management/SKILL.md`: Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.
+
+## problem-solving
+- `Collision-Zone Thinking` -> `skills/problem-solving/collision-zone-thinking/SKILL.md`: Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?
+- `Defense-in-Depth Validation` -> `skills/problem-solving/defense-in-depth/SKILL.md`: Validate at every layer data passes through to make bugs impossible
+- `Inversion Exercise` -> `skills/problem-solving/inversion-exercise/SKILL.md`: Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?
+- `Meta-Pattern Recognition` -> `skills/problem-solving/meta-pattern-recognition/SKILL.md`: Spot patterns appearing in 3+ domains to find universal principles
+- `Root Cause Tracing` -> `skills/problem-solving/root-cause-tracing/SKILL.md`: Systematically trace bugs backward through call stack to find original trigger
+- `Scale Game` -> `skills/problem-solving/scale-game/SKILL.md`: Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
+- `sequential-thinking` -> `skills/problem-solving/sequential-thinking/SKILL.md`: Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
+- `Simplification Cascades` -> `skills/problem-solving/simplification-cascades/SKILL.md`: Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z
+- `systematic-debugging` -> `skills/problem-solving/systematic-debugging/SKILL.md`: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
+- `When Stuck - Problem-Solving Dispatch` -> `skills/problem-solving/when-stuck/SKILL.md`: Dispatch to the right problem-solving technique based on how you're stuck
+
+## productivity
+- `brainstorming` -> `skills/productivity/brainstorming/SKILL.md`: You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
+- `caveman` -> `skills/productivity/caveman/SKILL.md`: Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
+- `dispatching-parallel-agents` -> `skills/productivity/dispatching-parallel-agents/SKILL.md`: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
+- `executing-plans` -> `skills/productivity/executing-plans/SKILL.md`: Use when you have a written implementation plan to execute in a separate session with review checkpoints
+- `finishing-a-development-branch` -> `skills/productivity/finishing-a-development-branch/SKILL.md`: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
+- `grill-me` -> `skills/productivity/grill-me/SKILL.md`: Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
+- `grill-with-docs` -> `skills/productivity/grill-with-docs/SKILL.md`: Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
+- `parallel-agents` -> `skills/productivity/parallel-agents/SKILL.md`: Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
+- `plan-writing` -> `skills/productivity/plan-writing/SKILL.md`: Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
+- `receiving-code-review` -> `skills/productivity/receiving-code-review/SKILL.md`: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
+- `requesting-code-review` -> `skills/productivity/requesting-code-review/SKILL.md`: Use when completing tasks, implementing major features, or before merging to verify work meets requirements
+- `subagent-driven-development` -> `skills/productivity/subagent-driven-development/SKILL.md`: Use when executing implementation plans with independent tasks in the current session
+- `test-driven-development` -> `skills/productivity/test-driven-development/SKILL.md`: Use when implementing any feature or bugfix, before writing implementation code
+- `using-git-worktrees` -> `skills/productivity/using-git-worktrees/SKILL.md`: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
+- `using-superpowers` -> `skills/productivity/using-superpowers/SKILL.md`: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
+- `verification-before-completion` -> `skills/productivity/verification-before-completion/SKILL.md`: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
+- `writing-plans` -> `skills/productivity/writing-plans/SKILL.md`: Use when you have a spec or requirements for a multi-step task, before touching code
+- `writing-skills` -> `skills/productivity/writing-skills/SKILL.md`: Use when creating new skills, editing existing skills, or verifying skills work before deployment
+- `zoom-out` -> `skills/productivity/zoom-out/SKILL.md`: Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
+
+## security
+- `red-team-tactics` -> `skills/security/red-team-tactics/SKILL.md`: Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.
+
+## writing-docs
+- `behavioral-modes` -> `skills/writing-docs/behavioral-modes/SKILL.md`: AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
+- `doc` -> `skills/writing-docs/doc/SKILL.md`: Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.
+- `documentation-templates` -> `skills/writing-docs/documentation-templates/SKILL.md`: Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.
+- `docx` -> `skills/writing-docs/docx/SKILL.md`: Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
+- `mermaidjs-v11` -> `skills/writing-docs/mermaidjs-v11/SKILL.md`: Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.
+- `pdf` -> `skills/writing-docs/pdf/SKILL.md`: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
+- `pptx` -> `skills/writing-docs/pptx/SKILL.md`: Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
+- `slides` -> `skills/writing-docs/slides/SKILL.md`: Create and edit presentation slide decks (`.pptx`) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.
+- `templates` -> `skills/writing-docs/templates/SKILL.md`: Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.
+- `template-skill` -> `skills/writing-docs/template-skill/SKILL.md`: A template for creating new modular and scalable agent skills.
+- `xlsx` -> `skills/writing-docs/xlsx/SKILL.md`: Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

package/skills/agent-frameworks/claukit/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: claukit
+description: Advanced Agentic Coding framework providing mission briefs, guardrails, and integration hints for complex tasks. This skill ensures high-quality output through disciplined automation and systematic workflows.
+---
+
+# Claukit - Advanced Agentic Coding
+
+Claukit là meta-skill điều phối được căn chỉnh theo hệ sinh thái ClaudeKit Skills. Trong cài đặt local này, `claukit` đóng vai trò wrapper/orchestrator cho các skill đang có sẵn, chứ không phải một upstream skill độc lập.
+
+## Source
+
+- Public source tham chiếu: `https://github.com/mrgoonie/claudekit-skills`
+- Gốc ý tưởng: ClaudeKit Skills dùng mô hình `mission briefs + guardrails + integration hints` để điều phối các skill chuyên biệt.
+- Vai trò local: nối triết lý đó với bộ skill hiện có trong `C:\Users\Admin\.gemini\antigravity\skills\` và các junction của Codex.
+
+## 🎯 Khi nào sử dụng Skill này
+
+Sử dụng khi:
+- Người dùng nhắc đến `claukit`, `ClaudeKit`, hoặc muốn làm việc theo phong cách ClaudeKit.
+- Tác vụ cần phối hợp nhiều skill thay vì chỉ một domain skill đơn lẻ.
+- Dự án có nhiều pha: thiết kế, lập kế hoạch, thực thi, review, verification.
+- Cần giữ cùng một bộ tiêu chuẩn xuyên suốt giữa nhiều subagents hoặc nhiều lần handoff.
+- Cần giảm context bloat bằng cách chỉ tải đúng skill và references cần thiết.
+
+## 🛠 Hướng dẫn thực hiện (Quy trình bắt buộc)
+
+1. **Đọc Mission Briefs**: Mở `references/mission-briefs.md` để chốt nguyên tắc vận hành và ưu tiên tổng thể.
+2. **Đọc Guardrails**: Mở `references/guardrails.md` để biết các ranh giới bắt buộc trước khi phân tích hay sửa code.
+3. **Đọc Integration Hints**: Mở `references/integration-hints.md` để chọn đúng chain skill cho task hiện tại.
+4. **Chọn skill tối thiểu cần thiết**: Dùng `references/skills-directory.md` để chọn 1-3 skill phù hợp nhất thay vì bật cả hệ thống.
+5. **Bắt buộc đọc SKILL.md của skill được chọn**: Claukit không thay thế skill chuyên biệt. Nó chỉ điều phối.
+6. **Giữ progressive disclosure**: Chỉ đọc thêm references hoặc scripts khi task thực sự cần.
+7. **Re-check guardrails trước khi kết luận xong việc**: Đặc biệt trước khi claim “đã fix”, “đã pass”, hoặc “đã hoàn tất”.
+
+## Operating Rules
+
+- **User instructions thắng Claukit**: Nếu user yêu cầu khác với workflow mặc định, làm theo user.
+- **Không bịa upstream**: Không nói repo công khai có skill `claukit` riêng nếu thực tế không có. Local `claukit` là wrapper dựa trên ClaudeKit ecosystem.
+- **Không load catalog bừa bãi**: Chỉ chọn số skill nhỏ nhất giải được bài toán.
+- **Không thay domain skill**: Task backend vẫn phải đọc `backend-development`; task debug vẫn phải đọc `systematic-debugging`; task UI vẫn phải đọc `frontend-design` hoặc `aesthetic`.
+- **Không bỏ verification**: Khi đã có code/test/build liên quan, phải có bước xác minh thực tế trước khi báo xong.
+
+## 📂 Danh mục Kỹ năng & Tài liệu
+
+### Core references
+
+- [**Mission Briefs**](references/mission-briefs.md): Triết lý vận hành Claukit/ClaudeKit trong local environment.
+- [**Guardrails**](references/guardrails.md): Giới hạn bắt buộc về context, chất lượng, bảo mật và tính chính xác.
+- [**Integration Hints**](references/integration-hints.md): Skill chains khuyến nghị cho UI, backend, debugging, research.
+- [**Skills Directory**](references/skills-directory.md): Danh mục rút gọn các skill local nên phối hợp với Claukit.
+
+### Typical chains
+
+- `claukit -> brainstorming -> writing-plans -> subagent-driven-development -> code-review -> verification-before-completion`
+- `claukit -> systematic-debugging -> root-cause-tracing/defense-in-depth -> verification-before-completion`
+- `claukit -> frontend-design -> aesthetic -> ui-styling -> chrome-devtools`
+- `claukit -> backend-development -> databases -> better-auth -> devops`
+- `claukit -> docs-seeker -> repomix -> mermaidjs-v11`
+
+---
+*Lưu ý: Claukit là skill điều phối. Chất lượng đầu ra phụ thuộc vào việc chọn đúng skill chuyên biệt và tuân thủ guardrails.*

package/skills/agent-frameworks/claukit/references/guardrails.md

@@ -0,0 +1,42 @@
+# Guardrails - Ranh giới bắt buộc của Claukit
+
+## 1. Không bịa nguồn gốc
+
+- Không tuyên bố GitHub có upstream skill `claukit` độc lập nếu thực tế chỉ có ecosystem `ClaudeKit Skills`.
+- Khi cần nêu source, dùng repo công khai: `https://github.com/mrgoonie/claudekit-skills`.
+
+## 2. Không context bloat
+
+- Không đọc toàn bộ catalog skill nếu chỉ cần 1-3 skill.
+- Không mở toàn bộ references của một skill nếu chưa có nhu cầu cụ thể.
+- Không biến Claukit thành “super prompt” thay cho skill chuyên biệt.
+
+## 3. Bắt buộc đọc skill được chọn
+
+- Nếu Claukit điều phối đến skill khác, phải đọc `SKILL.md` của skill đó trước khi hành động.
+- Nếu skill đó dẫn đến references/scripts, chỉ mở phần cần thiết cho task.
+
+## 4. User instructions thắng workflow mặc định
+
+- User yêu cầu cụ thể luôn có độ ưu tiên cao hơn style guide mặc định.
+- Khi có mâu thuẫn, giải thích ngắn gọn và làm theo yêu cầu của user nếu an toàn.
+
+## 5. Verification trước completion
+
+- Không được báo “xong”, “đã fix”, “đã pass” nếu chưa có xác minh tương ứng.
+- Với coding task: ít nhất phải nêu rõ đã chạy hay chưa chạy test/build/lint/command liên quan.
+
+## 6. Security và safety
+
+- Không để lộ secrets/API keys/credentials.
+- Dùng `.env` hoặc secret store phù hợp.
+- Không đề xuất command phá hủy hoặc thay đổi diện rộng nếu chưa xác nhận rõ target.
+
+## 7. Quality bar theo ngữ cảnh
+
+- UI task: đòi hỏi hierarchy rõ, responsive, không placeholder giả.
+- Backend task: đòi hỏi correctness, validation, idempotency khi phù hợp.
+- Debug task: bắt buộc truy nguyên nhân gốc trước khi sửa.
+
+---
+*Nếu vi phạm một guardrail, Claukit phải dừng lại và chỉnh lại workflow trước khi tiếp tục.*

package/skills/agent-frameworks/claukit/references/integration-hints.md

@@ -0,0 +1,67 @@
+# Integration Hints - Skill chaining theo ClaudeKit style
+
+## Chain chuẩn cho feature delivery
+
+`claukit -> brainstorming -> writing-plans -> subagent-driven-development hoặc executing-plans -> code-review -> verification-before-completion`
+
+Dùng khi:
+- bắt đầu feature mới
+- có nhiều bước phân tích, code, review
+- cần workflow chặt và nhất quán
+
+## Chain cho debugging
+
+`claukit -> systematic-debugging -> root-cause-tracing hoặc defense-in-depth -> verification-before-completion`
+
+Dùng khi:
+- có bug khó
+- test flake
+- hành vi lệch nhưng chưa rõ nguyên nhân
+
+## Chain cho UI/UX
+
+`claukit -> frontend-design -> aesthetic -> ui-styling -> chrome-devtools`
+
+Dùng khi:
+- build landing page, dashboard, component library
+- cần visual polish hoặc interaction quality
+- cần kiểm tra giao diện bằng browser tooling
+
+## Chain cho backend/platform
+
+`claukit -> backend-development -> databases -> better-auth -> devops`
+
+Dùng khi:
+- thiết kế API/backend service
+- thêm auth, data model, deployment concerns
+- cần giữ consistency giữa domain logic và infra
+
+## Chain cho research/docs
+
+`claukit -> docs-seeker -> repomix -> mermaidjs-v11`
+
+Dùng khi:
+- cần đọc docs mới nhất
+- cần phân tích repo bên ngoài
+- cần biến findings thành sơ đồ hoặc tài liệu
+
+## Mapping theo nhóm skill local
+
+| Nhóm nhu cầu | Skill local nên ưu tiên |
+| :--- | :--- |
+| Orchestration | `brainstorming`, `writing-plans`, `subagent-driven-development`, `executing-plans` |
+| Quality gates | `code-review`, `systematic-debugging`, `verification-before-completion` |
+| Frontend | `frontend-design`, `aesthetic`, `ui-styling`, `web-frameworks` |
+| Backend | `backend-development`, `databases`, `better-auth`, `devops` |
+| Research & tooling | `docs-seeker`, `repomix`, `chrome-devtools`, `mcp-management` |
+| Advanced reasoning | `sequential-thinking`, `problem-solving/*` |
+
+## Gợi ý chọn skill
+
+- Chọn chain ngắn nhất giải được task.
+- Nếu task chỉ là debug, đừng kéo cả planning chain vào.
+- Nếu task chỉ là design review, đừng gọi backend skill.
+- Nếu task đã ở giữa một workflow superpowers, Claukit nên bổ trợ chứ không reset lại toàn bộ flow.
+
+---
+*Claukit hiệu quả nhất khi nó chọn đúng chain, không phải chain dài nhất.*

package/skills/agent-frameworks/claukit/references/mission-briefs.md

@@ -0,0 +1,38 @@
+# Mission Briefs - Chiến lược Vận hành Claukit
+
+Tài liệu này cập nhật `claukit` local theo tinh thần của `mrgoonie/claudekit-skills`: dùng skill chuyên biệt, progressive disclosure và workflow kỷ luật thay vì dồn mọi thứ vào một prompt lớn.
+
+## Mục tiêu cốt lõi
+
+### 1. Skill-first orchestration
+- Mỗi task phải đi qua skill phù hợp nhất, không giải quyết tất cả bằng meta-prompt.
+- `claukit` chỉ điều phối và chọn workflow; implementation vẫn thuộc về domain skill.
+
+### 2. Progressive disclosure
+- Chỉ tải `SKILL.md`, references và scripts thực sự cần cho task.
+- Tránh context bloat bằng cách không đọc cả catalog skill hoặc cả repo nếu chưa cần.
+
+### 3. User intent first
+- User instructions có độ ưu tiên cao nhất.
+- Nếu workflow mặc định của Claukit mâu thuẫn với yêu cầu cụ thể của user, theo user.
+
+### 4. Verification over claims
+- Không claim đã xong, đã fix, đã pass nếu chưa có bằng chứng chạy thật.
+- Khi có build/test/lint/CLI liên quan, verification là bắt buộc.
+
+### 5. Cross-skill consistency
+- Các skill được chain phải có cùng mục tiêu, cùng tiêu chuẩn naming, cùng quality bar.
+- Khi handoff giữa skills hoặc subagents, cần giữ rõ assumptions, file ownership, verification criteria.
+
+### 6. Local-first compatibility
+- Ưu tiên dùng các skill đã được cài local cho Codex/Gemini thay vì sao chép nguyên văn hướng dẫn chỉ dành cho Claude Code.
+- Dùng repo GitHub ClaudeKit làm nguồn tham chiếu công khai, nhưng ánh xạ vào toolchain local hiện tại.
+
+## Hệ quả thực thi
+
+- Task UI-heavy: ưu tiên chất lượng thị giác nhưng vẫn theo guardrails của dự án.
+- Task backend/debugging: ưu tiên correctness, traceability và validation.
+- Task lớn: phải tách thành workflow rõ ràng thay vì kích hoạt hàng loạt skill cùng lúc.
+
+---
+*Mission brief của Claukit là: đúng skill, đúng thứ tự, đúng bằng chứng.*

package/skills/agent-frameworks/claukit/references/skills-directory.md

@@ -0,0 +1,70 @@
+# Skills Directory - Danh mục rút gọn dùng với Claukit
+
+Tài liệu này không cố liệt kê mọi skill trong hệ thống. Nó chỉ gom các skill local có giá trị nhất khi `claukit` cần điều phối workflow.
+
+## Cách dùng
+
+1. Xác định task thuộc nhóm nào.
+2. Chọn 1 meta/process skill và 1-2 domain skill.
+3. Đọc `SKILL.md` của các skill đó trước khi tiếp tục.
+4. Chỉ mở references sâu hơn khi task cần.
+
+## 1. Orchestration & delivery
+
+| Skill | Khi nào dùng | Path |
+| :--- | :--- | :--- |
+| `claukit` | Điều phối workflow nhiều skill, bám theo ClaudeKit style | `claukit/SKILL.md` |
+| `brainstorming` | Làm rõ yêu cầu, thiết kế trước khi code | `superpowers-core/brainstorming/SKILL.md` |
+| `writing-plans` | Viết implementation plan chi tiết | `superpowers-core/writing-plans/SKILL.md` |
+| `subagent-driven-development` | Thực thi plan bằng nhiều worker/review gate | `superpowers-core/subagent-driven-development/SKILL.md` |
+| `executing-plans` | Chạy plan theo batch/checkpoint | `superpowers-core/executing-plans/SKILL.md` |
+| `using-git-worktrees` | Tách môi trường làm việc an toàn | `superpowers-core/using-git-worktrees/SKILL.md` |
+
+## 2. Quality & debugging
+
+| Skill | Khi nào dùng | Path |
+| :--- | :--- | :--- |
+| `code-review` | Review kỹ thuật, nhận hoặc yêu cầu review | `code-review/SKILL.md` |
+| `systematic-debugging` | Debug theo quy trình, không nhảy vào sửa ngay | `superpowers-core/systematic-debugging/SKILL.md` |
+| `verification-before-completion` | Gate cuối trước khi claim hoàn tất | `superpowers-core/verification-before-completion/SKILL.md` |
+| `root-cause-tracing` | Truy nguyên nhân gốc | `debugging/root-cause-tracing/SKILL.md` |
+| `defense-in-depth` | Chặn bug ở nhiều lớp | `debugging/defense-in-depth/SKILL.md` |
+
+## 3. Product & application skills
+
+| Skill | Khi nào dùng | Path |
+| :--- | :--- | :--- |
+| `frontend-design` | UI/UX khác biệt, component/page production-grade | `frontend-design/SKILL.md` |
+| `aesthetic` | Nâng quality thị giác và micro-interactions | `aesthetic/SKILL.md` |
+| `ui-styling` | Tailwind, shadcn/ui, design system | `ui-styling/SKILL.md` |
+| `web-frameworks` | Next.js, full-stack web app structure | `web-frameworks/SKILL.md` |
+| `backend-development` | API, services, security, performance | `backend-development/SKILL.md` |
+| `databases` | Schema/query/index/ops cho PostgreSQL và MongoDB | `databases/SKILL.md` |
+| `better-auth` | Auth/authz flow | `better-auth/SKILL.md` |
+| `devops` | Deploy, infra, containers, cloud | `devops/SKILL.md` |
+
+## 4. Research, docs, and tooling
+
+| Skill | Khi nào dùng | Path |
+| :--- | :--- | :--- |
+| `docs-seeker` | Tìm docs mới nhất và source chính thống | `docs-seeker/SKILL.md` |
+| `repomix` | Đóng gói repo để phân tích | `repomix/SKILL.md` |
+| `chrome-devtools` | Browser automation, perf, snapshots | `chrome-devtools/SKILL.md` |
+| `mcp-management` | Tìm và dùng MCP tools/resources đúng cách | `mcp-management/SKILL.md` |
+| `mermaidjs-v11` | Vẽ sơ đồ, flow, architecture docs | `mermaidjs-v11/SKILL.md` |
+
+## 5. Advanced reasoning
+
+| Skill | Khi nào dùng | Path |
+| :--- | :--- | :--- |
+| `sequential-thinking` | Bài toán nhiều bước, scope chưa rõ | `sequential-thinking/SKILL.md` |
+| `problem-solving/*` | Cần đổi góc nhìn hoặc phá bế tắc | `problem-solving/ABOUT.md` |
+| `context-engineering` | Tối ưu context và multi-agent flows | `context-engineering/SKILL.md` |
+
+## Public source reference
+
+- GitHub ecosystem reference: `https://github.com/mrgoonie/claudekit-skills`
+- Local root: `C:\Users\Admin\.gemini\antigravity\skills\`
+
+---
+*Claukit nên chọn ít skill nhưng đúng skill. Đó là điểm khác biệt giữa orchestration và context spam.*

package/skills/ai-media/ai-multimodal/.env.example

@@ -0,0 +1,97 @@
+# Google Gemini API Configuration
+
+# ============================================================================
+# OPTION 1: Google AI Studio (Default - Recommended for most users)
+# ============================================================================
+# Get your API key: https://aistudio.google.com/apikey
+GEMINI_API_KEY=your_api_key_here
+
+# ============================================================================
+# OPTION 2: Vertex AI (Google Cloud Platform)
+# ============================================================================
+# Uncomment these lines to use Vertex AI instead of Google AI Studio
+# GEMINI_USE_VERTEX=true
+# VERTEX_PROJECT_ID=your-gcp-project-id
+# VERTEX_LOCATION=us-central1
+
+# ============================================================================
+# Model Selection (Optional)
+# ============================================================================
+# Override default model for specific tasks
+# Default: gemini-2.5-flash for most tasks
+# GEMINI_MODEL=gemini-2.5-flash
+# GEMINI_IMAGE_GEN_MODEL=gemini-2.5-flash-image
+
+# ============================================================================
+# Rate Limiting Configuration (Optional)
+# ============================================================================
+# Requests per minute limit (adjust based on your tier)
+# GEMINI_RPM_LIMIT=15
+
+# Tokens per minute limit
+# GEMINI_TPM_LIMIT=4000000
+
+# Requests per day limit
+# GEMINI_RPD_LIMIT=1500
+
+# ============================================================================
+# Processing Options (Optional)
+# ============================================================================
+# Video resolution mode: default or low-res
+# low-res uses ~100 tokens/second vs ~300 for default
+# GEMINI_VIDEO_RESOLUTION=default
+
+# Audio quality: default (16 Kbps mono, auto-downsampled)
+# GEMINI_AUDIO_QUALITY=default
+
+# PDF processing mode: inline (<20MB) or file-api (>20MB, automatic)
+# GEMINI_PDF_MODE=auto
+
+# ============================================================================
+# Retry Configuration (Optional)
+# ============================================================================
+# Maximum retry attempts for failed requests
+# GEMINI_MAX_RETRIES=3
+
+# Initial retry delay in seconds (uses exponential backoff)
+# GEMINI_RETRY_DELAY=1
+
+# ============================================================================
+# Output Configuration (Optional)
+# ============================================================================
+# Default output directory for generated images
+# OUTPUT_DIR=./output
+
+# Image output format (png or jpeg)
+# IMAGE_FORMAT=png
+
+# Image quality for JPEG (1-100)
+# IMAGE_QUALITY=95
+
+# ============================================================================
+# Context Caching (Optional)
+# ============================================================================
+# Enable context caching for repeated queries on same file
+# GEMINI_ENABLE_CACHING=true
+
+# Cache TTL in seconds (default: 1800 = 30 minutes)
+# GEMINI_CACHE_TTL=1800
+
+# ============================================================================
+# Logging (Optional)
+# ============================================================================
+# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
+# LOG_LEVEL=INFO
+
+# Log file path
+# LOG_FILE=./logs/gemini.log
+
+# ============================================================================
+# Notes
+# ============================================================================
+# 1. Never commit API keys to version control
+# 2. Add .env to .gitignore
+# 3. API keys can be restricted in Google Cloud Console
+# 4. Monitor usage at: https://aistudio.google.com/apikey
+# 5. Free tier limits: 15 RPM, 1M-4M TPM, 1,500 RPD
+# 6. Vertex AI requires GCP authentication via gcloud CLI