分析

Analyzes content marketing metrics to identify top performers, trends, and optimization opportunities. Use when reviewing blog posts, social media, or campaign performance. Accepts CSV data with engagement metrics and provides actionable insights.

Use when designing animations for enterprise software, B2B platforms, admin dashboards, or corporate applications

Automatically convert uploaded data (CSV, Excel, JSON) into complete interactive dashboards with zero user input required. Detects patterns in PPC reports, sales data, analytics exports, and business metrics - then generates insights, recommendations, and visualizations instantly. Works seamlessly with CURV design system for on-brand outputs with tabs, funnels, filters, and multi-view layouts.

Systematic error fixing workflow for Dashboard Link SaaS. Use when user says "fix all errors", "resolve errors", "fix the build", "make it work", "troubleshoot", or when encountering TypeScript errors, lint errors, build failures, test failures, or runtime errors. Provides step-by-step debugging and resolution strategies.

Comprehensive guide for following the Zapier-style architecture patterns in Dashboard Link SaaS. Use when implementing new features, adding integrations, refactoring code, or when user says "follow the architecture", "use proper patterns", "implement like Zapier", "add a new plugin", or any architecture-related requests.

Orchestrates EUFM monetization: pricing strategy, funnel optimization,revenue projections, and marketing execution. Targets €50K bootstrap in30 days and €4.5M-12M ARR within 12 months by testing pricing models,tracking customer acquisition metrics, and aligning constitutional guardrailswith data-driven growth tactics.

Advanced visibility analysis using head pose, face mesh, and temporal patterns. Use for face-visible vs body-only breakdowns.

Create dbt models following FF Analytics Kimball patterns and 2×2 stat model. This skill should be used when creating staging models, core facts/dimensions, or analytical marts. Guides through model creation with proper grain, tests, External Parquet configuration, and per-model YAML documentation using dbt 1.10+ syntax.

Expert in FFmpeg-based video creation and editing. **Use when users request to extract, cut, trim, or clip segments from videos (e.g., "first 5 minutes", "extract from 1:30 to 2:45"), create video montages, apply transitions, process/extract/add audio, convert video/audio formats, optimize for platforms, or any video/audio manipulation using ffmpeg, sox, ffprobe, and related media tools.** Trigger on keywords: extract, cut, trim, clip, segment, video, audio, convert, montage, transition, ffmpeg.

Comprehensive guide for ActivityWatch setup, configuration, watchers, integrations, API usage, and automation. Covers aw-qt, aw-watcher modules, aw-client libraries, aw-sync, data export, MCP server integration, and package managers. Use when working with ActivityWatch components, creating custom watchers, querying data, setting up sync, integrating with analytics dashboards, or using the ActivityWatch API.

Use when segmenting time-series into regimes, detecting structural breaks, or constructing context sets for few-shot learning. Covers GP-CPD algorithms, Matérn kernels, likelihood ratio tests, regime identification, market state transitions, volatility regime changes, and trend reversals in financial markets.

Image processing, object detection, segmentation, and vision models. Use for image classification, object detection, or visual analysis tasks.

LMS feature implementations including Browse Gradebook, Course Kanban, Communications, Statistics Module, MAP Analytics, Teacher Schedule, and Attendance System. Use this skill when implementing or modifying these features, understanding their data structures, or debugging feature-specific issues.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.

Monitor Proxmox infrastructure health and performance. Track node statistics, analyze resource utilization, and identify optimization opportunities across your cluster.

Generate and execute Python code to analyze large log datasets, detect patterns, and extract actionable insights

AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity.USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, generating continuation prompts, scoring feasibility risk, or adding editing metadata.PIPELINE POSITION: screenwriter → **production-validator** → imagine/arch-vINPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 promptsKEY FUNCTIONS: - Veo 3 feasibility validation with risk scoring (LOW/MEDIUM/HIGH/CRITICAL) - 8-second scene chunking with continuation prompts - Shot continuity tagging for editors - Technical optimization for AI-friendly alternatives

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 with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

Expert on integrating Shelby Protocol decentralized storage into applications. Helps with use case evaluation, architecture design, migration strategies, cost optimization, performance tuning for video streaming, AI training, data analytics, content delivery, and read-heavy workloads. Triggers on keywords integrate Shelby, decentralized storage integration, video streaming storage, AI training data, data analytics storage, migration to Shelby, storage architecture, content delivery, Shelby use case.

Vercel deployment using Vercel CLI for Next.js, React, Vue, static sites, and serverless functions. Includes project validation, deployment orchestration, environment management, domain configuration, and analytics integration. Use when deploying frontend applications, static sites, or serverless APIs, or when user mentions Vercel, Next.js deployment, serverless functions, or edge network.