hetzner-cloud-management

Connect to HeyReach for LinkedIn automation. Load when user mentions 'heyreach', 'linkedin outreach', 'linkedin campaigns', 'heyreach campaigns', 'add leads', 'campaign stats'. Meta-skill that validates config and routes to operations.

HeyReach LinkedIn automation integration. Load when user mentions 'heyreach', 'linkedin outreach', 'linkedin campaigns', 'list campaigns', 'add leads', 'campaign stats', or any LinkedIn automation operations.

Guidance for deploying HuggingFace models as inference APIs/services. This skill applies when tasks involve downloading pre-trained models from HuggingFace Hub, creating REST APIs for model inference, building Flask/FastAPI services around ML models, or setting up sentiment analysis, text classification, or other NLP inference endpoints.

>-

Design hook-based event systems for ADW observability. Use when implementing real-time event broadcasting, creating hook pipelines, or building agent activity monitoring.

React Hooks patterns including custom hooks and dependency management. Use when implementing component logic.

>-

Imported skill how_to_guide from openai

Angular 21+ functional HTTP interceptors for auth, error handling, loading states, retry logic, caching, and security best practices

Connect to HubSpot CRM for contact, company, deal, and engagement management. Load when user mentions 'hubspot', 'crm', 'contacts', 'companies', 'deals', 'list contacts', 'create contact', 'search deals', or any HubSpot CRM operations. Meta-skill that validates config, discovers CRM objects, and routes to appropriate operations.

Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.

Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods

Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization. Use when working with local LLMs, embeddings, or custom model training.

GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human subjects in recordings, or classify individuals with optional head covering detection.

Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.

HyJAX Relational Thinking Skill

Comprehensive Hyprland Wayland compositor configuration skill. Use when users need help with: (1) Creating or modifying Hyprland config files, (2) Setting up keybindings, window rules, monitors, or animations, (3) Troubleshooting Hyprland configuration issues, (4) Searching for valid config variables and values, (5) Understanding Hyprland syntax and structure, (6) Setting up multi-monitor configurations, (7) Configuring input devices, decorations, or layouts, or (8) Any other Hyprland-related configuration tasks.

Complete idea-to-exit pipeline for solo builders with 8 interconnected agents managing the entire product lifecycle

Transform bullet points into enhanced, prioritized items for MASTER_PLAN.md. Process ideas inbox and integrate with project tracking.

Extract the fundamental requirement from user requests before any research or implementation.

Extract quantities from IFC/Revit models for quantity takeoff. Uses DDC converters to get element counts, areas, volumes, lengths with grouping and reporting.

Creates image carousels with hover-activated auto-advance, touch swipe support, and animated progress indicators. Use when building image galleries, product showcases, or any multi-image display with navigation.

Image processing for basic edits and color adjustments. Use this skill when users request image operations like resize, rotate, crop, flip, or color adjustments (brightness, contrast, saturation). Supports both uploaded images and images from URLs.

Extract EXIF metadata from images including GPS coordinates, camera settings, and timestamps. Map photo locations and strip metadata for privacy.

Extract data from construction images using AI Vision. Analyze site photos, scanned documents, drawings

Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding

Upload images to Imgur for free hosting. Use this skill when you need to upload images and get public URLs for sharing or embedding in articles.

Master skill for generating immunopipe pipeline configurations. Determines pipeline architecture based on data type (scRNA-seq with or without scTCR/BCR-seq) and analysis requirements. Routes to individual process skills for detailed configuration. Use this skill when starting a new immunopipe configuration or modifying pipeline-level options.

Implement code using sonnet model with full main context access

Strategic guidance for operationalizing machine learning models from experimentation to production. Covers experiment tracking (MLflow, Weights & Biases), model registry and versioning, feature stores (Feast, Tecton), model serving patterns (Seldon, KServe, BentoML), ML pipeline orchestration (Kubeflow, Airflow), and model monitoring (drift detection, observability). Use when designing ML infrastructure, selecting MLOps platforms, implementing continuous training pipelines, or establishing model governance.

Set up RAG pipelines with document chunking, embedding generation, and retrieval strategies using LlamaIndex. Use when building new RAG systems, choosing chunking approaches, selecting embedding models, or implementing vector/hybrid retrieval for src/ or src-iLand/ pipelines.

Import existing markdown files into Kurt database. Fix ERROR records, bulk import files, link content to database.

Download skill content from Notion and create it locally in `03-skills/`.

Quality control of phasing and imputation results. Filter by INFO scores, assess accuracy, and prepare imputed data for downstream analysis. Use when filtering low-quality imputed variants or validating imputation accuracy before GWAS.

Manage Gmail inbox with AI-powered triage, cleanup, and restore. Use when the user mentions inbox, email triage, clean inbox, email cleanup, check email, email summary, delete emails, manage inbox, or wants to organize their email.

Workflow for processing large Things3 inboxes (100+ items) using LLM-driven confidence matching and intelligent automation. Integrates with personal taxonomy and MCP tools for efficient cleanup with self-improving pattern learning.

Build resilient data ingestion pipelines from APIs. Use when creating scripts that fetch paginated data from external APIs (Twitter, exchanges, any REST API) and need to track progress, avoid duplicates, handle rate limits, and support both incremental updates and historical backfills. Triggers: 'ingest data from API', 'pull tweets', 'fetch historical data', 'sync from X', 'build a data pipeline', 'fetch without re-downloading', 'resume the download', 'backfill older data'. NOT for: simple one-shot API calls, websocket/streaming connections, file downloads, or APIs without pagination.

Use when working with inductor components - adding inductor patterns, parsing inductor MPNs, extracting inductance values, current ratings, or package codes from inductor part numbers.

Infrastructure, DevOps, and platform reliability

>

>

Unified atomic ingestion of CFN dependency manifests (trigger-dev, cli-mode, shared)

Create or update CLAUDE.md file for this project. Use when initializing a project for Claude Code, or when project structure/architecture has significantly changed.

Use when starting a new session without feature-list.json, setting up project structure, or breaking down requirements into atomic features. Load in INIT state. Detects project type (Python/Node/Django/FastAPI), creates feature-list.json with priorities, initializes .claude/progress/ tracking.

Achieve and maintain low input latency by engineering event-to-render pipelines.

You are an expert in the Instagram US Reels search pipeline for this influencer discovery platform. This skill provides comprehensive knowledge about search providers, rate limits, normalization logic

Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extraction, structured generation, and type-safe LLM responses.

Use when defining events, fields, and governance for GTM analytics pipelines.

This skill should be used when integrating OpenAI Agents SDK with FastAPI, building message arrays from database history, running agents with MCP tools, parsing tool calls, executing them, and saving conversations to the database.