Claude Skills by majiayu000

Use when writing HubSpot integration code in Nango - HubSpot-specific guidance on Search API for incremental syncs, property name variations, rate limits, and OAuth introspection

Search companies in HubSpot CRM by name or domain. Load when user says 'search companies', 'find company', 'lookup company', 'search for [company]'.

Search contacts in HubSpot CRM by email, name, or company. Load when user says 'search contacts', 'find contact', 'lookup contact', 'search for [name]'.

Search deals in HubSpot CRM by name or amount. Load when user says 'search deals', 'find deal', 'lookup deal', 'deals over $X', 'search for [deal]'.

Update an existing contact in HubSpot CRM. Load when user says 'update contact', 'edit contact', 'modify contact', 'change contact'. Requires contact ID.

Update an existing deal in HubSpot CRM. Load when user says 'update deal', 'edit deal', 'change deal stage', 'move deal', 'close deal'. Requires deal ID.

This skill should be used when the user asks to "build an AI assistant", "create a chatbot", "make an agent that does X for me", "design a copilot feature", "automate this workflow with AI", or requests delegation-style AI features. Offers a reframe from copilot patterns (conversation, delegation) to HUD patterns (ambient awareness, perception augmentation).

Project dashboard that guides you through setup and tracks progress

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Create, configure, and deploy Hugging Face Spaces for showcasing ML models. Supports Gradio, Streamlit, and Docker SDKs with templates for common use cases like chat interfaces, image generation, and model comparisons.

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

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

Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.

A set of resources to help me write blog posts for hugozhu.site

This skill should be used when checking Hugo content for consistency issues, validating internal references, detecting duplicate content, verifying frontmatter completeness, and ensuring proper naming conventions. Use this skill to audit content quality, fix broken links, and maintain consistency across a Hugo site.

Help met Hugo templates, shortcodes en debugging. Gebruik bij Hugo-gerelateerde vragen, template problemen, of wanneer de gebruiker hulp nodig heeft met Hugo.

UX/UI specialist auditing Hugo layouts, components, navigation, and interactions against the Tone & Voice Guide. Ensures designs embody intimacy, consent-forward principles, mystery, sensuality, and inclusive accessibility.

This skill provides comprehensive knowledge for building static websites with Hugo static site generator. It should be used when setting up Hugo projects (blogs, documentation sites, landing pages, portfolios), integrating Tailwind CSS v4 for custom styling, integrating headless CMS systems (Sveltia CMS or TinaCMS), deploying to Cloudflare Workers with Static Assets, configuring themes and templates, and preventing common Hugo setup errors. Use this skill when encountering these scenarios: s...

HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to enable.

Stream Hulu content, manage watchlist, and access live TV features

Guide for creating Huma API endpoints following this project's conventions including routing, input/output structs, error handling, and OpenAPI documentation.

Generates role-based human documentation (<1000 words per doc). Use when epics complete, breaking changes occur, or architecture decisions are made. Creates guides for developers, QA, DevOps, and business stakeholders.

Creates human-friendly documentation from AI context documentation. Transforms detailed AI documentation in ai/ folder into digestible summaries, quick starts, and visual diagrams in docs/ folder. Use when users need to quickly understand complex systems or when AI documentation is too detailed for human consumption. Specializes in Mermaid diagrams, executive summaries, and quick reference guides.

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.

Instrument human approval workflows, feedback loops, and escalations

Transform AI-sounding text into natural, human-like writing by applying proven linguistic patterns and stylistic techniques. Use when text needs to sound more conversational, authentic, and less robotic - especially for essays, assignments, professional writing, blog posts, emails, or any content where human voice matters. Applies sentence variation, natural phrasing, contractions, personal voice, and removes AI tell-tale patterns.

Write content that sounds natural, conversational, and authentically human - avoiding AI-generated patterns, corporate speak, and generic phrasing

Remove signs of AI-generated writing from text (formerly human-writing). Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.

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.

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, application methodology, and validation checklist. Version 1.0-beta definitive reference.

Hummingbot trading bot framework - automated trading strategies, market making, arbitrage, connectors for crypto exchanges. Use when working with algorithmic trading, crypto trading bots, or exchange integrations.

Run and test HTTP requests with Hurl. Use when working with HTTP APIs, testing web services, or creating HTTP-based test scenarios. Hurl allows you to define HTTP requests in plain text files and validate responses with asserts and captures.

Activates when querying livestock and animal data from GCS. Use this skill for: CHR registry, pig movements, animal welfare, antibiotics, animal density, mortality rates, herd tracking, svineflytning. Keywords: husdyr, livestock, animal, dyr, CHR, svin, pig, ko, cattle, antibiotika, dyrevelfærd, flytning, movement

Generate Husky Git hooks for pre-commit, pre-push, and commit-msg automation. Triggers on "create husky hooks", "generate git hooks", "husky setup", "pre-commit hooks".

Generates Husky Git hooks configuration with pre-commit checks. Creates .husky/pre-commit file for running linting, testing, and formatting before commits.

Look up HVAC equipment specifications (capacity, efficiency, dimensions, electrical requirements) by brand and model number. Use when the user mentions equipment specs, model numbers, AHU, VAV, chiller, boiler, pump, fan specifications, or needs to find manufacturer data sheets. Searches manufacturer websites and processes PDF spec sheets with security safeguards.

HVM Runtime Skill

HWP/HWPX 한글 문서 텍스트 자동 치환 도구. 한글 파일에서 특정 텍스트를 찾아 치환할 때 사용. 템플릿 문서 자동화, 대량 문서 수정에 활용.

Detects hybrid agent anti-pattern where agents perform execution work directly instead of delegating to skills

Coordinate multi-tool workflows with guardrails; use when asked to chain retrieval, analysis, and action steps.

Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.

Reciprocal Rank Fusion for merging full-text and vector search results in this project. Convex native searchIndex + vectorIndex integration with admin-toggleable hybrid search. Triggers on "hybrid search", "RRF", "full-text", "vector search", "mergeMessagesWithRRF", "searchIndex", "vectorIndex".

Use when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25 search with Reciprocal Rank Fusion, alpha tuning for search weight control, and optimizing retrieval quality

Adaptive routing strategies for distributed systems with multi-channel communication