Top Agent Skills

Search arXiv papers by keyword, author, category, or ID.

Extend Hermes Agent by adding new tools (sync + async patterns), authoring in-repo skills, upgrading Hermes, and understanding s6 container supervision. Class-level umbrella for Hermes development workflows.

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Author/validate/export Google's DESIGN.md token spec files.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Linear: manage issues, projects, teams via GraphQL + curl.

Query Polymarket: markets, prices, orderbooks, history.

波总个人财务中枢 v2.0 — 债务追踪 + 消费分析 + 还款日预测 + 暴力催收。当你收到"还了XX YY元""花呗清了""我的债务""截图""消费"等财务相关指令时使用。

Manim CE animations: 3Blue1Brown math/algo videos.

Create, triage, label, assign GitHub issues via gh or REST.

本地 pub2gg 全链路：文章→DeepSeek排版→GitHub存稿→WordPress发布→Telegram推送。不依赖阿里云中继，纯 Hermes 本地执行。

YouTube transcripts to summaries, threads, blogs.

Synchronizes audio tracks with video footage, handles multi-camera sync, and fixes drift issues

Analyzes BIM models for clash detection, quantity takeoff, and construction sequence planning

Generates client SDKs in TypeScript, Python, Go, and Java from OpenAPI specifications

Formats citations and bibliographies in APA 7th, MLA 9th, Chicago, Harvard, and IEEE styles

Validates data quality with completeness, consistency, accuracy checks and generates quality reports

Creates Helm charts with values files, templates, and dependency management for Kubernetes deployments

Designs investor pitch decks with storytelling framework, financial slides, and team presentation

Creates pixel art animation sprites with walk cycles, attack animations, and idle sequences

Optimizes SQL queries with execution plan analysis, index suggestions, and query rewriting

Scores real estate leads based on engagement, budget, timeline, and property preference matching

Provides mixing and mastering guidance with EQ, compression, and spatial processing recommendations

Optimizes content for search engines with keyword density, meta tags, heading structure, and internal linking

Optimizes video titles, descriptions, tags, and chapters for maximum YouTube/TikTok discoverability

Designs drum patterns and beats with genre templates, swing settings, and velocity humanization

Debugs ML pipelines by identifying data leakage, overfitting, and distribution shift issues

Builds DeFi protocols with lending, staking, and liquidity pool implementations

Assesses image quality with blur detection, noise estimation, and aesthetic scoring

Designs ETL/ELT data pipelines with Apache Airflow, dbt, or Prefect configurations

Write news articles following AP style with inverted pyramid structure and fact attribution

Builds automated email sequences for onboarding, nurturing, and re-engagement with A/B test variants

Applies artistic styles to photographs using neural style transfer with fine-grained control

Builds yoga sequences with pose transitions, difficulty progression, and breathing pattern integration

Implements gamification elements in educational content with points, badges, leaderboards, and quests

When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are signing up but not sticking around. For signup/registration optimization, see signup. For ongoing email sequences, see emails.

Use when applying seamless infinite marquee loops with duplicated items for logo strips, tickers, or continuous horizontal content.

Use when composing corner-anchored laser accents with thin beams, a bright emitter node, bloom, and atmospheric glow or fog. Prefer this over mengto-webgl-laser when lasers are layout corner ornaments, not a fixed full-screen WebGL beam.

Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English.

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

用于组合和派遣并行团队的交互式代理选择器

You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines."

Discover hidden content, directories, subdomains, and API endpoints with ffuf — the fastest web fuzzer. Use when someone asks to "find hidden directories", "fuzz URLs", "discover API endpoints", "subdomain enumeration", "content discovery", "ffuf", "brute force paths", or "find hidden files on a website". Covers directory fuzzing, parameter fuzzing, subdomain discovery, virtual host enumeration, and recursive scanning.

You are an expert in Hapi.js, the configuration-centric enterprise framework for Node.js. You help developers build production APIs with built-in input validation (Joi), authentication strategies, plugin architecture, caching, rate limiting, and comprehensive request lifecycle hooks — designed for teams that need structure, security, and testability without third-party middleware sprawl.

Jest is a comprehensive JavaScript testing framework built by Meta, designed for zero-configuration testing of JavaScript and TypeScript applications. It provides a complete ecosystem for unit testing, integration testing, and snapshot testing with built-in code coverage, mocking capabilities, and parallel test execution. Jest works seamlessly with React, Node.js, Angular, Vue, and virtually any JavaScript project, making it the most widely adopted testing framework in the ecosystem.

Bundle TypeScript libraries with tsup — zero-config, powered by esbuild. Use when someone asks to "bundle a TypeScript library", "build npm package", "tsup", "publish TypeScript to npm", "build ESM and CJS", "bundle with esbuild", or "library bundling with zero config". Covers ESM/CJS dual output, declaration files, tree-shaking, and npm publishing.

Executing Plans

Validate procurement workflows, skills, data extraction, compliance, and integration with systematic testing methodology for procurement domain

AI Team Coordination

Use when making changes to existing systems to ensure those changes don't break existing functionality. This skill provides procedures for identifying at-risk areas, adding regression tests, and validating changes don't cause unintended side effects.

UI Button Positioning Skill

Dropdown Implementation