Loading...
Loading...
Found 7,014 Skills
Use the Data Analysis Agent to perform natural language business analytics, auto-generate SQL queries, create visualizations, and produce business insights from Excel/CSV/databases
This skill should be used when the user wants to interact with their paper database — listing papers, searching content, showing paper details, adding papers, or exporting context. Matches queries like "search papers for X", "add this arXiv paper", "show equations from paper Y", "what papers do I have". Prefer CLI over MCP RAG tools for direct lookups.
Cram Engine - An AI tutor well-versed in learning science. Triggered when users mention terms like final exam cramming, final review, exam sprint, last-minute exam preparation, quick exam prep, intensive last-minute review, or use the /cram command. Based on six learning science principles including Cognitive Load Theory, Elaborative Processing, Generation Effect, and Retrieval Practice, it converts key points of university courses into efficient interactive learning sessions through a four-stage pipeline: deconstructing knowledge point tree → teaching each point individually → testing with real exam question types → diagnosing and filling knowledge gaps. Suitable for all qualitative knowledge-intensive university liberal arts courses.
Chinese Documentation Formatting Reference – Rules for spaces between Chinese and English, full-width/half-width punctuation, term retention, link formatting, and conventions from the Chinese Copywriting Guidelines. Only invoke when the user explicitly uses /chinese-documentation; do not trigger automatically based on context.
HertzFlow on-chain trade-decision intelligence. Currently covers Binance Alpha forensic across all surf-SQL EVM chains (BSC / Ethereum / Arbitrum / Base / Polygon / Optimism) — insider distribution, 真实派发 confirmed sell-out, 筹码三分法 (operator / CEX pool / verifiable retail), anomaly waves, monitoring exports. Solana runs in HOLDER_SNAPSHOT mode. Auto-trigger whenever the user pastes a raw 0x-prefixed 40-hex EVM CA, a Solana base58 CA, mentions a Binance Alpha token by ticker, or asks about 链上 forensic / 内幕出货 / 派发 / chip structure / quiet insider / Alpha distribution / on-chain dump — even if they don't say "hertzflow" explicitly. Pipeline runs deterministically (~2-10 min per CA depending on activity + surf cache state); LLM only fills narrative slots, never picks the verdict or writes SQL. Perp metrics, bridge audits, and HertzFlow core contract analysis sub-domains are coming — when those ship, this skill will dispatch to them based on input pattern (perp symbol, bridge protocol name, etc.) using the router table below. REQUIRES a Surf account + SURF_API_KEY. New users get 2000 free credits (~6-8 reports) via the HertzFlow private invite. Full forensic costs ~$1.5-3 USD per CA in Surf credits after the free tier runs out.
Set up a Godot 4.x 3D scene: Node3D transforms, Camera3D, lighting (DirectionalLight3D/OmniLight3D), WorldEnvironment for sky/ambient/tonemap/post, MeshInstance3D materials, and GridMap for tile-based 3D levels. Use when building a 3D scene in a Godot project, placing cameras/lights, configuring environment and post-processing, or working with Node3D/.tscn 3D content and GridMap.
Use when deploying to Fly.io or configuring flyctl, fly.toml, Fly.io secrets, databases, or GitHub Actions.
Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments).
Create Railway projects, services, and databases with proper configuration. Use when user says "setup", "deploy to railway", "initialize", "create project", "create service", or wants to deploy from GitHub. Handles initial setup AND adding services to existing projects. For databases, use railway-railway-database skill instead.
Implement efficient pagination strategies for large datasets using offset/limit, cursor-based, and keyset pagination. Use when returning collections, managing large result sets, or optimizing query performance.
Deploy containerized applications on Google Cloud Run with automatic scaling, traffic management, and service mesh integration. Use for container-based serverless computing.
Use when writing, reviewing, or refactoring code for maintainability and readability. Triggers on code reviews, naming discussions, function design, error handling, and test writing. Based on Robert C. Martin's Clean Code handbook.