Total 54,890 skills, AI & Machine Learning has 9107 skills
Showing 12 of 9107 skills
Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".
Compress documents for LLM token efficiency while preserving semantic content. Use when asked to compress, compact, shrink, or optimize a document, CLAUDE.md, system prompt, skill file, or any text for fewer tokens. Also use when the user mentions token count, token budget, context window limits, or wants to make prompts shorter for cost savings.
March Madness, playoff brackets, tournament picks. Upset potential, chalk vs contrarian strategies, historical trends, confidence levels.
This skill should be used when the user asks to "create rules", "add custom instructions", "set up AGENTS.md", "configure project rules", "add global rules", or needs guidance on customizing OpenCode behavior with custom instructions.
Starts a voice conversation with the user via the agent-voice CLI. Use when the user invokes /voice. The user is not looking at the screen — they are listening and speaking. All agent output and input goes through voice until the conversation ends.
OpenMAIC — Open Multi-Agent Interactive Classroom platform for generating immersive AI-powered learning experiences with slides, quizzes, simulations, and multi-agent discussions.
Develop, debug, and optimize SGLang LLM serving engine. Use when the user mentions SGLang, sglang, srt, sgl-kernel, LLM serving, model inference, KV cache, attention backend, FlashInfer, MLA, MoE routing, speculative decoding, disaggregated serving, TP/PP/EP, radix cache, continuous batching, chunked prefill, CUDA graph, model loading, quantization FP8/GPTQ/AWQ, JIT kernel, triton kernel SGLang, or asks about serving LLMs with SGLang.
A comprehensive traditional Chinese metaphysics agent ("Yi Jing" expert) that combines Mei Hua Yi Shu (Timing) with Gemini AI for modern interpretation.
Benchmark any agent skill to measure whether it actually improves performance. Use when the user wants to evaluate, test, or compare a skill against baseline, or when they mention "benchmark", "eval", "skill performance", or "does this skill help". Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
Constructs technical Suno V5 style prompts, selects genres, and optimizes generation settings. Use when creating or refining Suno prompts for track generation.
ML-powered Karaoke app in Rust using Bevy, WhisperX, and Demucs for stem separation, lyrics transcription, and pitch scoring.
Use this skill when a CFO, VP Finance, Controller, or Head of Finance needs to orchestrate the full financial operations of a company — from strategic financial planning and investor reporting to day-to-day control of accounts payable, accounts receivable, payroll, tax compliance, and revenue operations. This is the top-level financial orchestrator that commissions all finance sub-skills, maintains the single source of truth for all company numbers, drives budget allocation, manages cash flow, ensures regulatory compliance, and produces board-ready financial reports. Trigger this skill when anyone needs a comprehensive view of company finances, a board pack, a fundraising data room, or needs to coordinate across invoicing, payroll, commissions, procurement, taxes, and expenses simultaneously.