Loading...
Loading...
Found 1,310 Skills
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Extract frames from video files using ffmpeg for AI/LLM analysis. Use when (1) the user asks to analyze, describe, or summarize a video file, (2) the user wants to extract frames or screenshots from a video, (3) the user provides a video file (.mp4, .mov, .avi, .mkv, .webm, etc.) and asks questions about its visual content, (4) the user wants to identify scenes, objects, or events in a video, (5) the user wants timestamps overlaid on extracted frames for temporal reference. Converts video into JPEG frames that can be attached to LLM prompts as images. Requires ffmpeg on PATH. Supports scene-change detection, model-aware optimization (Claude/OpenAI/Gemini), quality presets (efficient/balanced/detailed/ocr), grayscale and high-contrast OCR mode, and automatic FPS calculation via --max-frames.
OpenAI-compatible proxy aggregating 14 free-tier LLM providers with automatic failover and per-key rate tracking.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Run cross-framework agent comparisons using evaluatorq from orqkit — compares any combination of agents (orq.ai, LangGraph, CrewAI, OpenAI Agents SDK, Vercel AI SDK) head-to-head on the same dataset with LLM-as-a-judge scoring. Use when comparing agents, benchmarking, or wanting side-by-side evaluation. Do NOT use when comparing only orq.ai configurations with no external agents (use run-experiment instead).
Extract text from PDFs as structured, semantic Markdown. Use when converting a PDF to Markdown, extracting text from a PDF, processing one or more PDFs into Markdown output, reading PDF contents for analysis, ingesting documents for RAG pipelines, preparing PDFs for LLM context, or any task where PDF text needs to be in a machine-readable format. ALWAYS use this skill when the user has a PDF and needs its content as text or Markdown — even if they don't explicitly say "convert to markdown".
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
INVOKE THIS SKILL when auditing an AI agent or LLM app for regulatory compliance. Covers EU AI Act, GPAI Code of Practice, GDPR, NIST AI RMF, Colorado AI Act, HIPAA, and ISO 42001. Scans the codebase for compliance gaps, cross-references Arize instrumentation for audit trail coverage, and produces an actionable remediation checklist tailored to the selected frameworks.
Comprehensive testing doctrine for software and AI systems — covers positive patterns, anti-patterns, gates for coding agents writing tests, CI discipline, and an LLM/agent evaluation primer. Use when authoring or reviewing tests, adding mocks, deciding test placement, generating tests via agents, debugging flaky CI, designing eval suites for LLM features, or rebuilding a brittle test suite. Contains 12 positive patterns (selector hierarchy, table-driven, builders, real-system gates), 25 anti-patterns across Brittleness, Flakiness, Mock-misuse, Process, and AI-specific families, 7 mandatory gates for agents writing tests, flaky-test taxonomy with quarantine workflow, contract / property / mutation testing patterns, and an oracle-ladder primer for LLM-as-judge and agent eval. Language-agnostic — pseudo-code only. Don't use for general code review, library-specific debugging unrelated to tests, non-testing CI pipeline design, or production observability.
Design, test, and optimize prompts for LLM interactions. Cover prompt patterns (few-shot, chain-of-thought, ReAct), system prompt design, output formatting, prompt evaluation, and prompt optimization techniques. Triggers on "write prompt", "optimize prompt", "design system prompt", "few-shot examples", "chain of thought", "prompt evaluation", "LLM output formatting", "prompt testing", or "prompt patterns".
Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing academic-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.