Loading...
Loading...
Found 1,943 Skills
· Batch-improve skill collections with evaluation loops, lint checks, behavioral tests, peer review. Triggers: 'skill refiner', 'improve skills', 'quality sweep', 'batch improve', 'skill loop'. Not for one skill.
Nassim Taleb's Antifragility framework applied to a business idea, system, or portfolio position. Spawns a team of specialist agents — Fat-Tail Detector, Fragility Auditor, Optionality Scout, Iatrogenics Checker, Skin-in-the-Game Auditor — who each apply a distinct lens from Taleb's Incerto to evaluate whether the subject is fragile, robust, or antifragile. The lead synthesizes into a convexity assessment: what's the payoff structure under disorder, where are the hidden tail risks, and the honest Taleb verdict. Use when the user says "taleb this", "is this fragile", "antifragility analysis", "what would Taleb think", "tail risk check", or proposes a business/system and wants structural risk analysis. Works standalone or after /munger for complementary analysis.
Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.
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).
Research and discovery workflow for document deliverables — competitive analyses, architecture comparisons, ADR scaffolding, literature reviews, vendor evaluations. No TDD requirement. Phases: gathering → synthesizing → completed. Triggers: 'discover', 'research', 'explore topic', or /discover.
Sector-rotation snapshot across A-share, HK, and US markets — point-in-time multi-factor scoring of momentum, capital flow, and valuation to rank sectors by current cycle strength. For ongoing 6–12 month cycle positioning and allocation recommendations use longbridge-sector-monitor. Triggers: "行业轮动", "板块轮动", "行业动量排名", "强势板块", "弱势板块", "行业资金流", "板块涨幅榜", "行業輪動", "板塊輪動", "行業動量排名", "強勢板塊", "弱勢板塊", "行業資金流", "板塊漲幅榜", "sector rotation", "sector momentum ranking", "leading sector", "lagging sector", "sector capital flow", "sector strength ranking".
Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.
Use this skill when working with audio, sound, music, UAudioComponent, PlaySoundAtLocation, SoundCue, MetaSound, attenuation, submix, concurrency, SFX, or spatial audio in Unreal Engine. See references/audio-setup-patterns.md for music system and ambient soundscape architectures. For VFX audio synchronization, see ue-niagara-effects.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
Review and improve documentation with parallel evaluation and iterative improvement loop.
Evaluate UX/UI using Don Norman's 7 fundamental design principles from The Design of Everyday Things. Audit discoverability, affordances, signifiers, feedback, mapping, constraints and conceptual models.
Complete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder reranking, query rewriting, ranking pipelines, nDCG/MRR evaluation, and production search systems. Modern patterns for retrieval-augmented generation and semantic search.