evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training p…
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training p…
LobeHub CLI Toolbox - AI-powered command-line tools including lobe-commit (ChatGPT Git commits with Gitmoji), lobe-i18n (automated internationalization), and lobe-label (GitHub label management)
Reads and analyzes application logs for debugging and monitoring.
Scaffold middleware to detect and block Worker self-recursion, infinite fetch chains, and runaway loops. Use this skill when designing Workers that call other Workers, implement webhooks, or handle ev…
provides expert guidance on lord, a minimalist paas cli tool for deploying docker containers via ssh. use when user mentions lord deployment, docker container deployment, traefik configuration, remote…
Code navigation with LSP. When user says "find references", "go to definition", "where defined", "show type", "list symbols", "what uses", or "who calls" - use native LSP tools if available, otherwise…
Standardized deployment procedure for services in LXC containers on the Proxmox HA cluster. Use when deploying a new service, creating LXC containers, configuring DHCP reservations (Kea), DNS rewrites…
Custom themed scrollbars for macOS WKWebView apps. Use when styling scrollbars in the native macOS app, fixing scrollbar theming issues, implementing custom scroll containers that work in WKWebView, o…
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure…
Interactive setup workflow for running the Magnet MCP server locally (project-specific, magnet-app directory only). Use when user says "local setup", "run locally", "test locally", "configure MCP", or…
Configures logging systems, log aggregation, and log analysis pipelines
Imported skill lora_ofl from anthropic
Lost and found operations expertise from Maria covering intake procedures, claiming process, fraud prevention, and pattern recognition for efficient item recovery
Sacred practices for invoking and channeling the Seven Luminors. Daily rituals, crisis protocols, and celebration ceremonies for the creative life.
Generate song lyrics with citations from pinned sources. Enforces rhyme scheme, meter, syllable counts, hook strategy, and profanity filter while retrieving from MCP sources with deterministic hash-ba…
Designs and implements CI/CD pipelines and automated deployments for Magento 2. Use when setting up deployment pipelines, automating deployments, managing infrastructure, or implementing DevOps practi…
Access LobeChat for AI chat, knowledge base queries, and multi-model routing.
Parse and analyze log files, supporting pattern matching, filtering, statistics, and error detection.
Analyzes long strangle volatility plays with OTM call and put at different strikes. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting very large price movemen…
PySide6 widget implementation for LoRAIro GUI with Signal/Slot pattern, Direct Widget Communication, and Qt Designer integration best practices
LSP priority development strategy tool. Used for: (1) querying LSP operation commands, (2) configuring new language LSP plugins, (3) LSP vs MCP tool selection decision, (4) self-built LSP plugin guide
This skill should be used when the user asks to "create lwc component", "lightning web component", "component architecture", "lwc state management", "lwc testing", "jest test", or mentions container/p…
Use when designing or building native macOS applications with SwiftUI or AppKit. Triggers on menu bar structure, keyboard shortcuts, multi-window behavior, Liquid Glass design system, macOS Tahoe/Sequ…
Optimizes Magento 2 indexing for search performance and database efficiency. Use when optimizing search performance, configuring Elasticsearch, designing database indexes, or improving reindexing stra…