Loading...
Loading...
Found 2,397 Skills
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
Luau best practices and clean code patterns for Roblox development. Use this skill when: - Writing new Luau modules, services, or controllers - Reviewing code for quality and maintainability - Setting up project structure and organization - Implementing error handling and validation - Managing memory and preventing leaks - Writing secure server-authoritative code - Following Roblox-specific conventions - Refactoring or improving existing code Triggers: "best practices", "clean code", "code review", "refactor", "code quality", "naming convention", "code style", "module pattern", "service pattern", "memory leak", "error handling", "pcall", "security", "server authority", "validation", "code organization"
Evaluate GitHub contributors for MLOps/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments.
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks"
Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvement cycles. Use when refining drafts into production-grade quality.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
Guides idiomatic Lua 5.4 programming, module design, and project maintenance for Neovim plugin/config ecosystems (LazyVim, lazy.nvim) and macOS bar tools (SketchyBar/SbarLua). Covers style, tooling (StyLua, Selene, LuaLS), module patterns, and testing. Use when writing Lua code, configuring Neovim plugins, working with SketchyBar Lua configs, debugging Lua require/module errors, or when the user mentions Lua, .lua files, LazyVim, lazy.nvim, SbarLua, SketchyBar, luarocks, LuaLS, StyLua, or Selene.
Generates a Jupyter notebook that evaluates a fine-tuned SageMaker model using LLM-as-a-Judge. Use when the user says "evaluate my model", "how did my model perform", "compare models", or after a training job completes. Supports built-in and custom evaluation metrics, evaluation dataset setup, and judge model selection.
Use for Luau type-system work focused on strictness modes, annotations, inference-aware API design, generics, refinements, advanced type patterns, and Roblox-aware type usage at the type level.
Assess business quality, competitive positioning, and sustainability of value creation beyond financial models. Use when the user asks about economic moats, competitive advantages, Porter's Five Forces, management quality, ESG integration, or business model analysis. Also trigger when users mention 'does this company have a moat', 'switching costs', 'network effects', 'brand value', 'management track record', 'capital allocation', 'insider ownership', 'red flags', or ask whether a company's advantage is durable.
Roblox Luau Development Workflow for implementing, reviewing, and refactoring Roblox game scripts, ModuleScript, ServerScript, LocalScript, RemoteEvent/RemoteFunction, DataStore, and server/client layering. Use when working on Roblox, Luau, Roblox Studio code, Rojo-synced scripts, gameplay systems, UI scripts, replication, remotes, or Roblox services.
Create and manage Architecture Decision Records (ADRs) using MADR 4.0.0 format. Use this skill when evaluating technology choices, documenting design decisions, or reviewing past architectural choices.