3.5K skills · sorted by relevance
Develop Garry's Mod addons with guidance on Lua scripts, file organization, assets, and packaging. Covers server and client execution contexts, API lookup, and debugging, with in-game testing included in the workflow.
Luamake 构建系统指南——用于当前项目的 `luamake` / `make.lua` / Ninja 生成流程。当用户需要编写、修改、排查或理解 `make.lua`、目标定义、`lm:conf`、`deps` / `objdeps`、代码生成、Lua C 模块、Bee 运行时集成，或需要解决当前项目中由 `luamake` 驱动的构建问题时，使用此 skill。即使用户没有明确提到 `luamake`，但上下文明显是在处理本项目的构建脚本、构建目录、目标依赖或 `luamake` 生成的 Ninja 流程，也应使用此 skill。不要把它用于纯通用的 C/C++ 编译知识、与本项目无关的 CMake / xmake / Bazel / Meson 问题，或仅讨论编译器理论而未涉及 `luamake` / `make.lua` 的请求。
The English summary is being prepared. Showing the original description.
Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.
Evaluate companies using projected cash flows, dividends, business segments, and comparisons with peers. Select suitable valuation methods, examine how assumptions change estimated value, and check for problems that can make a seemingly cheap stock misleading.
Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.
Evaluate code generation models with HumanEval, MBPP, and other benchmarks. Test generated programs, compare models across programming languages, and record pass@k scores, which estimate the chance that at least one of k solutions passes the tests.
Evaluate a driving agent on CARLA Leaderboard routes after checking the required setup. Select routes and repetitions, save driving scores and infractions, record runs, and resume interrupted evaluations from a saved checkpoint.
Evaluate NVIDIA Cosmos Policy for robot manipulation in LIBERO and RoboCasa simulations. Follow GPU environment setup, configure rendering without a display, run small checks before larger benchmarks, inspect success rates, and profile inference latency.
Evaluate code generation models with HumanEval, MBPP, and multilingual benchmarks. The skill guides test execution and model comparisons using pass@k, an estimate of whether at least one of k generated solutions passes the tests.
Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, bin/obj), deep import chains (>20 levels), preprocessed output >10K lines indicating heavy evaluation, property functions with file I/O ($([System.IO.File]::ReadAllText(...))), multiple evaluations per project. Covers the 5 MSBuild evaluation phases, glob optimization via DefaultItemExcludes, import chain analysis with /pp preprocessing. DO NOT USE FOR: compilation-time slowness (use build-perf-diagnostics), incremental build issues (use incremental-build), non-MSBuild build systems. INVOKES: binlog MCP server tools (evaluations, evaluation_global_properties, evaluation_properties, imports, properties); falls back to dotnet msbuild -pp:full.xml for preprocessing, /clp:PerformanceSummary.
The English summary is being prepared. Showing the original description.
Lua scripting context for the Megahub project. Use when working on Lua script execution, Lua bindings, libluahub, Lua error handling, Lua threads, or the Blockly-to-Lua code generation pipeline.
The English summary is being prepared. Showing the original description.
Use for Nauthilus Lua plugins, Lua callback tests, policy compiler and registry work, Lua environment and subject sources, Lua actions, hooks, backend scripts, policy facts, obligation targets, `server/lualib`, `server/lua-plugins.d`, `server/policy`, and JSON fixtures under `testdata/lua`.
The English summary is being prepared. Showing the original description.
Create and analyze AI model evaluation experiments in Arize using the ax CLI, a command-line tool. Collect real model outputs, export results, compare evaluation scores, and identify examples where a new model performs worse.
Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.
Compare a listed company with relevant peers using valuation multiples, ratios linking price or company value to financial measures. Produce reports or editable workbooks covering peer selection, implied prices, data quality, and valuation assumptions.
Instrument Python or TypeScript agents to record runs for Failproof AI, verify local event files, and troubleshoot missing sessions. The skill also guides building evaluator workers that score completed runs on your own infrastructure.
Advanced Evaluation workflow skill. Use this skill when the user needs This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
The English summary is being prepared. Showing the original description.
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval, score my spans or experiment, ax tasks, trigger-run, trigger eval, column mapping, continuous monitoring, query filter for evals, evaluator version, or improve an evaluator prompt.
The English summary is being prepared. Showing the original description.
Set up a realtime evaluation folder with a suitable shared harness, the framework that runs evaluations. Prepare prompts, tool definitions, realistic starter data, and a README, then validate the setup with evaluation and test runs.
Plan AI application work across six areas: prompt evaluation, context allocation, retrieval-based answer generation, agent security, evaluation pipelines, and product strategy. This overview explains the approaches; the individual workflow packages, test cases, and CI templates are not included.
Build an Excel comparison of public companies using financial performance, valuation ratios, and statistical benchmarks. The spreadsheet includes formulas, source notes, medians, and quartiles to show how each company compares with its peers.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.