Loading...
Loading...
Found 1,893 Skills
Luau type system: annotations, generics, narrowing, inference philosophy, sealed/unsealed tables, exports, and Roblox-aware typing.
Configure LangWatch online evaluations and guardrails for production traffic. Use when the user wants to score live traces or threads, monitor production quality, sample incoming traffic, or synchronously block unsafe requests and responses. Do not use for batch experiments.
Use this skill when users need to evaluate potential co-founders, assess founder compatibility, design equity splits, or navigate co-founder relationships. Activates for "should I work with this person," "co-founder fit," "equity split," or founding team questions.
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo. Invoke when: - Setting up prompt evaluation or regression testing - Integrating LLM testing into CI/CD pipelines - Configuring security testing (red teaming, jailbreaks) - Comparing prompt or model performance - Building evaluation suites for RAG, factuality, or safety Keywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
Use when evaluating LLMs, running benchmarks like MMLU/HumanEval/GSM8K, setting up evaluation pipelines, or asking about "NeMo Evaluator", "LLM benchmarking", "model evaluation", "MMLU", "HumanEval", "GSM8K", "benchmark harnesses"
Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income. Use when the user asks about discounted cash flow, DCF models, WACC, terminal value, dividend discount models, comparable multiples, or sum-of-the-parts valuation. Also trigger when users mention 'what is this stock worth', 'fair value estimate', 'Gordon growth model', 'free cash flow valuation', 'cost of equity', 'sensitivity analysis', 'exit multiple', or ask whether a stock is overvalued or undervalued.
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.
Investigate LLM analytics evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).
Valuation analysis for a single stock via Longbridge — current PE / PB / PS / EV-EBITDA snapshot, historical percentile (1–3 years), industry median + relative premium, industry rank. Triggers: "估值贵不贵", "是不是被低估", "PE 历史百分位", "PB 分位", "行业溢价", "行业折价", "X 现在适合买不", "估值水平", "估值貴不貴", "是否被低估", "PE 歷史分位", "行業溢價", "行業折價", "is X expensive", "is X undervalued", "PE percentile", "industry valuation premium", "valuation snapshot".
Use when designing or auditing computer science experiments, evaluation plans, baselines, metrics, ablations, datasets, statistical tests, benchmarks, validity threats, or reproducibility claims.