Loading...
Loading...
Found 1,622 Skills
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati
Build and maintain a personal knowledge base using Karpathy's llm-wiki methodology across Claude Code, Codex, and OpenClaw agents.
Connect to local LLM endpoints (Ollama, llama.cpp, vLLM) with automatic provider fallback. Use when: (1) you need to run LLM inference locally for privacy/cost, (2) you want to use models not available via cloud APIs, (3) you need offline capability, (4) you want automatic fallback to cloud providers when local fails.
This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns. Use when the user asks to benchmark prefix caching hit rate, caching efficiency, or repeated-prompt performance in vLLM.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
OpenAI-compatible proxy aggregating 14 free-tier LLM providers with automatic failover and per-key rate tracking.
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Comprehensive LLM audit. Model currency, prompt quality, evals, observability, CI/CD. Ensures all LLM-powered features follow best practices and are properly instrumented. Auto-invoke when: model names/versions mentioned, AI provider config, prompt changes, .env with AI keys, aiProviders.ts or prompts.ts modified, AI-related PRs. CRITICAL: Training data lags months. ALWAYS web search before LLM decisions.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Use when you want rubric based LLM quality scoring on generated outputs; pair with addon-deterministic-eval-suite.
Fact-checks LLM responses by extracting verifiable claims, verifying each via web search, producing an audit report with verdicts, and optionally revising inaccurate responses. Use when the user asks to audit, fact-check, double-check, or verify a response.