Loading...
Loading...
Found 2,500 Skills
Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.
Python testing with pytest, coverage, fixtures, parametrization, and mocking. Covers test organization, conftest.py, markers, async testing, and TDD workflows. Use when user mentions pytest, unit tests, test coverage, fixtures, mocking, or writing Python tests.
Systematic approach to implementing new features in the Rust memory system following project conventions. Use when adding new functionality with proper testing and documentation, maintaining code quality and test coverage.
Diseño de prompts para LLMs: system prompts, few-shot examples, chain-of-thought, RAG, structured outputs.
Store and serve files via Storage; set visibility, generate URLs, and handle streaming safely
Creates comprehensive test suites for Move contracts with 100% coverage requirement. Triggers on: 'generate tests', 'create tests', 'write test suite', 'test this contract', 'how to test', 'add test coverage', 'write unit tests'.
Comprehensive QA testing orchestrator. Use when user says 'test', 'qa', 'check site', 'find bugs', 'helpmetest', provides a URL to test, or wants complete testing coverage from discovery through bug reporting. Discovers ALL pages, enumerates ALL features, tests comprehensively, reports exact metrics.
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage. Use when building local storage layers, offline-first patterns, or any shared mutable state that needs both concurrency safety and disk persistence.
Edge-optimized RAG memory system for OpenClaw with semantic search. Automatically loads memory files, provides intelligent recall, and enhances conversations with relevant context. Perfect for Jetson and edge devices (<10MB memory).
Audit design token usage across a product for consistency and coverage.
Manages permanent memory storage for decisions, blockers, context, preferences, and procedures. Use when user says "remember", "save this decision", "what did we decide", "recall", "search memories", "any blockers", or when making important architectural decisions. Provides SDAM compensation through external memory.
Build Next.js web applications with Google Gemini Nano Banana image generation APIs (gemini-2.5-flash-image, gemini-3-pro-image-preview). Use when creating image generators, editors, galleries, or any app integrating conversational image generation with server actions, API routes, and storage. Use for "image generation app", "nano banana", "text to image", "AI image generator", or "gemini image". Do NOT use for non-Gemini models, Python/Go backends, model fine-tuning, or image classification/input tasks.