Total 50,661 skills, AI & Machine Learning has 8491 skills
Showing 12 of 8491 skills
Expert-level AI implementation, deployment, LLM integration, and production AI systems
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Use ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.
Retrieves scientific papers from PubMed and creates plain-language research summaries. Use when users ask about medical research, scientific studies, clinical trials, disease treatments, or want to understand recent scientific literature on any biomedical topic.
DeepSeek AI large language model API via curl. Use this skill for chat completions, reasoning, and code generation with OpenAI-compatible endpoints.
Create and manage user rules that customize AI behavior. Use this skill when users want to create new rules, update existing rules, organize rules, or need guidance on writing effective rules for their projects or personal preferences.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Use when adding LangChain-based LLM routes or services in Python or Next.js stacks; pair with architect-stack-selector.
Use when reviewing SKILL.md files for structure and trigger quality.
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.