Results for “llm-agents”

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

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.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

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.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Mine LITCOIN — a proof-of-comprehension and proof-of-research cryptocurrency on Base. Use when the user wants to mine crypto with AI, earn tokens through reading comprehension or solving optimization problems, stake LITCOIN, open vaults, mint LITCREDIT, manage mining guilds, deploy autonomous agents, or interact with the LITCOIN DeFi protocol.

Run Comet's Opik — open-source LLM observability, evaluation, and optimization — from one routing-first skill: install the Python/TypeScript SDK, stand up a server (Comet.com cloud, Docker Compose via `./opik.sh`, or Kubernetes/Helm), wire tracing through `@opik.track` or one of 50+ framework integrations (OpenAI, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, DSPy, Ollama, Bedrock, Vercel AI SDK, …), score outputs with LLM-as-a-judge metrics (Hallucination, Moderation, Answer Relevance, Context Precision), and run Datasets/Experiments evaluations including PyTest CI gates. Use when the user wants LLM tracing, prompt evaluation, production LLM monitoring, agent optimization, or guardrails with Opik. Triggers on: opik, comet opik, opik configure, opik.sh, llm observability, llm tracing, llm as a judge, hallucination metric, prompt evaluation, opik dashboard, opik guardrails, agent optimizer.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Apply world-class developer documentation principles (Stripe, Snowflake, Databricks, TiDB Cloud) to structure, write, review, or refactor technical documentation. Use this skill whenever the user mentions documentation, docs, sidebar or navigation, information architecture, restructuring a section, writing or editing a guide, reviewing docs, where content belongs, English doc prose, headings, code comments, link text, docs home pages, section landing pages, long-form guides mixing content types, cross-referencing, or making docs readable for AI agents and LLMs. Covers VeloDB Cloud docs work (Monitoring restructure, sidebar, EN/中文 alignment, writing style, landing pages, LLM-friendly docs) and any SaaS or database documentation task. Trigger broadly: if the conversation touches doc organization, page structure, doc quality, doc sentences, landing pages, or AI-readable docs, consult this skill rather than answering from intuition.

Turn natural-language descriptions into editable `.drawio` diagrams and export them to PNG / SVG / PDF / JPG via the native draw.io desktop CLI, or turn an existing codebase (Python / JS-TS / Go / Rust) into an auto-laid-out structure diagram. Wraps Agents365-ai/drawio-skill: 6 diagram presets (ERD, UML class, sequence, architecture, ML/DL, flowchart), search across 10,000+ official AWS/Azure/GCP/Cisco/K8s/UML/ BPMN shapes, 321 AI/LLM brand logos, vision self-check + auto-fix, and a 5-round iterative refinement loop. No MCP server, no daemon — runs from a single SKILL.md and the draw.io CLI. Use when the user wants polished, precise, exportable diagrams or wants to visualize code structure. Triggers on: drawio, draw.io, drawio diagram, architecture diagram, ERD, UML diagram, sequence diagram, flowchart, network diagram, visualize codebase, code structure diagram, class hierarchy, export diagram png/svg/pdf, AWS/Azure/GCP icon, draw.io shapes.