Agent Skills
Read from each publisher's repository, labelled by what each skill lets an agent do. Nothing is run.
2,104 skills
- verl-rl-trainingDaniel AvilaProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.Instructions only
- voice-agentsDaniel AvilaVoice 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, backgrou…Instructions only1 high finding
- voice-ai-developmentDaniel AvilaExpert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals…Instructions only
- weights-and-biasesDaniel AvilaTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platformInstructions only
- whisperDaniel AvilaOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or mult…Instructions only
- a11y-auditAlireza RezvaniNo description.Instructions only
- ab-test-setupAlireza RezvaniNo description.Instructions only
- ad-creativeAlireza RezvaniNo description.Instructions only
- adversarial-reviewerAlireza RezvaniNo description.Instructions only
- aeoAlireza RezvaniNo description.Instructions only
- agent-decision-receiptsAlireza RezvaniNo description.Instructions only
- agent-designerAlireza RezvaniNo description.Instructions only
- agent-harnessAlireza RezvaniNo description.Instructions only
- agent-launcher-orchestratorAlireza RezvaniNo description.Instructions only
- agent-memoryAlireza RezvaniNo description.Instructions only
- agent-protocolAlireza RezvaniNo description.Instructions only
- agent-regression-evalsAlireza RezvaniNo description.Instructions only
- agent-workflow-designerAlireza RezvaniNo description.Instructions only
- agenthubAlireza RezvaniNo description.Instructions only
- agile-product-ownerAlireza RezvaniNo description.Instructions only
- ai-act-readinessAlireza RezvaniNo description.Instructions only
- ai-decision-authorityAlireza RezvaniNo description.Instructions only
- ai-securityAlireza RezvaniNo description.Instructions only
- aims-auditAlireza RezvaniNo description.Instructions only
- analytics-trackingAlireza RezvaniNo description.Instructions only
- andreessenAlireza RezvaniNo description.Instructions only
- api-design-reviewerAlireza RezvaniNo description.Instructions only
- api-test-suite-builderAlireza RezvaniNo description.Instructions only
- app-store-optimizationAlireza RezvaniNo description.Instructions only
- apple-hig-expertAlireza RezvaniNo description.Instructions only
- ar-resumeAlireza RezvaniNo description.Instructions only
- ar-runAlireza RezvaniNo description.Instructions only
- ar-statusAlireza RezvaniNo description.Instructions only
- arquiteto-de-empresaAlireza RezvaniNo description.Instructions only
- atlassian-adminAlireza RezvaniNo description.Instructions only
- atlassian-templatesAlireza RezvaniNo description.Instructions only
- autoresearch-agentAlireza RezvaniNo description.Instructions only
- aws-solution-architectAlireza RezvaniNo description.Instructions only
- azure-cloud-architectAlireza RezvaniNo description.Instructions only
- behumanAlireza RezvaniNo description.Instructions only
Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.