Total 32,507 skills, AI & Machine Learning has 5245 skills
Showing 12 of 5245 skills
Create a new skill. When to use: When the user says "create skill", "new skill", "add skill", "initialize skill".
Convert text to natural speech using Sarvam AI's Bulbul v3 model. Handles audio generation, voiceovers, and voice interfaces for 11 Indian languages with 30+ voices. Supports REST, HTTP streaming, WebSocket, and pronunciation dictionaries. Use when generating spoken audio from text.
Meta-skill for building and managing agent persona skill packs. Use when the user wants to create a new agent persona, install/manage existing personas, or publish persona skill packs to ClawHub.
Agent Teams Orchestration Playbook for Claude Code. This skill should be used when the user requests to "create agent teams", "use agent swarm", "set up multi-agent collaboration", "orchestrate agents", "coordinate parallel agents", "organize team collaboration", "build agent teams", "implement swarm orchestration", "set up multi-agent system", "coordinate agent collaboration", or needs guidance on adaptive team formation, quality gates, skill discovery, task distribution, team coordination strategies, or Agent Teams best practices. It should also be used when the user mentions terms like "multi-agent", "agent collaboration", "agent orchestration", "parallel agents", "divisional collaboration", "assemble a team", "put together a team", "multi-agent collaboration", "swarm orchestration", "agent team". Note: "swarm" is a generic industry term; Claude Code's official concept is "Agent Teams".
Extracts text (with locations) from images and PDF documents using PaddleOCR.
Model configuration editor for ~/.pi/agent/models.json with multi-protocol curl testing support.
Builds sustained high agency through internalized standards, identity anchoring, cross-session learning, and self-recovery — all delivered in corporate PUA rhetoric. This is the evolution of PUA: same pressure culture, but with an internal engine that never burns out. Apply it to all tasks to maintain constant high agency. It is especially valuable for complex multi-step tasks, long debugging sessions, quality-sensitive deliverables, tasks requiring initiative and ownership, or whenever sustained motivation is critical. It can operate standalone or be stacked with PUA — when stacked, this skill's Recovery Protocol activates before PUA's L1 pressure takes effect. Trigger scenarios: start of any task, sustained work sessions, multi-turn problem-solving, or when you need the agent to think as an owner rather than a tool.
Diagnose and fix common FiftyOne issues automatically. Use when a dataset disappeared, the App won't open, changes aren't saving, MongoDB errors occur, video codecs fail, notebook connectivity breaks, operators are missing, or any recurring FiftyOne pain point needs solving.
ZenTao MCP Large Model Capability Extension Package. It provides four native capabilities: cross-project data aggregation view, one-sentence task creation, seamless effort logging, and automatic state transition.
Search and discover 50,000+ AI models on ModelsLab, check usage analytics, and monitor generation history via the Agent Control Plane API.
Handle async operations efficiently using ModelsLab webhooks. Get real-time notifications when API requests complete instead of polling.
Edit and enhance images using ModelsLab's Image Editing API. Features background removal, super resolution upscaling, outpainting, object removal, and AI-powered editing tools.