Total 31,434 skills, AI & Machine Learning has 5090 skills
Showing 12 of 5090 skills
Branch off a conversation to handle tangents. Outputs context summary and ready-to-paste command for a new terminal session.
Publish and update agent skills on agentskill.sh and skills.sh marketplaces. Covers SKILL.md preparation, submission, verification, and ongoing sync. Use when the user mentions publishing skills, listing on marketplace, updating skill listings, or asks about agentskill.sh or skills.sh.
Use when annotating code with structured metadata, tags, and markers for AI-assisted development workflows. Covers annotation formats, semantic tags, and integration with development tools.
Enables Claude Code to collaborate with OpenAI Codex CLI on Windows. Use this skill when the user wants to get a second opinion from Codex, compare approaches between Claude and Codex, or leverage both AI assistants for collaborative problem-solving. This skill supports both non-interactive mode (automatic response retrieval) and interactive mode (visual pane splitting with tmux).
Trend intelligence and cultural signal detection for emerging news and behaviors. USE WHEN: Researching latest news (48h), identifying cultural/tech/consumer shifts before mainstream adoption, analyzing emerging trends with advanced elicitation. PRIMARY TRIGGERS: "coolhunt [topic]" = Full research workflow (5 steps) "trend analysis" = Deep analysis with elicitation methods "news scan [topic]" = Quick news gathering WORKFLOW: Request → Web Research → Elicitation Selection → Analysis → Report OUTPUT: Markdown report with headline, summary, fact-check, and behavioral analysis saved to coolhunter-output/report-{datetime}/{title}.md
Safe experimentation framework for AI agents. Creates isolated sandbox environments for trying new features, testing approaches, and exploring solutions without polluting the main codebase. USE WHEN: Agent needs to try something uncertain, explore multiple approaches, test a new library, prototype a feature, or run a technical spike before committing to implementation. PRIMARY TRIGGERS: "experiment with" = Setup sandbox + run experiment "try this approach" = Quick experiment in sandbox "spike" / "POC" / "prototype" = Time-boxed technical investigation "tinker" / "tinkering mode" = Enter experimentation workflow "explore options" = Multi-approach comparison in sandbox NOT FOR: Debugging (use debugger), testing (use test runner), or committed feature work (use git branches). DIFFERENTIATOR: Unlike git branches (for committed direction), tinkering is for "I don't know if this will work" exploration. Try 5 things in sandbox before committing to a branch. Faster feedback, zero codebase pollution.
Extract structured information from unstructured text using LLMs with source grounding. Use when extracting entities from documents, medical notes, clinical reports, or any text requiring precise, traceable extraction. Supports Gemini, OpenAI, and local models (Ollama). Includes visualization and long document processing.
Vertex Ai Deployer - Auto-activating skill for ML Deployment. Triggers on: vertex ai deployer, vertex ai deployer Part of the ML Deployment skill category.
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
Stores decisions and patterns in knowledge graph. Use when saving patterns, remembering outcomes, or recording decisions.
Set up and manage a Memory Bank system for cross-session context continuity across AI coding agents. Use when the user mentions 'memory bank' with any action intent — setup, install, initialize, init, update, refresh, sync, status, check, read, show, review, display, or equivalents in any language (e.g. Turkish: kur, kurulum, güncelle, durumu, oku; German: einrichten, aktualisieren; Spanish: configurar, actualizar; French: installer, mettre à jour). Supports Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Roo Code, Aider, Antigravity, and OpenAI Codex.
4. Next task