Total 31,446 skills, AI & Machine Learning has 5093 skills
Showing 12 of 5093 skills
Expert guidance for Anthropic Claude API development including Messages API, tool use, prompt engineering, and building production applications with Claude models.
Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.
Skill to create custom agents for VS Code Copilot or OpenCode, helping users configure and generate agent files with proper formatting and configurations. Use when users want to create specialized AI assistants for VS Code Copilot (.agent.md files) or OpenCode (JSON/markdown agent configs) with specific tools, prompts, models, and behaviors. If the user is not specific about the target platform, ask them to specify Copilot or OpenCode.
Meta-prompting framework for critiquing responses, analyzing solution trajectories, and evaluating AI-generated content quality
Persistent cross-session task queue for AI agents using Claude Code Tasks schema. Add, claim, complete, and reassign tasks with move-based locking, dependency tracking (blocks/blockedBy), conversation transcript linking, and staleness detection. Use for: (1) saving tasks for future agent sessions, (2) cross-session task persistence, (3) multi-agent task coordination, (4) linking conversation transcripts to tasks. Triggers: task queue, save task, agent task, queue task, persistent task, cross-session task, task for agent.
Plan and execute federated analytics workflows with the Rhino Health Python SDK. Use when the user wants to run survival analysis, metrics, data harmonization, model training, or any multi-step SDK workflow. Takes high-level research goals and produces phased execution plans with runnable code. Also handles SDK questions, debugging rhino_health errors, and metric selection. Triggers on: rhino-health, rhino_health, RhinoSession, FCP, federated analytics, OMOP, FHIR, harmonization, or any of the 40+ federated metrics.
AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.
Autonomous development agent that picks tasks from a project board (Jira, ClickUp, GitHub Issues), explores the codebase, implements the solution, opens a PR, and notifies the team. Configurable per-project via project files in ~/.config/delivering-tickets/projects/. Use this skill when the user asks to "work on a ticket", "pick up a task", "implement issue X", "work autonomously on the board", "take the next task", or any variation of autonomous task execution from a project board. Also triggers when the user mentions delivering-tickets, project configuration, or wants to set up autonomous development workflows for their team. Available commands: /delivering-tickets (start), /delivering-tickets:check (check replies), /delivering-tickets:status (workflow status), /delivering-tickets:setup (verify environment), /delivering-tickets:project (manage projects). Do NOT use for general coding without a ticket, standalone code reviews, project setup without a board configured, or questions unrelated to task execution from a project board.
A 10-step methodology for building software with AI collaboration - from north star through automated Ralph loop execution with zero human-in-the-loop code writing
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
Build AI agents and automate Claude Code programmatically using the Claude Agent SDK and headless CLI mode. Use this skill when you need to build an agent, create a Claude agent, make a bot, work with the agent SDK, run Claude in headless mode, write programmatic agent code, automate with Claude, create an MCP server builder, or query Claude programmatically. Covers the Python SDK, the claude -p headless interface, custom tool creation with SDK MCP servers, hooks for deterministic control, session management, and CLI flag reference. Authentication uses existing ~/.claude/ config — no API keys required.
Systematic LLM prompt engineering: analyzes existing prompts for failure modes, generates structured variants (direct, few-shot, chain-of-thought), designs evaluation rubrics with weighted criteria, and produces test case suites for comparing prompt performance. Triggers on: "prompt engineering", "prompt lab", "generate prompt variants", "A/B test prompts", "evaluate prompt", "optimize prompt", "write a better prompt", "prompt design", "prompt iteration", "few-shot examples", "chain-of-thought prompt", "prompt failure modes", "improve this prompt". Use this skill when designing, improving, or evaluating LLM prompts specifically. NOT for evaluating Claude Code skills or SKILL.md files — use skill-evaluator instead.