Total 31,387 skills, AI & Machine Learning has 5079 skills
Showing 12 of 5079 skills
Use this skill whenever the user asks to analyze, understand, or survey an entire project, codebase, or any collection of files. Trigger phrases include "analyze a large file", "process multiple files", "comprehend this problem", "take a look at these files", "familiarize yourself with this project", or any similar request, however phrased. Also activate when the task involves processing context that exceeds what can be reasoned about in a single pass, when encountering any input larger than ~50KB that requires detailed analysis, or when the user mentions "context comprehension" or "recursive comprehension". This skill TAKES PRIORITY over your default explore subagents for any project-wide or codebase-wide analysis task.
Set up a full AI ensemble/mob programming team for any software project. Creates team member profiles (.team/), coordinator instructions (.team/coordinator-instructions.md), project owner constraints (PROJECT.md), team conventions (AGENTS.md), architectural decisions (docs/ARCHITECTURE.md), domain glossary, and supporting docs. Use when: (1) starting a new project and wanting a full expert agent team, (2) the user asks to "set up a team", "create a mob team", "set up ensemble programming", or "create agent profiles", (3) converting an existing project to the driver-reviewer mob model, (4) the user wants AI agents to work as a coordinated product team with retrospectives and consensus-based decisions.
File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize project memory. Activate when starting tasks, encountering errors, making decisions, or when context may be lost between sessions.
Generate and edit images using AI. Use when the user asks to "generate an image," "create an image," "make a picture," "edit this image," "modify this image," or when building UI that needs visual assets like hero images, icons, or illustrations.
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
Reads invoice images and returns structured data. It can be called by other skills or directly by users.
Reads images of payment statements and returns structured data. It can be called by other skills or directly by users.
Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory. Use when triggered by cron, heartbeat, or explicit request to reflect on recent activity. Runs as background processing to improve memory quality over time.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate exte...
Reads images of receipts, payment receipts, and Furusato Nozei donation receipts and returns structured data. It can be called from other skills or directly by users.
Generate comic and manga panels, strips, and pages using each::sense AI. Create superhero comics, manga pages, webtoons, action sequences, and convert photos to comic art with consistent characters.
Reads images of deduction certificates (life insurance premiums, earthquake insurance premiums, etc.) and returns structured data. It can be called from other skills or directly by users.