Loading...
Loading...
Found 140 Skills
Delegate noisy investigation to one or more subagents so the orchestrator's context stays clean, then work from the distilled answer. Use this skill whenever answering a question would require reading many files, long logs, large diffs, or wide codebase surveys — i.e. when producing the answer generates far more noise than the answer itself. Use it for "how does X work", "where is Y used", "what's the root cause of Z", "summarize this PR/log" style questions, and reach for it liberally before reading a pile of files inline.
This skill should be used when analyzing codebases, understanding architecture, or when "analyze", "investigate", "explore code", or "understand architecture" are mentioned.
Use when you need a fast, reliable architecture or impact view in a large unfamiliar repo, especially under time pressure or tight context budgets where manual grep or folder inference would be risky.
This skill helps users get started with existing (brownfield) projects by scanning the codebase, documenting structure and purpose, analyzing architecture and technical stack, identifying design flaws, suggesting improvements for testing and CI/CD pipelines, and generating AI agent constitution files (AGENTS.md) with project-specific context, coding principles, and UI/UX guidelines.
Generate LLM skills from documentation, codebases, and GitHub repositories
This skill should be used when user asks to "generate UML", "create sequence diagram", "生成时序图", "生成类图", "generate PlantUML", or discusses generating UML diagrams for new interfaces or API design.
Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.
Analyze codebases from the bottom up and generate a hierarchical README.md document tree. Start analysis from leaf directories, generate README.md files for each directory containing one-sentence descriptions of files, classes, and functions, and summarize layer by layer upwards to form a complete codebase documentation system. Supports state persistence and resumable analysis, suitable for scenarios such as understanding new projects, generating technical documentation, and analyzing code structures. Use this skill when you need to understand codebase structures, analyze function implementations, or generate code documentation.
Deep codebase analysis to generate or regenerate STYLE_GUIDE.md with full evidence citations. Use when /setup-ai's quick pass isn't thorough enough, when conventions have drifted, or after a major refactor. Produces a 17-section style guide citing specific files as evidence.
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Search and analyze a codebase with the `codemap` CLI: semantic search, symbol lookup, dependency tracing, file summaries, importance ranking, coupling metrics, and cycle detection. Use when the user wants architecture-aware code discovery rather than plain text search.
Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.