vexor-cli_skill

Overview

This skill provides a CLI for semantic file discovery using vexor. It finds where behavior is implemented, loaded, or documented across medium to large repositories by searching intent instead of literal text. Use it to quickly locate files, function definitions, configs, and relevant doc sections without manual browsing.

How this skill works

vexor indexes files into embedding-backed vectors and searches by semantic similarity to your query. You run vexor search "<QUERY>" with optional flags to scope by path, file extensions, or search mode. Results include similarity scores, file paths, line numbers, and snippet previews for quick inspection.

When to use it

• Locating where a feature, command, or config is implemented in a large repo
• Finding documentation sections or headings relevant to a user flow
• Discovering where files load or validate configuration data
• Rapidly narrowing candidates before opening files or creating PRs
• Scripting automated scans for files that match an intent across projects

Best practices

• Start with a short intent phrase rather than exact code; vexor is semantic
• Pick the cheapest mode that returns useful results (auto → code → full) to save time
• Use --ext to limit languages and --exclude-pattern to remove noisy paths
• Use --format porcelain or porcelain-z for reliable scripting output
• Run vexor once to build the index; subsequent searches are much faster

Example use cases

• Find CLI entrypoints: vexor search "typer app commands" --top 5
• Locate config loading/validation: vexor search "config loader" --path . --mode code --ext .py
• Search docs by headings: vexor search "user authentication flow" --path docs --mode outline --ext .md --format porcelain
• Exclude tests and noise: vexor search "config loader" --path . --exclude-pattern tests/** --exclude-pattern .js
• Scripted pipelines: use --format porcelain-z for NUL-delimited output in automation