From auk
Generates, verifies, and compiles AI context from codebase analysis. Use for codebase conventions, architecture rules, context health, and CLAUDE.md generation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/auk:aukThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
auk (`npx -y auk-develop`) generates, verifies, and compiles AI context from
auk (npx -y auk-develop) generates, verifies, and compiles AI context from
the actual codebase.
auk generate — analyze code → .auk/rules.yaml, graph.json, semantic.json, compiled context filesauk verify — re-check every rule against current code; reports context rotauk review --diff <ref> — architectural diff review (layer violations, new cycles, god objects)auk enhance --emit / --apply <json> — LLM enhancement loop (you write the JSON)auk graph --open — interactive dependency/call-graph viewerauk mcp — MCP server (tools: get_rules, get_architecture, get_call_graph, get_dependencies, get_enhancement_tasks, apply_enhancements, …).auk/rules.yaml, graph.json, decisions.yaml, semantic.json should be committed; .auk/cache.json and .auk/prompts/ gitignored.auk compile.npx claudepluginhub sandeepshekhar26/develop-anything --plugin aukAuto-generates CLAUDE.md and .rune/ context for AI sessions by scanning codebase structure, config files, and tech stack. Saves re-explaining project context on undocumented repos.
Generates, analyzes, and enhances CLAUDE.md files using best practices, modular architecture, and tech stack customization for new and existing projects.
Generates project-specific CLAUDE.md rules by detecting stack from package.json, Cargo.toml, pyproject.toml, go.mod, git log, and user-selecting categories like response format, library preference, code review stance. Use for new projects, repo onboarding, or establishing conventions.