skills/deepinit/SKILL.md
Deep codebase initialization — create hierarchical AGENTS.md documentation across the entire project
npx skillsauth add sartoris-digital/pi-superpowers deepinitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Creates comprehensive, hierarchical AGENTS.md documentation across the entire codebase. AI-readable documentation that helps agents understand what each directory contains, how components relate, and how to work in each area.
Every AGENTS.md (except root) includes a parent reference:
<!-- Parent: ../AGENTS.md -->
This creates a navigable hierarchy agents can traverse.
<!-- Parent: {relative_path}/AGENTS.md -->
<!-- Generated: {timestamp} -->
# {Directory Name}
## Purpose
{One paragraph: what this directory contains and its role}
## Key Files
| File | Description |
|------|-------------|
| `file.ts` | Brief purpose |
## Subdirectories
| Directory | Purpose |
|-----------|---------|
| `subdir/` | What it contains (see `subdir/AGENTS.md`) |
## For AI Agents
### Working In This Directory
{Special instructions for agents modifying files here}
### Testing Requirements
{How to test changes in this directory}
### Common Patterns
{Code patterns or conventions used here}
## Dependencies
### Internal
{Other codebase areas this depends on}
### External
{Key external packages used}
<!-- MANUAL: Notes below this line are preserved on regeneration -->
subagent({
agent: "scout",
tier: "fast",
task: "List all directories recursively. Exclude: node_modules, .git, dist, build, __pycache__, .venv, coverage, .next"
})
Group directories by depth level:
Level 0: / (root)
Level 1: /src, /docs, /tests
Level 2: /src/components, /src/utils
...
Parent levels before child levels — ensures parent references are valid.
For each directory, dispatch writer to generate content:
subagent({
tasks: [
// Same-level directories processed in parallel
{
agent: "writer",
tier: "fast",
task: "Generate AGENTS.md for directory: {dir}\nFiles: {file_list}\nSubdirs: {subdir_list}\nParent: {parent_path}/AGENTS.md"
}
]
})
When files already exist:
<!-- MANUAL: --> sections<!-- Updated: --> timestampAfter generation:
| Condition | Action | |-----------|--------| | No files, no subdirs | Skip — no AGENTS.md | | No files, has subdirs | Minimal AGENTS.md with subdirectory listing only | | Only generated files (*.min.js, *.map) | Skip | | Has config files | AGENTS.md describing configuration purpose |
testing
Use when creating new skills, editing existing skills, or verifying skills work before deployment
development
Use when you have a spec or requirements for a multi-step task, before touching code
data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
tools
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions