- Design doc with full spec (dense markdown format, hybrid AST+LLM pipeline, consumption model, stale data mitigation) - Implementation plan with 6 milestones and rollout strategy - TypeScript package structure with all source stubs - CLI entry point, formatter, discover, init, patch, validate, extract, merge - Pi SKILL.md with tool definitions and format documentation
1.7 KiB
pi-project-map
A Pi skill that generates and maintains a hierarchical, machine-readable analysis of a software project. Each directory gets a .pi-map.md file containing architectural context, exported symbols, and dependencies.
Tools
project-map:init [root]
Runs a full project scan and generates .pi-map.md files in every directory.
project-map:patch <file-path>
Updates the .pi-map.md for the directory containing the given file. Uses full rewrite for small packages (< 10 files) or section-level patch for larger packages.
project-map:validate [root]
Checks all .pi-map.md files for staleness: missing files, orphaned entries, changed signatures, and dirty markers.
project-map:reinit [path]
Force full re-initialization of the entire project or a specific subtree. Clears all dirty markers.
Format
Each .pi-map.md uses dense markdown with conventions:
# pkg/auth
## role
Auth layer: JWT issuance, validation, refresh. Stateless. Dep: pkg/crypto, pkg/db.
## files
- tokens.ts | JWT gen/val | exp: issueToken, verifyToken, refreshToken | dep: crypto/hmac, db/sessions
- middleware.ts | HTTP auth guard | exp: requireAuth, requireRole | dep: tokens/verifyToken
## arch
Guard pattern on routes. Tokens short-lived (15m), refresh long-lived (7d). Rotation on every use.
## dirty
-
Configuration
Create .pi-project-map.json in the project root:
{
"ignorePatterns": ["node_modules", ".git"],
"smallPackageThreshold": 10,
"llmModel": "gpt-4o-mini",
"contextBudget": 4000,
"autoInjectPrompt": true
}
Installation
npm install -g pi-project-map
Then add to your Pi skills configuration.