codebase-mapper_skill

This skill analyzes a codebase to generate architecture and stack documentation, surface patterns, dependencies, and technical debt for informed planning.

PowerShell

497

GitHub Stars

1

Bundled Files

3 weeks ago

Catalog Refreshed

1 month ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstart where the catalogue uses aiagentskills.

npx veilstart add skill toonight/get-shit-done-for-antigravity --skill codebase-mapper

SKILL.md4.5 KB

Overview

This skill analyzes an existing codebase to produce clear, actionable architecture and stack documentation that supports planning and refactoring. It inspects project structure, dependencies, integration points, and technical debt to generate ARCHITECTURE.md and STACK.md. The output is oriented toward engineers and architects who need a fast, trustworthy map of a codebase.

How this skill works

The agent scans the repository to detect project type and discover source directories, entry points, tests, and configuration files. It extracts dependency manifests, searches for coding patterns and conventions, and identifies integrations with external services. It also surfaces technical debt by locating TODOs, deprecated code, missing tests, and common debug artifacts. Finally, it synthesizes findings into two artifacts: ARCHITECTURE.md (system overview, components, data flow, integrations, conventions, debt) and STACK.md (runtime, dependencies, dev tools, infra, config).

When to use it

Onboarding new engineers to understand a repository quickly
Before planning a refactor, migration, or major feature
During due diligence for acquisitions or audits
To generate baseline documentation for legacy code
When assessing upgrade or security remediation effort

Best practices

Run the mapper from the repository root and ensure dependency manifests are present
Keep the workspace clean (exclude node_modules, build artifacts) for accurate scans
Commit generated ARCHITECTURE.md and STACK.md to a docs folder and review manually
Use the mapper output as a starting point; validate integration and dependency versions before changing infrastructure
Iterate: re-run after significant changes to keep documentation current

Example use cases

Generate a component map and dependency table before migrating to a new framework
Identify hotspots of technical debt (TODO/FIXME clusters) to prioritize cleanup sprints
Produce a one-page architecture overview for a stakeholder or engineering lead
Audit production and dev dependencies to find outdated or vulnerable packages
Document external APIs, databases, and environment variables for secure deployments

FAQ

It produces ARCHITECTURE.md with component and data-flow details, and STACK.md with runtime, dependency, and infrastructure summaries.

Which languages and package systems does it detect?

It detects common ecosystems via markers (package.json, requirements.txt, go.mod, Cargo.toml, .csproj) and adapts extraction commands accordingly.