skills.rest
5onyy
5onyyCOMMUNITY
Explore all skills by this author →
GitHub

acquire-codebase-knowledge

Generates seven evidence-based documentation files mapping an existing codebase's stack, structure, and risks.

Updated Apr 9, 2026
Search Tags:#code analysis#onboarding#monorepo#tech debt#codebase documentation#architecture mapping#repository scan
One-click install
npx skills add https://github.com/5onyy/essential-ai-agent-skills --skill acquire-codebase-knowledge-5onyy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: acquire-codebase-knowledge
Source: https://github.com/5onyy/essential-ai-agent-skills/tree/main/.cursor/skills/acquire-codebase-knowledge
Command: npx skills add https://github.com/5onyy/essential-ai-agent-skills --skill acquire-codebase-knowledge-5onyy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Onboarding into an unfamiliar repository is slow and error-prone: READMEs are often outdated, architecture is undocumented, and tech debt is invisible. This Skill systematically scans a codebase and produces seven verifiable documentation files so developers can work effectively on the project without guessing. ## Core Features & Use Cases - Automated Repository Scanning: Runs a Python scan script that detects manifests for 25+ languages, CI/CD pipelines, containers, security configs, code metrics, git churn, and TODO/FIXME markers. - Seven Structured Documents: Populates STACK.md, STRUCTURE.md, ARCHITECTURE.md, CONVENTIONS.md, INTEGRATIONS.md, TESTING.md, and CONCERNS.md in docs/codebase/, with every claim traceable to source files. - Evidence-First Discipline: Unknowns are marked [TODO], intent-dependent decisions are marked [ASK USER], and a validation loop rejects unsupported claims before finalizing. - Use Case: A developer joining a legacy monorepo asks the agent to "map this codebase" and receives a complete, evidence-backed documentation set including high-churn fragile areas and security concerns. ## Quick Start Ask the agent to map this codebase and generate onboarding documentation in docs/codebase/ using the acquire-codebase-knowledge skill.

Frequently Asked Questions about acquire-codebase-knowledge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I document an existing codebase automatically?▼

Run the skill's scan.py script from the project root, then follow the four-phase workflow to populate seven templates covering stack, structure, architecture, conventions, integrations, testing, and concerns. Every claim must cite a source file or terminal output.

What languages and project types does the codebase scan support?▼

The scan detects manifests for over 25 ecosystems including Node.js, Python, Go, Rust, Java, Ruby, PHP, .NET, and Elixir. It also detects monorepo tools like pnpm workspaces, Nx, Turborepo, and Lerna.

Can I document only one area like architecture or testing?▼

Yes, focus area mode lets you specify a scope such as "architecture only" or "testing and concerns". The scan still runs in full, focus documents are completed first, and other documents keep required sections with [TODO] markers.

Does the codebase scanner work on monorepos?▼

Yes, it detects monorepo signals such as pnpm-workspace.yaml, nx.json, turbo.json, and packages/ or apps/ directories. Each workspace is mapped separately since sub-packages may have independent dependencies and conventions.

What are the requirements to run the scan script?▼

The scan requires Python 3.8+ and git, and must run from the target project root. It uses only Python standard library modules, so no pip installs are needed. Git history features are skipped gracefully in non-git directories.

When should I not use codebase documentation generation?▼

Do not trigger it for routine feature implementation, bug fixes, or narrow code edits. It is designed for repository-level discovery requests like onboarding, architecture mapping, or full codebase documentation.

Related Skills

Explore More Software Engineering Skills→
githubgithub
38.5k

acquire-codebase-knowledge

Generates seven evidence-backed documentation files describing a codebase's stack, structure, and risks.

Official
Advanced
Andy-HNUAndy-HNU

technical-roadmaps

Create structured technical roadmaps using Rumelt's Diagnosis, Guiding Policies, and Actions framework.

Community
Intermediate
knowz-ioknowz-io
1

knowzcode-audit

Audit source code against technical specifications and assess security risks.

Official
Advanced
Soham407Soham407
1

zoom-out

Map relevant modules and callers using domain glossary vocabulary.

Community
Basic