skills.rest
serpro-workshop-fortaleza
serpro-workshop-fortalezaOFFICIAL
Explore all skills by this author →
GitHub

acquire-codebase-knowledge

Generate seven evidence-based documentation files describing an existing codebase's stack, structure, and architecture.

Updated Sep 10, 2026
Search Tags:#onboarding#technical debt#repository analysis#codebase documentation#code scan#tech stack detection#architecture mapping
One-click install
npx skills add https://github.com/serpro-workshop-fortaleza/sifap-modernization-paula --skill acquire-codebase-knowledge-serpro-workshop-fortaleza
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: acquire-codebase-knowledge
Source: https://github.com/serpro-workshop-fortaleza/sifap-modernization-paula/tree/main/.github/skills/acquire-codebase-knowledge
Command: npx skills add https://github.com/serpro-workshop-fortaleza/sifap-modernization-paula --skill acquire-codebase-knowledge-serpro-workshop-fortaleza

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? New engineers and AI agents lack a reliable, verifiable map of an unfamiliar repository, leading to guesswork about its stack, architecture, and conventions. This Skill produces seven grounded documentation files in docs/codebase/ so anyone can become productive on a codebase quickly. ## Core Features & Use Cases - Automated Repository Scan: Runs a Python script that collects directory trees, manifests, entry points, lint configs, TODOs, git churn, CI/CD, containers, and security configs. - Seven Structured Documents: Fills templates for STACK, STRUCTURE, ARCHITECTURE, CONVENTIONS, INTEGRATIONS, TESTING, and CONCERNS, with every claim backed by file evidence. - Evidence Discipline: Unknowns are marked [TODO] and intent-dependent questions are marked [ASK USER], preventing hallucinated architecture claims. - Use Case: A developer joining a legacy modernization project asks the agent to map the repository; the Skill scans it and delivers validated documentation highlighting tech debt and fragile files. ## Quick Start Ask the agent to map this codebase and generate the full documentation set under 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 scan.py script at the project root to collect manifests, entry points, lint configs, TODOs, and git churn, then fill the seven templates in docs/codebase/. Every claim must cite a file or terminal output as evidence.

What documents does codebase knowledge acquisition produce?▼

It produces seven files: STACK.md, STRUCTURE.md, ARCHITECTURE.md, CONVENTIONS.md, INTEGRATIONS.md, TESTING.md, and CONCERNS.md. Each has mandatory core sections plus optional extended sections for complex repositories.

How do I detect the tech stack of an unfamiliar repository?▼

Check manifest files like package.json, go.mod, pyproject.toml, or pom.xml, and read the Dockerfile FROM line if no manifest exists. The stack-detection reference maps each manifest and dependency to its ecosystem and framework.

Does the scan script work on monorepos?▼

Yes, it detects pnpm-workspace.yaml, lerna.json, nx.json, turbo.json, and package.json workspaces fields. Each workspace should be mapped separately since subpackages can have independent dependencies and conventions.

What are the limitations of automated codebase documentation?▼

It only documents what is verifiable in files or terminal output; team intent and planned architecture cannot be inferred. Such gaps are marked [ASK USER], and generated output directories like dist/ or build/ are excluded from convention claims.

Related Skills

Explore More Software Engineering Skills→
ProtremixProtremix

commit-archaeologist

Reconstructs why code exists by tracing local git history, authorship, and commit intent signals.

Official
Intermediate
Ethical-AI-SyndicateEthical-AI-Syndicate
1

technical-debt-cataloger

Document, prioritize, and plan remediation for technical debt across software projects.

Official
Advanced
shalevaminshalevamin

spec-miner

Extract software specifications from codebases using EARS format.

Community
Advanced
vickysrawatvickysrawat
1

explain

Answers codebase questions from architecture docs and the knowledge graph without scanning source.

Community
Intermediate