Code Documenter

Analyzes source code to generate accurate, contextaware documentation at multiple levels: inline comments for complex logic, function/class docstrings, modulelevel overviews, architecture documents, and onboarding guides. Understands control flow, data transformations, side effects, and crossmodule dependencies.

Overview

The Code Documenter is a specialized AI agent skill hosted within the TerminalSkills/skills repository, which currently maintains a popularity of 72 stars. This tool automates the creation of technical documentation by performing deep analysis of source code structures. It evaluates control flows, data transformations, and side effects to produce multi-level outputs, ranging from function-specific docstrings to comprehensive onboarding guides and architectural overviews. Compatible with agents like Codex and Claude, it identifies cross-module dependencies to ensure context-aware documentation. By interpreting complex logic and data paths, the skill assists developers in maintaining clear, up-to-date records of their codebase without manual drafting, leveraging the broader capabilities of the TerminalSkills collection.

Use Cases

Generating comprehensive docstrings and inline comments for legacy Python codebases.
Creating high-level architectural overviews and onboarding guides for new team members.
Mapping cross-module dependencies and data transformations to document system-wide logic.

Install Notes

# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/code-documenter/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

This skill requires access to source code files to perform its analysis. Users should ensure that the AI agents utilizing this skill are operating within a secure environment and that sensitive information within the code is handled according to organizational data privacy policies.

Related Skills

Doc Coauthoring

anthropics/skills

Documents

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for reader...

Claude CodeClaude
designtesting
164,398 StarsSource linked

Docx

anthropics/skills

Documents

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, pa...

Claude
pythondocuments
164,398 StarsSource linked

PDF

anthropics/skills

Documents

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, a...

CodexClaude
pythondata
164,398 StarsSource linked

Documentation And Adrs

addyosmani/agent-skills

Documents

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Claude
typescriptdata
80,654 StarsMIT

Data360 Prepare

forcedotcom/sf-skills

Documents

Salesforce Data Cloud Prepare phase. Use this skill when the user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations. TRIGGER when: user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations, or asks about ingestion into Data Cloud. DO NO...

pythontesting
760 StarsApache-2.0

Documentation and ADRs

TerminalSkills/skills

Documents

Document decisions, not just code. The most valuable documentation captures the why — the context, constraints, and tradeoffs that led to a decision. Code shows what was built; documentation explains why it was built this way and what alternatives were considered.

CodexClaude Code
documentsdocumentation
72 StarsApache-2.0