Documentation and ADRs
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.
Overview
The Documentation and ADRs skill, part of the TerminalSkills/skills repository, provides AI agents like Claude and Gemini with a framework for capturing architectural decision records (ADRs). Rather than focusing solely on code output, this skill emphasizes the preservation of technical context, including the specific constraints and tradeoffs encountered during development. By documenting the rationale behind design choices, the skill ensures that the "why" of a project is as accessible as the "what." This approach helps maintain long-term project health by recording rejected alternatives and decision-making logic. As a component of the TerminalSkills collection, which has garnered 72 stars on GitHub, this skill facilitates structured data validation and comprehensive documentation workflows across various compatible AI platforms.
Use Cases
Install Notes
# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/documentation-and-adrs/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
Security Notes
Users should ensure that any architectural decision records generated do not inadvertently include sensitive credentials or internal infrastructure secrets. Since this skill focuses on documenting the logic and constraints of a project within the TerminalSkills/skills repository, standard data validation practices should be applied to all output to maintain security compliance across compatible agents.
Related Skills
Doc Co-Authoring Workflow
anthropics/skills
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 readers.
PDF Processing Guide
anthropics/skills
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, and
DOCX creation, editing, and analysis
anthropics/skills
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when ex
Code Documenter
TerminalSkills/skills
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.