Generate Standardized Documentation Templates
A skill providing templates for READMEs, API docs, code comments, changelogs, ADRs, and AI-friendly llms.txt docs.
Why it matters
Streamline your project's documentation process with pre-defined templates for READMEs, API references, code comments, changelogs, and Architecture Decision Records. Ensure consistency and clarity for both human and AI consumption.
Outcomes
What it gets done
Generate README and API documentation structures.
Provide guidelines for code comments and changelogs.
Create templates for Architecture Decision Records (ADRs).
Format documentation for AI-friendly consumption (LLMs, RAG).
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/ag-documentation-templates | bash Overview
Documentation Templates
A skill providing structure templates for READMEs, API docs, code comments, changelogs, ADRs, and AI-friendly llms.txt documentation. Use it when writing or restructuring any of these documentation types, adapting the template rather than following it rigidly.
What it does
Documentation Templates provides structure guidelines and templates for six common documentation types. Its README structure prioritizes sections in order - title and one-liner, a quick start runnable in under 5 minutes, features, configuration, an API reference link, contributing, and license:
### Project Name
Brief one-line description.
### Quick Start
[Minimum steps to run]
### Features
- Feature 1
- Feature 2
### Configuration
| Variable | Description | Default |
|----------|-------------|---------|
| PORT | Server port | 3000 |
### Documentation
- API Reference
- Architecture
### License
MIT
Beyond READMEs, it templates per-endpoint API documentation (parameters table, response codes, example), JSDoc/TSDoc code comments, a Keep-a-Changelog-style changelog, and an Architecture Decision Record (status, context, decision, consequences). A 2025-specific addition is AI-friendly documentation: an llms.txt template naming core files and key concepts for AI crawlers and agents, plus MCP-ready documentation guidance (clear H1-H3 hierarchy, JSON/YAML examples for data structures, Mermaid diagrams for flows, self-contained sections for RAG indexing).
When to use - and when NOT to
Use this skill when writing or restructuring a README, API reference, code comments, changelog, ADR, or AI-crawler-facing documentation. Its code-comment guidance draws a clear line: comment the why (business logic, complex algorithms, non-obvious behavior, API contracts), not the what (obvious code, every line, self-explanatory code, implementation details). All templates are explicitly starting points to adapt to the project's needs, not fill-in-the-blank forms to follow rigidly, and the skill's own structure principles emphasize scannability (headers, lists, tables), showing examples before explaining, progressive detail from simple to complex, and keeping docs up to date since outdated documentation is actively misleading.
Inputs and outputs
Input is the documentation type needed (README, API endpoint, code comment, changelog entry, ADR, or AI-crawler doc); output is the matching template filled in for the specific project - a structured README, a per-endpoint API doc block, a JSDoc/TSDoc comment, a changelog entry under Added/Changed/Fixed, an ADR, or an llms.txt file.
Who it's for
Developers and technical writers producing consistent documentation across a project - READMEs, API references, code comments, changelogs, ADRs, and now AI-crawler-facing docs - who want proven structure templates rather than reinventing documentation format per document type. The README's own essential-sections ordering is itself a priority list, not just a checklist - title and one-liner first, quick start within 5 minutes second, features third, working down to configuration, API reference, contributing, and license - so a reader gets oriented before being asked to dig into details.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.