Skip to content

MustafaKucukcoskun/Refine-agent-kit / .agents/skills/documentation-templates

documentation-templates

Verified

Documentation Templates

Templates and quality standards for common documentation types — with explicit anti-patterns and a decision tree for picking the right template.


Quality Standards (per template type)

TemplateGoodBadTarget length
READMEUnder 5 min to quick-startTutorial-length saga150–400 lines
API reference1 request+response per endpoint with realistic dataSchema dumps, no examples1 page per endpoint
ChangelogSemantic versioning, breaking changes flagged"Fixed stuff", "misc improvements"1 line per change
ADRContext + options + decision + rationale + consequencesDecision without options considered1–2 pages
ArchitectureDiagrams + rationale (not diagram-only)Wall of prose, no visuals2–5 pages
RFCProblem, proposal, alternatives, migrationPremature implementation detail3–10 pages
llms.txtStructured sections, definitions upfrontMarketing copy100–300 lines

Template Selection Decision Tree

Is this for humans, AI, or both?
├── Humans only
│   ├── First-time user? → README
│   ├── Looking up specifics? → API Reference
│   └── Decision trail? → ADR / Changelog
├── AI only
│   ├── Fast citation? → llms.txt
│   └── Tool calling? → MCP-Ready spec
└── Both
    ├── Tutorial-style → README with examples
    └── Reference-style → API docs with JSON/YAML samples

Is this a decision that affects future work?
→ YES → ADR (lightweight) or RFC (heavier)
→ NO → Changelog entry or inline comment

1. README Structure

Essential Sections (Priority Order)

SectionPurpose
Title + One-linerWhat is this?
Quick StartRunning in <5 min
FeaturesWhat can I do?
ConfigurationHow to customize
API ReferenceLink to detailed docs
ContributingHow to help
LicenseLegal

README Template

# 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](./docs/api.md)
- [Architecture](./docs/architecture.md)

## License

MIT

2. API Documentation Structure

Per-Endpoint Template

## GET /users/:id

Get a user by ID.

**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| id | string | Yes | User ID |

**Response:**
- 200: User object
- 404: User not found

**Example:**
[Request and response example]

3. Code Comment Guidelines

JSDoc/TSDoc Template

/**
 * Brief description of what the function does.
 * 
 * @param paramName - Description of parameter
 * @returns Description of return value
 * @throws ErrorType - When this error occurs
 * 
 * @example
 * const result = functionName(input);
 */

When to Comment

✅ Comment❌ Don't Comment
Why (business logic)What (obvious)
Complex algorithmsEvery line
Non-obvious behaviorSelf-explanatory code
API contractsImplementation details

4. Changelog Template (Keep a Changelog)

# Changelog

## [Unreleased]
### Added
- New feature

## [1.0.0] - 2025-01-01
### Added
- Initial release
### Changed
- Updated dependency
### Fixed
- Bug fix

5. Architecture Decision Record (ADR)

# ADR-001: [Title]

## Status
Accepted / Deprecated / Superseded

## Context
Why are we making this decision?

## Decision
What did we decide?

## Consequences
What are the trade-offs?

6. AI-Friendly Documentation (2025)

llms.txt Template

For AI crawlers and agents:

# Project Name
> One-line objective.

## Core Files
- [src/index.ts]: Main entry
- [src/api/]: API routes
- [docs/]: Documentation

## Key Concepts
- Concept 1: Brief explanation
- Concept 2: Brief explanation

MCP-Ready Documentation

For RAG indexing:

  • Clear H1-H3 hierarchy
  • JSON/YAML examples for data structures
  • Mermaid diagrams for flows
  • Self-contained sections

7. Structure Principles

PrincipleWhy
ScannableHeaders, lists, tables
Examples firstShow, don't just tell
Progressive detailSimple → Complex
Up to dateOutdated = misleading

Remember: Templates are starting points. Adapt to your project's needs.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide 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. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall