agentleFS
frameforgedframeforged/technical-documentation-framework/publishing/SKILL.md

publishing

Skill2 starsChanged 4 months agoApache-2.0View on GitHub

Converts the final documentation into a publishable Markdown package with a README, detailed docs, glossary, troubleshooting, examples, and FAQ when applicable.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not every product needs every file, and some need more: sdk-guide.md, integration-guide.md, migration-guide.md, or runbooks/ join the …

    line 32
  2. Distinctive:

    Use lowercase file names.

    line 36
  3. Distinctive:

    Use hyphens instead of spaces.

    line 37
  4. Distinctive:

    No placeholder text remains unless intentionally marked.

    line 78
  5. Very specific:

    If the user requested a non-Markdown format, hand off to output-formats/SKILL.md — publishing is not finished until the requested artifact …

    line 80

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Publishing Skill

Purpose

Prepare the final documentation as a clean, navigable Markdown package. Markdown is the working format; if the user asked for a different deliverable (DOCX, PDF, HTML, slides), this package is the input to output-formats/SKILL.md, which handles the conversion and verification.

Default output package

docs/
├── README.md
├── overview.md
├── getting-started.md
├── concepts.md
├── architecture.md
├── configuration.md
├── api-reference.md
├── examples.md
├── troubleshooting.md
├── glossary.md
├── faq.md
└── assets/            # screenshots and rendered diagrams, referenced with relative paths

Include assets/ only when the documentation contains images. Name files NN-short-description.png in document order so converted formats keep figures in sequence.

Not every product needs every file, and some need more: sdk-guide.md, integration-guide.md, migration-guide.md, or runbooks/ join the package when the product and the request call for them (rules/structure-rules.md lists the extended set). Small products shrink to as little as README, getting-started, and troubleshooting.

File naming rules

  • Use lowercase file names.
  • Use hyphens instead of spaces.
  • Keep names descriptive.
  • Avoid unnecessary abbreviations.

README requirements

The README should include:

# Product Name

Short description.

## What It Does

## Who It Is For

## Quick Start

## Core Concepts

## Documentation Map

| Document | Description |
|---|---|

## Example Usage

## Support or Troubleshooting

Publishing checklist

  • Headings are consistent.
  • Links are valid or clearly marked as placeholders.
  • The glossary is included.
  • The README links to detailed docs.
  • Assumptions are visible.
  • The documentation language is consistent.
  • Code blocks are properly fenced.
  • Tables are readable.
  • No placeholder text remains unless intentionally marked.
  • Images referenced in the text exist in assets/ and every image is referenced from the text.
  • If the user requested a non-Markdown format, hand off to output-formats/SKILL.md — publishing is not finished until the requested artifact exists and has been verified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.