agentleFS
miniominio/skills/docs/SKILL.md

docs

Skill2 starsChanged 4 days agoApache-2.0View on GitHub

Use when writing or editing documentation and prose in a repository — READMEs, guides, tutorials, API reference, release notes, changelogs, and doc comments, in Markdown, reStructuredText, AsciiDoc, or plain text. Documentation must conform to the ISO 24495-1 Plain Language standard. This skill states that rule, gives the standard's four governing principles (relevant, findable, understandable, usable), sets out the plan, write, evaluate, and revise process, and gives a self-check to run before you save.

165 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use import-memory, perf and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • amirbironSkill

    import-memory

    Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.

    Also in 3 projects that use this

  • MicrosoftSkill

    perf

    Speed and memory performance rules for Rust crates, the Node addon, webui-framework, and webui-delivery.

    Also in 4 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 3 projects that use this

  • JkudjoSkill

    incident

    Production incident response — structured triage, hypothesis tree, safe remediation, incident record

    Also in 4 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 7 projects that use this

  • mbwsimsSkill

    impact

    This skill should be used when the user asks to "check the impact", "what will break if I change this", "blast radius", "impact analysis", "what depends on this", "who imports this", "is it safe to change this", mentions "/impact", or wants to understand the consequences of modifying a specific file or function before making changes.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a sentence does not meet the standard, rewrite it before you save the file.

    line 14
  2. Distinctive:

    Use the information to achieve their purpose.

    line 30
  3. Distinctive:

    Name the actor: Write "aimem uploads the file", not "the file is uploaded".

    line 56
  4. Distinctive:

    Use verbs, not nouns made from verbs: Write "configure", not "perform the configuration of".

    line 58
  5. Very specific:

    Talk to the reader: Use "you". Write each step as an instruction: "Run make test."

    line 60
  6. Distinctive:

    Choose the structure that fits the content: Use a numbered list for steps in order, bullets for items in no order, and a table to compare …

    line 64
  7. Distinctive:

    Evaluate: Read the draft as the reader.

    line 97
  8. Distinctive:

    When you edit someone else's page, run the same loop on the part you touch.

    line 102
  9. Distinctive:

    Findable: Do the headings say what each section holds?

    line 111

“Common” is measured: kept by at least 6 in 10 of the 129 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

docs — write documentation in plain language

Every piece of documentation you write or edit must conform to ISO 24495-1 Plain Language. This is not a preference or a house style you can trade away. If a sentence does not meet the standard, rewrite it before you save the file. The rule covers new pages, edits to existing pages, and any prose you add to a repository: READMEs, guides, tutorials, reference pages, release notes, changelogs, and doc comments.

Purpose

ISO 24495-1 is the first international standard for plain language. Its goal is to help writers create documents that readers can find, understand, and use effectively.

Definition of plain language

A document uses plain language when its wording, structure, and design enable the intended audience to:

  • Find the information they need.
  • Understand that information.
  • Use the information to achieve their purpose.

The four governing principles

  1. Relevant – Include only information readers need, based on their goals and context.
  2. Findable – Organize content so readers can quickly locate what they need.
  3. Understandable – Use familiar words, clear sentences, and logical explanations.
  4. Usable – Present information so readers can successfully act on it or make decisions.

The standard itself is a paid ISO document, so you will usually not have it. This page carries what you need to apply it: the principles above, the patterns below, and the self-check.

Why the rule is strict

Readers of technical documentation skim. They arrive from a search result in the middle of a task, many read English as a second language, and more of them are now agents or translation tools. Each of them stops at the first sentence they cannot parse. Plain writing is how a page still works for that reader.

Patterns that meet the standard

  • Lead with the point. The first sentence of a page or section says what the reader gets or must do. Background comes after.
  • One idea per sentence. Aim for sentences under 25 words. Split a sentence that joins two ideas with "and" or a semicolon.
  • Name the actor. Write "aimem uploads the file", not "the file is uploaded". Passive voice hides who does what.
  • Use verbs, not nouns made from verbs. Write "configure", not "perform the configuration of".
  • Talk to the reader. Use "you". Write each step as an instruction: "Run make test."
  • Put the condition first. "If the bucket is versioned, run …" lets the reader skip a step that does not apply to them.
  • Choose the structure that fits the content. Use a numbered list for steps in order, bullets for items in no order, and a table to compare options.
  • Write headings that name a task or answer a question. "Mount a bucket" beats "Overview". A reader who skims the headings should find their place.
  • Keep one word for one thing. Define a term on first use, then use the same term every time. Switching between "bucket", "store", and "backend" for one thing reads as three things.
  • Be concrete. Give the number, the name, or the command. Cut "simply", "just", "easily", and "various": they tell the reader nothing.

Before and after

Before:

In order to facilitate the configuration of the mount, it should be noted that the specification of a local directory is required, which will be utilized for the purposes of staging and caching.

After:

Pass a local directory with --local. aimem stages your writes there and caches reads in it.

The rewrite keeps every fact. It names the flag, says who does what, and drops the words that carried no meaning.

The process

Plain language is a loop, not a single pass:

  1. Plan. Identify the reader, their task, and what they need. Decide what the page will not cover.
  2. Write. Draft against the four principles above.
  3. Evaluate. Read the draft as the reader. Check it against the four principles and the self-check below. Where you can, have a real reader use it, or run the instructions yourself.
  4. Revise. Fix what the evaluation found, then evaluate again.

When you edit someone else's page, run the same loop on the part you touch. Do not rewrite text that already meets the standard.

Self-check before you save

Answer each question. Where the answer is no, revise.

  • Relevant. Does every section help the reader finish their task? Have you cut what they do not need?
  • Findable. Do the headings say what each section holds? Can a reader who skims land in the right place?
  • Understandable. Are the sentences short and active? Is each technical term defined the first time you use it?
  • Usable. Are the steps in the order the reader performs them? Can the reader act on the page without guessing?

What plain language is not

  • It is not simplified content. You keep the full technical meaning. You remove the difficulty the reader gains nothing from.
  • It is not a ban on technical terms. Storage docs need words like "erasure coding" and "idempotent". Define them once and reuse them.
  • It is not shorter at the cost of accuracy. Accuracy wins. If the plain wording would be wrong, write the precise wording and then explain it.
  • It is not informality. Plain writing can be formal. It cannot be vague.

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.