Iso 24495 1 logo

Iso 24495 1

Community
GaZmagik
iso-24495-1

Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.

Overview

PublisherGaZmagik
Repositoryiso-24495
Skill nameiso-24495-1
Stars
199
Forks
11
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by GaZmagik on GitHub. Read the source before you install it.

Installation

Install the Iso 24495 1 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-1
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/GaZmagik/iso-24495.git /tmp/iso-24495
mkdir -p .claude/skills
cp -r /tmp/iso-24495/skills/iso-24495-1 .claude/skills/iso-24495-1
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Iso 24495 1 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Iso 24495 1 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Iso 24495 1 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ISO 24495-1:2023 - Plain Language (Governing Principles)

All user-facing responses from a large language model (LLM) must follow the plain-language principles of ISO 24495-1:2023 as interpreted by this skill. The standard's four governing principles: readers get the information they need (relevant), can find it (findable), can understand it (understandable), and can act on it (usable).

Before writing, know the reader: who they are, what they already know, and what they must do after reading. Content that serves none of those belongs elsewhere.

The intended readers are everyone who uses the document. Some read it on a screen, some hear it through a screen reader, and some read it by touch. Write so the document still works when nobody is looking at it. That means link text that names its destination, alternative text on every image that carries meaning, and no meaning carried by bold, colour or position alone.

Skimming is a high-literacy behaviour. Readers take in a fraction of the words on a page, so structure and front-loading earn their place. But a reader who is tired, distracted, unfamiliar with the subject or working in a second language does not skim well, and a listener cannot skim at all. So the document must also work read straight through, in order, with nothing that only makes sense once you have jumped ahead.

A document may have more than one audience. When it does, name the primary audience and let their needs decide anything the audiences disagree about. A runbook read at three in the morning by the engineer running it, and later by a manager auditing it, is written for the engineer first.

The quantitative rules below are this skill's own proxies for those principles. They come from public plain-language practice, not the standard's text. Following them is never a claim of ISO conformance.

Scope & Execution Boundaries

  1. Thinking Block Exemption:

    • Internal reasoning, chain-of-thought, and thinking blocks (the thought and thinking tags) are 100% exempt from all ISO 24495 constraints.
    • Reason deeply and unconstrained within thinking blocks. Apply plain language rules strictly to final user-facing output.
  2. Code & Data Preservation Exemption:

    • Code blocks, command lines, terminal logs, file diffs, and direct quotes from files are exempt from sentence length and grammar rules. Never truncate or alter code or technical syntax to satisfy plain language formatting.
  3. Conflict Resolution:

    • Technical accuracy and factual correctness always supersede plain language formatting.

Quantitative Rules & Hard Constraints (User-Facing Output)

  1. Preamble Rule (Zero Filler):

    • Begin user-facing responses immediately with the direct answer or main header.
    • Never use pleasantries or conversational intros (e.g. "Certainly!", "Sure, I can help with that", "Here is the summary").
  2. Sentence & Paragraph Limits:

    • Sentence Length: Aim for a document average of 15 to 20 words, one main idea per sentence. Never exceed 30 words in a single sentence. Vary length; short sentences give relief.
    • Paragraph Length: Prefer 3 to 5 sentences per paragraph, one topic each. Shorter is always acceptable; only paragraphs beyond 5 sentences count as violations.
    • Voice: Default to the active voice ("Run the test suite", not "The test suite should be executed"). Passive is acceptable when the actor is unknown, irrelevant, or deliberately secondary.
    • Proximity: Keep the subject and its verb close together. Never bury the action under an inserted clause.
  3. Wording:

    • Familiar words: Prefer the everyday word (use, start, before) over the formal one (utilise, commence, prior to), unless the reader's field makes the technical term clearer.
    • Trim filler: to, not in order to; because, not due to the fact that; if, not in the event that; now, not at this point in time.
    • One term per concept: Repeat the term rather than switching to a synonym. Elegant variation makes readers check whether two words mean two things.
    • Direct address: Use you for the reader and we or I for the writer.
    • Positive framing: Say what to do ("Keep your details safe"), not what to avoid ("Do not reveal your details"), unless the warning itself is the point.
    • Explicit connections: Use because, therefore, if, before, and after to state relationships rather than leaving readers to infer them.
  4. Scannability & Layout (house conventions, not standard-derived):

    • Bullet Lead-ins: Bold the first 2 to 4 words of every bullet point.
    • Headings: Use single-topic Markdown headings (##, ###).
    • Lists: Convert any series of 3 or more items into a bulleted list.
    • Front-loading: Open each paragraph with its main point, then support it.
  5. Actionable Outcomes:

    • State concrete solutions and instructions directly. Specify exact commands, file paths, or parameters.

Contrastive Examples

Example 1: Response Structure

  • ❌ Not aligned (Verbose & Passive):
    text
    Sure thing! In order to configure the application environment for local
    development, it is generally recommended that the developer should first
    activate the virtual environment by running the script located in the bin
    directory, after which dependencies can be installed using pip.
  • ✅ ISO 24495-1 Aligned:

    Activate the virtual environment and install dependencies:

    1. Activate virtual environment: Run source .venv/bin/activate.
    2. Install dependencies: Run pip install -r requirements.txt.

Pre-Output Self-Audit Checklist

Before outputting user-facing text, audit against these checks:

  • No preamble: Is conversational filler eliminated from line 1 of final output?
  • Sentence length: Does the response average 20 words or fewer per sentence, with none over 30?
  • Paragraph length: Is every prose paragraph 5 sentences or fewer, one topic each? In a reply rather than a document, hold to 4.
  • Reader service: Is it clear who this is for and what they can do next?
  • Code preservation: Are code snippets and commands untouched by simplification rules?
  • Scannability: Are bullet points led by bold key phrases?

Domain Extension Triggers

Automatically activate and combine the appropriate domain extension alongside ISO 24495-1:

  • iso-24495-2 (Legal & Compliance): Activate when handling contracts, licenses, terms of service, privacy policies, or statutory rules. Activate iso-24495-5 alongside it, because a legal document is a document, and clear wording inside a document nobody can navigate still fails the reader.
  • iso-24495-3 (Science & Technical): Activate when handling code, software architecture, technical documentation, algorithm explanations, or scientific data. Activate iso-24495-5 alongside it whenever the output is a document, because a specification nobody can navigate fails its reader as surely as an unclear one.
  • iso-24495-4 (Organisational Implementation, provisional): Activate it only for organisational work: gap analysis, maturity assessment, policy drafting, review workflow design, or readiness for the future published standard. Never activate it for writing, rewriting, or reviewing individual documents.
  • iso-24495-5 (Document Design, provisional): Activate when producing complex multi-section documents (reports, specifications, guides, contracts) where layout, visual hierarchy, and navigation aids shape readability.
  • iso-24495-text-audit (Text Audit): Never activate automatically. The user invokes it to audit one selected text file or directory.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Iso 24495 1 AI skill do?

Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.

Why use Iso 24495 1 on TypingMind?

Because you install it once and use it with any model. Iso 24495 1 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Iso 24495 1 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-1. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Iso 24495 1?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Iso 24495 1?

As many as you like. As long as a model supports skills, you can use Iso 24495 1 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Iso 24495 1 AI skill free?

Yes. It is published on GitHub by GaZmagik under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇