Agent skill

ISO 24495-1 Plain Language

by GaZmagik in GaZmagik/iso-24495

Makes the agent write every user-facing reply by the four plain-language principles of ISO 24495-1:2023: relevant, findable, understandable and usable.

MITAuto-check passedWriting & Content

Install ISO 24495-1 Plain Language

skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-1 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GaZmagik/iso-24495 iso-24495-1 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GaZmagik/iso-24495.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/iso-24495-1 .claude/skills/iso-24495-1 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
iso-24495-1
GitHub stars
190
Token cost
~2k tokens
SKILL.md length
1,048 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Makes the agent write every user-facing reply by the four plain-language principles of ISO 24495-1:2023: relevant, findable, understandable and usable.

  • Works in 3 steps: Thinking Block Exemption → Code & Data Preservation Exemption → Conflict Resolution
  • You want every agent reply written in clear, structured plain language
  • SKILL.md covers Scope & Execution Boundaries, Quantitative Rules & Hard…, Contrastive Examples and Pre-Output Self-Audit Checklist, plus 1 more section
  • Calls pip

What it does

This skill sets a standing rule: every reply meant for a reader must follow the four governing principles of ISO 24495-1:2023, so readers get the information they need, can find it, can understand it and can act on it. Before writing, the agent identifies who the reader is, what they already know and what they must do afterward, and it moves out any content that serves none of that.

Accessibility is treated as part of the job: link text that names its destination, alternative text for meaningful images, and no meaning carried by bold, colour or position alone. Documents should work when read straight through as well as skimmed, and a document with several audiences gets a named primary one. Internal reasoning blocks, code, command lines, logs, diffs and quotes from files are exempt. The numeric rules are the skill's own proxies, and following them is not a claim of ISO conformance.

When your agent uses it

  • You want every agent reply written in clear, structured plain language
  • Drafting documentation that screen reader users and second-language readers must follow
  • Rewriting dense instructions so readers can act on them

Example prompts

  • “Rewrite this onboarding email so a first-time user can follow it without help.”
  • “Explain this deployment runbook for the engineer on call at night, not for the auditor.”
  • “Apply plain-language principles to the error messages in our checkout flow.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Thinking Block Exemption
  2. Code & Data Preservation Exemption
  3. Conflict Resolution

What it can do on your machine

Read from SKILL.md and the folder at commit 5951eb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ISO 24495-1 Plain Language loads about 2k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 1,048 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GaZmagik/iso-24495 at commit 5951eb7, republished under its MIT licence (© GaZmagik). 1,048 words, ~2,026 tokens.

Download SKILL.mdSave it as .claude/skills/iso-24495-1/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
iso-24495-1
description
Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.
metadata.version
0.7.0
metadata.iso-standard
ISO 24495-1:2023
metadata.iso-status
published

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.

Show full SKILL.md (347 more words)Show less

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.

© GaZmagik, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/iso-24495-1 of GaZmagik/iso-24495.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 5951eb7

Compare with similar skills

ISO 24495-1 Plain Language next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ISO 24495-1 Plain Language compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ISO 24495-1 Plain Language this skillGaZmagik/iso-24495190—~2kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
Defensive Writing Editorlennney/stop-that-shit2.5k1 repos~1.2kAutomated safety check: PassMIT
Chinese Technical Writingleter/zh-tech-writing352—~656Automated safety check: PassMIT
Oil Tone Chinese Writing Styleoil-oil/oil-tone229—~517Automated safety check: PassMIT
Declaudingoaustegard/claude-skills150—~5.2kAutomated safety check: PassMIT

Similar skills

  • Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Defensive Writing Editor

    lennney/stop-that-shit

    Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

    2.5k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed
  • Chinese Technical Writing

    leter/zh-tech-writing

    Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.

    352 GitHub stars~656 tokensUpdated 16 days ago
    Writing & ContentAuto-check passed
  • Chinese-language style guide that keeps articles, scripts and product copy natural, readable and fact-grounded, with a lint script that flags tired phrasing.

    229 GitHub stars~517 tokensUpdated 17 days ago
    Writing & ContentAuto-check passed
  • Declauding

    oaustegard/claude-skills

    Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.

    150 GitHub stars~5.2k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Rewrites docs, READMEs, issues, comments or UI text in plain Global English that translates well and still sounds native, keeping every fact intact.

    138 GitHub stars~1.1k tokensUpdated today
    Writing & ContentAuto-check passed

More from GaZmagik/iso-24495

All 8 skills in this repo
  • Assesses how ready an organization is to produce plain language, through evidence sweeps, interviews and a maturity gap report.

    190 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • ISO 24495 Text Audit

    GaZmagik/iso-24495

    Audits a Markdown or text file or folder you choose for plain-language problems such as legalese, wordy phrases and long sentences, reporting each finding with file and line.

    190 GitHub stars~817 tokensUpdated 2 days ago
    Auto-check passed
  • Iso 24495 5

    GaZmagik/iso-24495

    Provisional sector-specific Plain Language standard for document design (based on ISO/WD 24495-5, under development).

    190 GitHub stars~3.7k tokensUpdated 2 days ago
    Auto-check passed
  • Applies ISO 24495-2 style plain-language rules to contracts and legal writing, standardizing modal verbs without weakening enforceability.

    190 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Applies plain language rules to software documentation, architecture explanations, code reviews and technical analysis, following the principles of ISO 24495-3:2026.

    190 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Iso 24495 Code

    GaZmagik/iso-24495

    Plain language applied to source code (ISO 24495-1:2023 principles).

    190 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

Questions about ISO 24495-1 Plain Language

What does ISO 24495-1 Plain Language do?

Makes the agent write every user-facing reply by the four plain-language principles of ISO 24495-1:2023: relevant, findable, understandable and usable. This skill sets a standing rule: every reply meant for a reader must follow the four governing principles of ISO 24495-1:2023, so readers get the information they need, can find it, can understand it and can act on it. Before writing, the agent identifies who the reader is, what they already know and what they must do afterward, and it moves out any content that serves none of that.

When should I use ISO 24495-1 Plain Language?

ISO 24495-1 Plain Language fits situations like: you want every agent reply written in clear, structured plain language; drafting documentation that screen reader users and second-language readers must follow; rewriting dense instructions so readers can act on them.

How do I install ISO 24495-1 Plain Language in Claude Code?

Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-1 -a claude-code`. Or copy the skill folder (skills/iso-24495-1 in GaZmagik/iso-24495) into .claude/skills/iso-24495-1 in your project. Claude Code loads it when a task matches its description.

How do I install ISO 24495-1 Plain Language in Codex?

Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-1 -a codex`. Or copy the skill folder (skills/iso-24495-1 in GaZmagik/iso-24495) into .agents/skills/iso-24495-1 in your project. Codex loads it when a task matches its description.

Can I use ISO 24495-1 Plain Language in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GaZmagik/iso-24495 --skill iso-24495-1 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iso-24495-1, .gemini/skills/iso-24495-1, .github/skills/iso-24495-1 and .opencode/skills/iso-24495-1 in your project.

What does ISO 24495-1 Plain Language need to run?

Going by SKILL.md and its folder, ISO 24495-1 Plain Language needs the command-line tools its instructions call (pip).

Does ISO 24495-1 Plain Language access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is ISO 24495-1 Plain Language safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ISO 24495-1 Plain Language use?

ISO 24495-1 Plain Language is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ISO 24495-1 Plain Language use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to ISO 24495-1 Plain Language?

Skills that share tags, products or a category with ISO 24495-1 Plain Language: Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars), Defensive Writing Editor (lennney/stop-that-shit, 2.5k stars), Chinese Technical Writing (leter/zh-tech-writing, 352 stars) and Oil Tone Chinese Writing Style (oil-oil/oil-tone, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ISO 24495-1 Plain Language?

GaZmagik (a GitHub user) maintains it in GaZmagik/iso-24495, which has 190 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 9, 2026.

Source: GaZmagik/iso-24495 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.