Applies plain language rules to software documentation, architecture explanations, code reviews and technical analysis, following the principles of ISO 24495-3:2026.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .claude/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .agents/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .cursor/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .gemini/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
GitHub CLI
$ gh skill install GaZmagik/iso-24495 iso-24495-3
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .github/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "iso-24495-3" agent skill from https://github.com/GaZmagik/iso-24495/tree/main/skills/iso-24495-3 into .opencode/skills/iso-24495-3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iso-24495-3", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
iso-24495-3
GitHub stars
190
Token cost
~1.6k tokens
SKILL.md length
840 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
MIT
At a glance
Applies plain language rules to software documentation, architecture explanations, code reviews and technical analysis, following the principles of ISO 24495-3:2026.
Works in 3 steps: Thinking Block Exemption → Code & Data Preservation Immunity → Document Design Applies Here Too
Writing architecture documentation that readers outside the team can follow
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Rules in this skill govern how the agent writes final, user-facing technical text: architecture notes, algorithm explanations, code review comments and scientific analysis. It extends ISO 24495-1:2023 for technical subjects. The author describes the rules as the project's own proxies for the standard's principles, so following them is not a claim of ISO conformance.
Explanations follow a fixed order: a one-sentence statement of the system's purpose, then architecture and data flow as a Mermaid diagram or summary table when several components relate to each other, then implementation detail with a code snippet and exact file citations. Internal reasoning blocks, code, stack traces, terminal commands and exact quotes are exempt from the sentence-length and simplification limits, and the sibling iso-24495-5 skill loads alongside when the output is a full document.
When your agent uses it
Writing architecture documentation that readers outside the team can follow
Explaining an algorithm or a design decision in plain language
Phrasing code review comments clearly and directly
Writing up a technical or scientific analysis for a general reader
Example prompts
“Rewrite the architecture section of our README in plain language.”
“Explain how the payment retry queue works, starting with its purpose and then the data flow.”
“Review this pull request and phrase every comment in plain technical language.”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
1Thinking Block Exemption
2Code & Data Preservation Immunity
3Document Design Applies Here Too
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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 24495-3 Technical Plain Language loads about 1.6k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 840 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~47
When it runs· the whole SKILL.md, loaded when a task matches
~1.6k
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.
Download SKILL.mdSave it as .claude/skills/iso-24495-3/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
iso-24495-3
description
Sector-specific Plain Language standard for science and technical writing (ISO 24495-3:2026). Applied during software documentation, architecture specs, and technical analysis.
metadata.version
0.7.0
metadata.iso-standard
ISO 24495-3:2026
metadata.iso-status
published
ISO 24495-3:2026 - Plain Language (Science and Technical Communication)
Proxy status: These rules are this project's own proxies for the standard's principles, not its text. Following them is never a claim of ISO conformance.
Extends ISO 24495-1:2023 for software architecture, technical documentation, algorithm explanations, code reviews, and scientific analysis.
Scope & Execution Boundaries
Thinking Block Exemption:
Internal architectural analysis, code reasoning, and mental trace blocks (the thought and thinking tags) are 100% exempt from plain language constraints.
Reason freely within thinking blocks. Apply plain language rules strictly to final user-facing technical text.
Code & Data Preservation Immunity:
Code blocks, stack traces, abstract syntax tree (AST) dumps, terminal commands, and exact line quotes are completely immune to sentence length and simplification constraints. Never alter, abbreviate, or mangle working code or logs to fit text constraints.
Document Design Applies Here Too:
A technical document is a document, so iso-24495-5 loads alongside this skill. Part 5 governs headings, navigation, chunking, signalling, and readers who cannot see the page.
It loads for a document, not for every explanation. A code review comment and a chat answer are explanations, and the rules below still govern them.
Where the two appear to conflict, follow the resolution named in the rules below.
Quantitative Rules & Hard Constraints (User-Facing Output)
Progressive Disclosure Ordering:
Structure every technical explanation in these stages, in this order:
System Purpose: High-level operational intent (1 sentence).
Architecture & Data Flow: Diagram (Mermaid) or summary table. Rule 4 governs the diagram's text alternative, and Part 5 governs the table. Required where the explanation covers how more than one component relates to another. A single mechanism needs none, and neither does a sequence of steps that an ordered list already presents in order. A diagram nobody needs is the decoration Part 5 forbids.
Implementation Detail: Concrete code snippet with exact file citations.
These stages order an explanation, and Part 5's three levels order a document. They are different axes rather than two versions of one, so they do not map one to one. Where the explanation is a document:
The purpose sentence supplies the purpose line of Part 5's opening block, and opens its overview where Part 5 calls for one. The block's title, version and named reader are not its to supply, and Part 5 still requires them of the author. That overview also keeps the conclusion, the action required and any essential qualification, which one sentence does not.
Stages 2 and 3 sit in the main body, in that order.
Part 5's optional detail holds what a reader can skip and still act on. No stage covers it, so nothing is demoted there by default.
A stage covers what the explanation contains. A runbook explains what to do and a decision record explains a choice, so neither needs stage 2's diagram of components nor stage 3's code. Omit a stage the explanation has no content for, and keep the order of those it has. They also do not exclude what a genre needs beside them: an incident report's timeline sits with the stages rather than inside one.
File & Code Citation Standard:
Quote exact file locations using markdown links with line numbers: [filename](file:///path/to/file#L10-L20).
Never describe code changes or logic without citing the exact file and line range. This governs an explanation of code. A guide describing what a user does needs no citation.
Terminology & Acronym Standardisation:
Define every acronym or domain-specific term upon first use in parentheses (e.g. "Abstract Syntax Tree (AST)").
Use consistent symbol names across text, code snippets, and diagrams.
Diagrams and Their Alternatives:
Give every diagram a text alternative saying what it shows, not what it is. Part 5 requires that of any image carrying meaning. Stage 2 above offers a diagram as one way to meet it, so this rule says where the alternative goes. A summary table is the other way, and Part 5 already governs it.
A Mermaid diagram reaches a listener as its source text, which is not an explanation. So the alternative is prose beside the diagram, never the diagram's own labels.
Show full SKILL.md (190 more words)Show less
Contrastive Examples
Example 1: Concurrency Control Explanation
❌ Not aligned (Dense & Abstract):text
In order to prevent race conditions during concurrent state mutations
within the execution pipeline, a mutex lock mechanism is introduced prior
to updating the shared buffer allocation in memory.
✅ ISO 24495-3 Aligned:
System Purpose:
Acquire a Mutex Lock to prevent data corruption during concurrent writes.
Implementation Detail:
The locking logic is implemented in state_manager.rs:L45-L52:
rust
let _guard = self.mutex.lock().unwrap();
self.buffer.update(data);
Pre-Output Self-Audit Checklist
Before outputting technical text, audit against these checks:
Progressive structure: Is system purpose stated before architecture and code?
Exact citations: Are code citations backed by file:/// links and line numbers?
Acronym definitions: Are acronyms and specialized terms defined upon first use?
Visual aids: Does a diagram or table show how components relate, unless an ordered list already presents that relationship as a sequence?
Code immunity: Are code snippets and commands intact and un-mangled?
Text alternatives: Does every diagram carry prose saying what it shows?
Layering: Where the explanation is a document, do the stages sit in Part 5's levels as rule 1 says?
Design applied: Did iso-24495-5 run over the document as well as this skill?
ISO 24495-3 Technical 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 24495-3 Technical Plain Language compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
ISO 24495-3 Technical Plain Language this skillGaZmagik/iso-24495
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
Writing developer-facing prose that can be skimmed first and trusted enough to finish — READMEs, guides, tutorials, reference docs, proposals, PR descriptions, release notes.
Writes or reviews documentation pages for the 33 JavaScript Concepts project, following its structure, a beginner-friendly voice and rules against AI-sounding language.
A skill your agent uses for planning, researching, drafting, revising, or auditing technical write-ups, textbooks, papers, reports, READMEs, research notes, PR narratives, and public technical prose.
Writes and updates Tabler documentation pages in simple English following the repository's page schema, and flags new components that have no docs yet.
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.
Makes the agent write every user-facing reply by the four plain-language principles of ISO 24495-1:2023: relevant, findable, understandable and usable.
Questions about ISO 24495-3 Technical Plain Language
What does ISO 24495-3 Technical Plain Language do?
Applies plain language rules to software documentation, architecture explanations, code reviews and technical analysis, following the principles of ISO 24495-3:2026. Rules in this skill govern how the agent writes final, user-facing technical text: architecture notes, algorithm explanations, code review comments and scientific analysis. It extends ISO 24495-1:2023 for technical subjects.
When should I use ISO 24495-3 Technical Plain Language?
ISO 24495-3 Technical Plain Language fits situations like: writing architecture documentation that readers outside the team can follow; explaining an algorithm or a design decision in plain language; phrasing code review comments clearly and directly; writing up a technical or scientific analysis for a general reader.
How do I install ISO 24495-3 Technical Plain Language in Claude Code?
Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a claude-code`. Or copy the skill folder (skills/iso-24495-3 in GaZmagik/iso-24495) into .claude/skills/iso-24495-3 in your project. Claude Code loads it when a task matches its description.
How do I install ISO 24495-3 Technical Plain Language in Codex?
Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-3 -a codex`. Or copy the skill folder (skills/iso-24495-3 in GaZmagik/iso-24495) into .agents/skills/iso-24495-3 in your project. Codex loads it when a task matches its description.
Can I use ISO 24495-3 Technical 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-24495-3 -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-24495-3, .gemini/skills/iso-24495-3, .github/skills/iso-24495-3 and .opencode/skills/iso-24495-3 in your project.
What does ISO 24495-3 Technical Plain Language need to run?
SKILL.md names no scripts, command-line tools or credentials: ISO 24495-3 Technical Plain Language is instructions for the agent only.
Does ISO 24495-3 Technical Plain Language access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is ISO 24495-3 Technical 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 24495-3 Technical Plain Language use?
ISO 24495-3 Technical 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 24495-3 Technical Plain Language use?
About 1.6k tokens (SKILL.md is roughly 6.4k 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 24495-3 Technical Plain Language?
Skills that share tags, products or a category with ISO 24495-3 Technical Plain Language: Technical Writing Standard (cursor/plugins, 11k stars), Technical Writing (citypaul/.dotfiles, 740 stars), JavaScript Concept Page Writer (leonardomso/33-js-concepts, 67k stars) and Technical Writing Workflow (tokenbender/agent-guides, 367 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ISO 24495-3 Technical 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.