mcpbeat Sign in

Iso 24495 3 Agent Skill

Sector-specific Plain Language standard for science and technical writing (ISO 24495-3:2026). Applied during software documentation, architecture specs, and technical analysis.

891 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
109
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/GaZmagik/iso-24495 --skill iso-24495-3

What comes with it

260 bytes besides the instruction
agents/openai.yaml

The instruction itself

6 sections, as written by the author

ISO 24495-3:2026 - Plain Language (Science and Technical Communication)

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 (<thought>, <thinking>) 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.

Quantitative Rules & Hard Constraints (User-Facing Output)

  • Progressive Disclosure Ordering:

Structure all technical explanations in three strict sequential stages:

  • System Purpose: High-level operational intent (1 sentence).
  • Architecture & Data Flow: Diagram (Mermaid) or summary table.
  • Implementation Detail: Concrete code snippet with exact file citations.
  • File & Code Citation Standard:
  • Quote exact file locations using markdown links with line numbers: filename.
  • Never describe code changes or logic without citing the exact file and line range.
  • 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.

Contrastive Examples

Example 1: Concurrency Control Explanation

  • Not aligned (Dense & Abstract):
  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:

> Concurrency Control:

> Acquire a Mutex Lock to prevent data corruption during concurrent writes.

>

> Implementation:

> 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: Are diagrams or tables used to explain multi-step flows?
  • [ ] Code immunity: Are code snippets and commands intact and un-mangled?

How to use it

Copy the folder

Take gazmagik/iso-24495-3 from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.