AugmentClaude

ISO 24495-3 Plain Language

Apply plain language standards to technical documentation, architecture specs, and scientific writing.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/iso-24495-3-gazmagik/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

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

What this skill does

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

  1. 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.
  2. 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)

  1. Progressive Disclosure Ordering: Structure all technical explanations in three strict sequential stages:

    1. System Purpose: High-level operational intent (1 sentence).
    2. Architecture & Data Flow: Diagram (Mermaid) or summary table.
    3. Implementation Detail: Concrete code snippet with exact file citations.
  2. 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.
  3. 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:

    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?

Related skills