Agent skill

ISO 24495 Text Audit

by GaZmagik in 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.

MITAuto-check passedWriting & Content

Install ISO 24495 Text Audit

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

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

GitHub CLI
$ gh skill install GaZmagik/iso-24495 iso-24495-text-audit --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-text-audit .claude/skills/iso-24495-text-audit && 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-text-audit
GitHub stars
190
Token cost
~817 tokens
SKILL.md length
444 words
Files
4 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 10 steps: Read the path from $ARGUMENTS. Ask for a… → Resolve the audit script relative to… → State the selected file or directory… → …
  • Checking a README or docs page for wordy or hard-to-read phrasing
  • SKILL.md covers Language and input scope, Workflow and Boundaries
  • Runs TypeScript scripts from its folder

What it does

This skill runs a deterministic audit script with Bun on the path you name and reads nothing outside it unless you agree. It supports English only. Word rules look for legalese, doublets, wordy phrases, filler openings, complex words and double negatives, a link-text rule flags empty or bare-URL labels, and further rules cover sentence length, the average sentence, paragraph length (a limit of five sentences) and prose enumeration.

Each finding is reported with its file, line, rule and an explanation. Skipped or unreadable entries are listed so an incomplete audit is never called clean, and the agent explains that the results are mechanical proxies for ISO 24495, not an ISO judgment. A flag lets a leading front matter block be read as text for content such as pull request descriptions. The skill is meant to be invoked explicitly, and any rewriting is left to you.

When your agent uses it

  • Checking a README or docs page for wordy or hard-to-read phrasing
  • Auditing a pull request description as plain text
  • Scanning a folder of Markdown files for long sentences and paragraphs

Example prompts

  • “Run the ISO 24495 text audit on docs/getting-started.md.”
  • “Audit the whole ./content folder for plain-language problems and list the findings by file.”
  • “Audit my PR description in pr.txt, and don't treat the top block as front matter.”

Requirements

  • Bun, to run the audit script

Workflow steps

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

  1. Read the path from $ARGUMENTS. Ask for a path when none was supplied.
  2. Resolve the audit script relative to this SKILL.md file.
  3. State the selected file or directory before running the script.
  4. Treat an explicitly supplied directory as approval to read that directory.
  5. Ask before expanding the audit beyond the supplied path.
  6. Run the script with Bun
  7. Report every finding with its file, line, rule, and explanation.
  8. Report skipped or unreadable entries. Never treat an incomplete audit as clean.
  9. Explain that findings are mechanical proxies, not an ISO judgement.
  10. Leave the final decision and any rewriting request to the user.

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

    Ships 2 files in scripts/ (TypeScript), which the agent can run.

    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 Text Audit loads about 817 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 444 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~817

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); the scripts in this folder are not scanned.

SKILL.md

The full file from GaZmagik/iso-24495 at commit 5951eb7, republished under its MIT licence (© GaZmagik). 444 words, ~817 tokens.

Download SKILL.mdSave it as .claude/skills/iso-24495-text-audit/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
iso-24495-text-audit
description
Audit user-selected Markdown or text files for deterministic plain-language findings. Use only when the user explicitly invokes this skill.
disable-model-invocation
true
argument-hint
[file-or-directory]
metadata.version
0.7.0

ISO 24495 Text Audit

Audit only the path the user selects. Report mechanical findings so the user can decide whether the text suits its readers and purpose.

Language and input scope

The audit is written for English and supports English only. The skills and output style are instructions a model interprets, so they are not limited to English in the same way.

Its word rules match English words and phrases: legalese, doublet, wordy-phrase, filler-opening, complex-word, double-negative, and the phrases link-text looks for. The filler-opening rule checks only the opening prose. The link-text rule also flags empty labels and labels that are bare web addresses.

Five word rules read headings as well as prose: legalese, doublet, wordy-phrase, complex-word, and double-negative. The rules about sentences and paragraphs read prose only, because a heading is not a sentence.

The sentence-length and sentence-average rules count words separated by whitespace, including spaces and line breaks, and use English benchmarks. The paragraph-length rule counts sentences, with a limit of five.

The prose-enumeration rule flags three or more distinct ranks in a prose block, including rank one. It recognises English ordinal words and numbered markers from one to six.

The audit reads Markdown as written and does not interpret raw HTML. It sets HTML tags aside and reads the text between them, even where GitHub would hide or change that text.

Show full SKILL.md (220 more words)Show less

Workflow

  1. Read the path from $ARGUMENTS. Ask for a path when none was supplied.
  2. Resolve the audit script relative to this SKILL.md file.
  3. State the selected file or directory before running the script.
  4. Treat an explicitly supplied directory as approval to read that directory.
  5. Ask before expanding the audit beyond the supplied path.
  6. Run the script with Bun:
text
bun <skill-directory>/scripts/audit-text-cli.ts <file-or-directory> --project-dir <project-directory>

Add --no-front-matter for text that cannot carry metadata, such as a pull request description. A leading --- block is then read as text, not set aside as front matter.

  1. Report every finding with its file, line, rule, and explanation.
  2. Report skipped or unreadable entries. Never treat an incomplete audit as clean.
  3. Explain that findings are mechanical proxies, not an ISO judgement.
  4. Leave the final decision and any rewriting request to the user.

Boundaries

  • Read .md, .markdown, and .txt files only.
  • Do not follow a selected or nested symbolic link or directory junction. Report each one as skipped.
  • Do not alter the selected text unless the user separately requests changes.
  • Do not create a report file unless the user requests one and names its location.
  • Do not describe zero findings as proof that text is valid, compliant, or suitable.
  • Use the relevant sector skill when interpreting findings in legal, technical, scientific, or designed documents.

© 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 3 other files (scripts) in skills/iso-24495-text-audit of GaZmagik/iso-24495.

  • SKILL.md
  • agents/openai.yaml
  • scripts/audit-text-cli.ts
  • scripts/audit-text.ts

Open the folder on GitHubat commit 5951eb7

Compare with similar skills

ISO 24495 Text Audit 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 Text Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ISO 24495 Text Audit this skillGaZmagik/iso-24495190—~817Automated safety check: PassMIT
Tabler Docs Writertabler/tabler42k—~2.5kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
JavaScript Concept Page Writerleonardomso/33-js-concepts67k—~14kAutomated safety check: PassMIT
Chinese Technical Writingleter/zh-tech-writing352—~656Automated safety check: PassMIT
Technical Writing Workflowtokenbender/agent-guides367—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Tabler Docs Writer

    tabler/tabler

    Writes and updates Tabler documentation pages in simple English following the repository's page schema, and flags new components that have no docs yet.

    42k GitHub stars~2.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Official

    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.

    11k GitHub starsUsed in 10 repos~2.3k tokens
    Writing & ContentAuto-check passed
  • JavaScript Concept Page Writer

    leonardomso/33-js-concepts

    Writes or reviews documentation pages for the 33 JavaScript Concepts project, following its structure, a beginner-friendly voice and rules against AI-sounding language.

    67k GitHub stars~14k tokensUpdated 1 mo ago
    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
  • Technical Writing Workflow

    tokenbender/agent-guides

    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.

    367 GitHub stars~1.3k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Nbj Write Clearly

    daniel-p-green/nbj-write-clearly

    Drafts, revises, and audits reader-first technical and product documentation.

    117 GitHub stars~1.1k tokensUpdated 1 mo ago
    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 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
  • ISO 24495-1 Plain Language

    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.

    190 GitHub stars~2k 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 Text Audit

What does ISO 24495 Text Audit do?

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. This skill runs a deterministic audit script with Bun on the path you name and reads nothing outside it unless you agree. It supports English only.

When should I use ISO 24495 Text Audit?

ISO 24495 Text Audit fits situations like: checking a README or docs page for wordy or hard-to-read phrasing; auditing a pull request description as plain text; scanning a folder of Markdown files for long sentences and paragraphs.

How do I install ISO 24495 Text Audit in Claude Code?

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

How do I install ISO 24495 Text Audit in Codex?

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

Can I use ISO 24495 Text Audit 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-text-audit -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-text-audit, .gemini/skills/iso-24495-text-audit, .github/skills/iso-24495-text-audit and .opencode/skills/iso-24495-text-audit in your project.

What does ISO 24495 Text Audit need to run?

Going by SKILL.md and its folder, ISO 24495 Text Audit needs TypeScript for the scripts in its folder. Our summary lists: Bun, to run the audit script.

Does ISO 24495 Text Audit 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 Text Audit 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does ISO 24495 Text Audit use?

ISO 24495 Text Audit 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 Text Audit use?

About 817 tokens (SKILL.md is roughly 3.3k 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 Text Audit?

Skills that share tags, products or a category with ISO 24495 Text Audit: Tabler Docs Writer (tabler/tabler, 42k stars), Technical Writing Standard (cursor/plugins, 11k stars), JavaScript Concept Page Writer (leonardomso/33-js-concepts, 67k stars) and Chinese Technical Writing (leter/zh-tech-writing, 352 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ISO 24495 Text Audit?

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.