New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

ISO 24495-4 Plain Language Audit

by GaZmagik in GaZmagik/iso-24495

Assesses how ready an organization is to produce plain language, through evidence sweeps, interviews and a maturity gap report.

MITAuto-check passedWriting & Content

Install ISO 24495-4 Plain Language Audit

skills CLI
$ npx skills add GaZmagik/iso-24495 --skill iso-24495-4 -a claude-code

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

GitHub CLI
$ gh skill install GaZmagik/iso-24495 iso-24495-4 --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-24495-4 .claude/skills/iso-24495-4 && 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-24495-4
GitHub stars
190
Token cost
~1.3k tokens
SKILL.md length
645 words
Files
66 (incl. scripts, references, assets)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Assesses how ready an organization is to produce plain language, through evidence sweeps, interviews and a maturity gap report.

  • Works in 3 steps: Activation Rules → Confirmation Before Sweeps → Evidence Primacy
  • Running a plain language gap analysis for an organization
  • SKILL.md covers Scope & Execution Boundaries, The Audit Workflow, Quantitative Rules & Hard… and Contrastive Examples, plus 1 more section
  • Runs TypeScript scripts from its folder; calls bun

What it does

This provisional skill treats plain language as an organizational capability rather than a writing task. It is based on the public scope of the committee draft ISO/CD 24495-4, which is not yet published, so the guidance is original, reproduces no ISO text and its output is never a compliance statement. It assesses governance, capability, process, measurement and culture instead of the quality of any single document, and it is not used for writing, rewriting, summarizing or reviewing individual documents, which the sibling iso-24495-1, -2, -3 and -5 skills handle.

The audit runs in order. A Bun script, audit-evidence-cli.ts, sweeps a workspace for process artifacts such as policy, review workflow, automated checks, training and glossary, noting presence only. A second script, audit-corpus-cli.ts, audits a document corpus and feeds only the measurement dimension, since text quality alone never raises a maturity level. The agent then asks three to five interview questions about what files cannot show, such as leadership and culture, and scoring and report scripts produce a maturity score and a gap report. It names the directory it will sweep and asks you to confirm first, and asserts no maturity level without evidence.

When your agent uses it

  • Running a plain language gap analysis for an organization
  • Drafting a plain language policy or style guide
  • Designing a review workflow or training plan for clear writing
  • Preparing the organization for the future published standard

Example prompts

  • “Run a plain language maturity assessment of the documents in ./workspace and produce a gap report.”
  • “Draft a plain language policy for our customer communications team based on what the audit finds.”
  • “Plan a review workflow and training so our teams can meet a plain language standard.”

Requirements

  • Bun to run the audit scripts

Workflow steps

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

  1. Activation Rules
  2. Confirmation Before Sweeps
  3. Evidence Primacy

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 10 files in scripts/ (TypeScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bun

    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 24495-4 Plain Language Audit loads about 1.3k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 645 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

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). 645 words, ~1,321 tokens.

Download SKILL.mdSave it as .claude/skills/iso-24495-4/SKILL.md (or your agent's skills folder). This skill also uses 65 other files; get the full folder from GitHub.
name
iso-24495-4
description
Provisional task skill for organisational plain language implementation (based on ISO/CD 24495-4, committee draft). Activates for plain language gap analysis, policy drafting, review workflow design, and organisational readiness for the future published standard. Does not activate for ordinary writing, rewriting, or reviewing of individual documents.
metadata.version
0.7.0
metadata.iso-standard
ISO/CD 24495-4
metadata.iso-status
committee-draft

ISO/CD 24495-4 - Plain Language (Organisational Implementation) [PROVISIONAL DRAFT]

Provisional status: ISO 24495-4 is a Committee Draft (ISO/CD 24495-4) and is not yet published; its text is not public. This skill is original guidance based on the draft's public scope. It does not reproduce ISO text and its output is never a compliance statement. Expect revision when the standard is published.

Turns the agent from a copy editor into an implementation consultant. It assesses an organisation's capacity to produce plain language across governance, capability, process, measurement, and culture, rather than the quality of any single text.

Scope & Execution Boundaries

  1. Activation Rules:

    • Activate for: plain language gap analysis, maturity assessment, policy or style guide drafting, review workflow design, training planning, readiness for the future published standard.
    • Never activate for: writing, rewriting, summarising, or reviewing an individual document. Those tasks belong to iso-24495-1, -2, -3, and -5.

  2. Confirmation Before Sweeps:

    • Both audit scripts read many files. State which directory will be swept and get the user's confirmation before running either.

  3. Evidence Primacy:

    • Never assert a maturity level without evidence: a found artefact, a confirmed answer, or a measured count. Absent evidence scores as absent.

The Audit Workflow

Run the four steps in order. Each feeds the next.

  1. Sweep for process artefacts (primary):
    • Run bun scripts/audit-evidence-cli.ts <workspace-dir> --json evidence.json.
    • This detects the system: policy, review workflow, automated checks, training, glossary. It reads presence only; you evaluate the quality of what it finds.
  2. Audit the document corpus (secondary):
    • Run bun scripts/audit-corpus-cli.ts <corpus-dir> --json findings.json.
    • Output feeds the Measurement dimension only, as evidence of what the system produces. Text quality alone never raises a maturity level: excellent text can come from one unsupported expert, and flawed text can coexist with a strong process that is catching it.
  3. Interview the human (3 to 5 questions maximum):
    • Use references/interview-guide.md. Ask only what the file system cannot show (leadership, culture, training delivery). Record answers in the answers.json structure and cite evidence for each true.
    • Score with bun scripts/score-maturity-cli.ts answers.json --json maturity.json. Scoring is deterministic so levels cannot drift between sessions.
  4. Generate the gap report:
    • Run bun scripts/generate-report-cli.ts findings.json evidence.json maturity.json --state <dir>/state.json --out gap-report.md.
    • State is append-only; successive audits produce a trend table that proves or disproves progress. Store state.json in the organisation's repository, not in the skill directory (installed skills may be read-only).
Show full SKILL.md (253 more words)Show less

Quantitative Rules & Hard Constraints

  1. Proxies, Not Compliance: Corpus metrics (sentence length, paragraph length, legalese, heading depth) are mechanical proxies. Never present them, or this report, as ISO compliance or certification.
  2. Interview Cap: Ask the human at most 5 questions per audit. Infer everything else from artefacts.
  3. Ranked Actions: Every gap in the report gets a recommended action, ranked by reader impact against effort, tied to the criterion it unblocks.
  4. Language Boundary: The text heuristics are English-centric. For non-English corpora, skip step 2 and say so in the report.

Contrastive Examples

Example 1: Reporting a Gap
  • ❌ Not aligned (Vague, Unevidenced):

    "The organisation's culture around plain language seems weak and should be improved."

  • ✅ ISO/CD 24495-4 (Draft) Aligned:

    Culture: Level 1. Leadership is aware of the policy, confirmed in interview, but does not champion it. No leader has communicated it in the last year, and no feedback loop exists. Action (unblocks leadership-champions): the policy owner asks one executive sponsor to open the next all-hands with a plain language example.

Pre-Output Self-Audit Checklist

Before delivering a gap report, audit against these checks:

  • Correct activation: Was this an implementation task, not a writing task?
  • Sweep confirmed: Did the user approve each directory sweep?
  • Evidence cited: Does every maturity level and true answer cite an artefact, answer, or count?
  • Proxies labelled: Are corpus metrics presented as proxies feeding Measurement only?
  • State saved: Was state.json updated so the next audit can show a trend?
  • Provisional stated: Does the report declare the committee-draft basis and its limitations?

© 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 65 other files (scripts, references, assets) in skills/iso-24495-4 of GaZmagik/iso-24495.

  • SKILL.md
  • agents/openai.yaml
  • assets/gap-report-template.md
  • references/evidence-map.md
  • references/interview-guide.md
  • references/maturity-model.md
  • scripts/audit-corpus-cli.ts
  • scripts/audit-corpus.ts
  • scripts/audit-evidence-cli.ts
  • scripts/audit-evidence.ts
  • scripts/generate-report-cli.ts
  • scripts/generate-report.ts
  • scripts/lib/lexicon.ts
  • scripts/lib/parse.ts
  • scripts/lib/types.ts
  • scripts/score-maturity-cli.ts
  • … and 50 more

Open the folder on GitHubat commit 5951eb7

Compare with similar skills

ISO 24495-4 Plain Language 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 24495-4 Plain Language Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ISO 24495-4 Plain Language Audit this skillGaZmagik/iso-24495190—~1.3kAutomated 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
Nbj Write Clearlydaniel-p-green/nbj-write-clearly117—~1.1kAutomated safety check: PassMIT

Similar skills

  • Technical Writing Standard

    cursor/plugins

    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

  • Technical Writing

    openclaw/openclaw-enterprise

    Write, organize, name, edit, or review Enterprise developer documentation, specifications, and technical instructions; ground claims in current source and finish with a plain-language cleanup.

    390 GitHub stars~2.4k tokensUpdated today
    Writing & ContentAuto-check passed

More from GaZmagik/iso-24495

All 8 skills in this repo

  • 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

  • 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

  • Plain Language for Legal Text

    GaZmagik/iso-24495

    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

  • ISO 24495-3 Technical Plain Language

    GaZmagik/iso-24495

    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

Categories

Questions about ISO 24495-4 Plain Language Audit

What does ISO 24495-4 Plain Language Audit do?

Assesses how ready an organization is to produce plain language, through evidence sweeps, interviews and a maturity gap report. This provisional skill treats plain language as an organizational capability rather than a writing task. It is based on the public scope of the committee draft ISO/CD 24495-4, which is not yet published, so the guidance is original, reproduces no ISO text and its output is never a compliance statement.

When should I use ISO 24495-4 Plain Language Audit?

ISO 24495-4 Plain Language Audit fits situations like: running a plain language gap analysis for an organization; drafting a plain language policy or style guide; designing a review workflow or training plan for clear writing; preparing the organization for the future published standard.

How do I install ISO 24495-4 Plain Language Audit in Claude Code?

Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-4 -a claude-code`. Or copy the skill folder (skills/iso-24495-4 in GaZmagik/iso-24495) into .claude/skills/iso-24495-4 in your project. Claude Code loads it when a task matches its description.

How do I install ISO 24495-4 Plain Language Audit in Codex?

Run `npx skills add GaZmagik/iso-24495 --skill iso-24495-4 -a codex`. Or copy the skill folder (skills/iso-24495-4 in GaZmagik/iso-24495) into .agents/skills/iso-24495-4 in your project. Codex loads it when a task matches its description.

Can I use ISO 24495-4 Plain Language 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-24495-4 -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-24495-4, .gemini/skills/iso-24495-4, .github/skills/iso-24495-4 and .opencode/skills/iso-24495-4 in your project.

What does ISO 24495-4 Plain Language Audit need to run?

Going by SKILL.md and its folder, ISO 24495-4 Plain Language Audit needs TypeScript for the scripts in its folder and the command-line tools its instructions call (bun). Our summary lists: Bun to run the audit scripts.

Does ISO 24495-4 Plain Language 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 24495-4 Plain Language 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 24495-4 Plain Language Audit use?

ISO 24495-4 Plain Language 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 24495-4 Plain Language Audit use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to ISO 24495-4 Plain Language Audit?

Skills that share tags, products or a category with ISO 24495-4 Plain Language Audit: Technical Writing Standard (cursor/plugins, 11k stars), JavaScript Concept Page Writer (leonardomso/33-js-concepts, 67k stars), Chinese Technical Writing (leter/zh-tech-writing, 352 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 24495-4 Plain Language 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.