Agent skill

Plain Language Rewrite

by mohitagw15856 in mohitagw15856/pm-claude-skills

Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and…

MITAuto-check passedWriting & Content

Install Plain Language Rewrite

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill plain-language-rewrite -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills plain-language-rewrite --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plain-language-rewrite .claude/skills/plain-language-rewrite && 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
plain-language-rewrite
GitHub stars
1.4k
Token cost
~1.4k tokens
SKILL.md length
658 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and…

  • Works in 5 steps: Fidelity is the contract: before… → The jargon triage, not the jargon purge:… → Sentence surgery before word surgery:… → …
  • Asked make this readable
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Translation Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plain Language Rewrite is an agent skill from mohitagw15856/pm-claude-skills. Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and the reading-level honesty for the actual audience. Use when asked make this readable, translate this for non-experts, de-jargon this announcement, or rewrite this so my parents/customers/new hires understand it. Produces the rewrite with a fidelity check, the jargon ledger, and the kept-terms glossary line.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Plain language and style rules and Translation. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked make this readable
  • Translate this for non-experts
  • De-jargon this announcement
  • Rewrite this so my parents/customers/new hires understand it

Example prompts

  • “/plain-language-rewrite”

Workflow steps

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

  1. Fidelity is the contract: before rewriting, extract the original's claims list (facts, numbers, conditions, hedges); after, diff the…
  2. The jargon triage, not the jargon purge: each term gets a verdict — translate (internal shorthand, latinate padding: "utilize"→"use"…
  3. Sentence surgery before word surgery: the biggest readability gains are structural — one idea per sentence, front-loaded subjects, lists…
  4. Calibrate one notch below the audience's floor: write to slightly simpler than the audience needs — comprehension costs nothing extra for…
  5. The two-reader test: a target-audience reader retells the content correctly (comprehension) AND a subject-matter expert confirms nothing…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

Plain Language Rewrite loads about 1.4k tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 658 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 658 words, ~1,353 tokens.

Download SKILL.mdSave it as .claude/skills/plain-language-rewrite/SKILL.md (or your agent's skills folder).
name
plain-language-rewrite
description
Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and the reading-level honesty for the actual audience. Use when asked make this readable, translate this for non-experts, de-jargon this announcement, or rewrite this so my parents/customers/new hires understand it. Produces the rewrite with a fidelity check, the jargon ledger, and the kept-terms glossary line.

Plain Language Rewrite Skill

Plain language has a bad reputation because it's done badly — "simplifying" that quietly drops the qualifiers, rounds the numbers, and turns precise claims into vibes. Done right, it's a translation with a fidelity guarantee: every fact, number, condition, and hedge in the original survives; what changes is the packaging — sentence length, word choice, structure, and the jargon triage (most terms translate; some are load-bearing and get kept-and-defined instead, because renaming a term of art creates confusion downstream). The test is a reader who knows nothing and a checker who knows everything, both satisfied.

What This Skill Produces

  • The rewrite — the same content at the target reading level, structured for the new reader
  • The fidelity check — facts/numbers/qualifiers in original vs. rewrite, diffed to zero loss
  • The jargon ledger — each term: translated (to what) / kept-and-defined (why it's load-bearing)
  • The audience calibration — what the target reader knows, and the one-notch rule applied

Required Inputs

Ask for these if not provided:

  • The text — verbatim; translation works on actual sentences
  • The audience, concretely — "customers who don't know insurance" beats "general public"; the rewrite calibrates to what they already know, and one text can't serve experts and novices simultaneously (say so when asked to)
  • The load-bearing terms — which jargon is contractual, regulatory, or searchable-by-the-reader (those get kept-and-defined; renaming "deductible" to "your share" helps nobody who then reads their policy)
  • The stakes — legal/medical/financial texts keep their hedges verbatim-in-meaning; marketing texts have more freedom — the fidelity bar scales up with stakes

Framework: The Translation Rules

  1. Fidelity is the contract: before rewriting, extract the original's claims list (facts, numbers, conditions, hedges); after, diff the rewrite against it. "Usually," "up to," and "unless" are content, not decoration — a plain rewrite that drops them is a different document with better fonts.
  2. The jargon triage, not the jargon purge: each term gets a verdict — translate (internal shorthand, latinate padding: "utilize"→"use", "prior to"→"before") or keep-and-define (terms of art the reader will meet again: "your deductible — the amount you pay before insurance starts paying"). The ledger records both, because reviewers will ask.
  3. Sentence surgery before word surgery: the biggest readability gains are structural — one idea per sentence, front-loaded subjects, lists for parallel items, 20-ish words average. Swapping words inside 60-word sentences polishes the unreadable.
  4. Calibrate one notch below the audience's floor: write to slightly simpler than the audience needs — comprehension costs nothing extra for strong readers, and the weakest reader in the audience is the one the text exists to reach. But never condescend in tone: plain is respectful; simplified-with-a-pat-on-the-head is not.
  5. The two-reader test: a target-audience reader retells the content correctly (comprehension) AND a subject-matter expert confirms nothing became false (fidelity). Passing one test is easy; the skill is passing both, and the output states both results.
Show full SKILL.md (195 more words)Show less

Output Format

Plain Rewrite: [text] — for [audience]

The Rewrite

[The translated text, structured for the reader]

Fidelity Check

Original claim/number/qualifierWhere it survives in the rewrite
[Zero-loss demonstrated, or the flagged intentional cuts with reasons]

Jargon Ledger

TermVerdictRendered as

The Two-Reader Result

[Comprehension: retellable? · Fidelity: expert-clean? · the stakes note for legal/medical texts: hedges preserved verbatim-in-meaning]

Quality Checks

  • The claims list was extracted before rewriting and diffed after
  • Every qualifier survives — no "usually" became "always"
  • Load-bearing terms were kept-and-defined, not renamed
  • Sentence structure did the heavy lifting before word swaps
  • Both readers pass: the novice retells it; the expert signs it

Anti-Patterns

  • Do not simplify by deletion — dropped hedges are the classic plain-language malpractice
  • Do not rename terms of art — the reader meets "deductible" again five minutes later
  • Do not write down at the audience — plain and respectful are the same register
  • Do not serve two audiences with one text — name the split when asked to
  • Do not skip the expert pass on high-stakes text — readable-but-wrong is the worst outcome on the board

Example Trigger Phrases

  • "Make this readable."
  • "Translate this for non-experts."
  • "De-jargon this announcement."
  • "Rewrite this so my parents/customers/new hires understand it."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/plain-language-rewrite of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Plain Language Rewrite 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.

Plain Language Rewrite compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plain Language Rewrite this skillmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
Plain English Translationzubair-trabzada/ai-legal-claude1.8k—~1.9kAutomated safety check: PassNone
Noob Modegithub/awesome-copilot40k1 repos~2.8kAutomated safety check: PassMIT
Science Communicationbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~3.1kAutomated safety check: PassCustom licence
Jev Question Translatorlawve-ai/awesome-legal-skills847—~6.9kAutomated safety check: PassApache-2.0
Client Explanation Translator Larissa Meredith Flisterlawve-ai/awesome-legal-skills847—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Plain English Translation

    zubair-trabzada/ai-legal-claude

    Translates every clause of a contract from legalese into clear, plain English with flags for deliberately confusing or misleading language

    1.8k GitHub stars~1.9k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed
  • Noob Mode

    github/awesome-copilot

    Official

    Plain-English translation layer for non-technical Copilot CLI users.

    40k GitHub starsUsed in 1 repo~2.8k tokens
    Writing & ContentAuto-check passed
  • Science Communication

    brycewang-stanford/Auto-Empirical-Research-Skills

    Translating technical findings for non-technical audiences. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~3.1k tokensUpdated 5 days ago
    Writing & ContentAuto-check passed
  • Jev Question Translator

    lawve-ai/awesome-legal-skills

    Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that…

    847 GitHub stars~6.9k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed
  • SQL To Business Logic

    nimrodfisher/data-analytics-skills

    Translate SQL queries into plain language business logic. An agent skill from nimrodfisher/data-analytics-skills.

    470 GitHub stars~636 tokensUpdated 15 days ago
    DatabasesAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Plain Language Rewrite

What does Plain Language Rewrite do?

Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and…. Plain Language Rewrite is an agent skill from mohitagw15856/pm-claude-skills. Rewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and qualifier, the jargon triage (terms to replace, terms to keep-and-define), and the reading-level honesty for the actual audience.

When should I use Plain Language Rewrite?

Plain Language Rewrite fits situations like: asked make this readable; translate this for non-experts; de-jargon this announcement; rewrite this so my parents/customers/new hires understand it.

How do I install Plain Language Rewrite in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill plain-language-rewrite -a claude-code`. Or copy the skill folder (skills/plain-language-rewrite in mohitagw15856/pm-claude-skills) into .claude/skills/plain-language-rewrite in your project. Claude Code loads it when a task matches its description.

How do I install Plain Language Rewrite in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill plain-language-rewrite -a codex`. Or copy the skill folder (skills/plain-language-rewrite in mohitagw15856/pm-claude-skills) into .agents/skills/plain-language-rewrite in your project. Codex loads it when a task matches its description.

Can I use Plain Language Rewrite 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 mohitagw15856/pm-claude-skills --skill plain-language-rewrite -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plain-language-rewrite, .gemini/skills/plain-language-rewrite, .github/skills/plain-language-rewrite and .opencode/skills/plain-language-rewrite in your project.

What does Plain Language Rewrite need to run?

SKILL.md names no scripts, command-line tools or credentials: Plain Language Rewrite is instructions for the agent only.

Does Plain Language Rewrite 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 Plain Language Rewrite 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 Plain Language Rewrite use?

Plain Language Rewrite 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 Plain Language Rewrite use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Plain Language Rewrite?

Skills that share tags, products or a category with Plain Language Rewrite: Plain English Translation (zubair-trabzada/ai-legal-claude, 1.8k stars), Noob Mode (github/awesome-copilot, 40k stars), Science Communication (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars) and Jev Question Translator (lawve-ai/awesome-legal-skills, 847 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plain Language Rewrite?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.