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

Comms Improver

by LegalQuants in LegalQuants/lq-ai

A skill your agent uses when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience.

Apache-2.0Auto-check passedWriting & Content

Install Comms Improver

skills CLI
$ npx skills add LegalQuants/lq-ai --skill comms-improver -a claude-code

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

GitHub CLI
$ gh skill install LegalQuants/lq-ai comms-improver --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/LegalQuants/lq-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/comms-improver .claude/skills/comms-improver && 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
comms-improver
GitHub stars
150
Token cost
~3.8k tokens
SKILL.md length
1,360 words
Files
7
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience.

  • Works in 3 steps: Read the original carefully → Rewrite for the audience → Produce the rewrite plus explanation
  • The user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience
  • SKILL.md covers When this skill applies, Inputs, Workflow and Output, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Comms Improver is an agent skill from LegalQuants/lq-ai. Use when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience. Common scenarios — email to a business stakeholder, legal disclaimer for a customer-facing page, memo for a non-legal audience, explanation of a contract clause for a deal team, summary of a regulatory development for an executive briefing. Produces the rewritten text plus a brief explanation of what was changed and why, including any preservation-of-meaning concerns where the…

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `examples/example_customer_disclaimer.md`, `examples/example_executive_briefing.md` and `examples/example_sales_team.md`).

It sits in Writing & Content, covering Plain language and style rules. The repository describes itself as: Open-source AI for legal teams. Bring your own keys, run it where you want, own your data. The licence is Apache-2.0.

When your agent uses it

  • The user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience
  • Tasks that involve Plain language and style rules

Example prompts

  • “/comms-improver”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Read the original carefully
  2. Rewrite for the audience
  3. Produce the rewrite plus explanation

What it can do on your machine

Read from SKILL.md and the folder at commit d185a62. 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 (its code samples are markdown).

    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

Comms Improver loads about 3.8k tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 1,360 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

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 LegalQuants/lq-ai at commit d185a62, republished under its Apache-2.0 licence (© LegalQuants). 1,360 words, ~3,767 tokens.

Download SKILL.mdSave it as .claude/skills/comms-improver/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
comms-improver
description
Use when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience. Common scenarios — email to a business stakeholder, legal disclaimer for a customer-facing page, memo for a non-legal audience, explanation of a contract clause for a deal team, summary of a regulatory development for an executive briefing. Produces the rewritten text plus a brief explanation of what was changed and why, including any preservation-of-meaning concerns where the rewrite required interpretation. Does not draft from scratch; the input is text that exists.
lq_ai.title
Comms Improver
lq_ai.version
1.0.0
lq_ai.author
LegalQuants
lq_ai.tags
communications, plain-language, transformation, drafting
lq_ai.jurisdiction
agnostic
lq_ai.trigger_examples
rewrite this in plain language, make this less lawyerly, translate this for the sales team, explain this clause to the deal team, simplify this disclaimer…
lq_ai.output_format
markdown
lq_ai.self_improvement
false

Comms Improver

Rewrite legal text in plain language for a specified non-legal audience. The output preserves meaning while changing form: shorter sentences, common words instead of jargon, active voice instead of passive, concrete examples instead of abstract formulations. The skill is transformation, not drafting from scratch.

This skill is for the everyday in-house counsel task of translating between legal precision and non-legal accessibility. Lawyers spend significant time rewriting their own work — or reviewing others' rewrites — for executive readouts, sales communications, customer disclosures, deal-team briefings, and engineering specs. The skill does this rewriting (or supports the user's rewriting) while flagging where translation involved interpretation.

When this skill applies

Apply when the user has legal-jargon-heavy text and wants it rewritten for a specified non-legal audience. Common inputs:

  • Email drafts to non-legal business stakeholders.
  • Contract clauses to be explained to a deal team or product team.
  • Legal disclaimers to be rewritten for customer-facing surfaces.
  • Memos to be summarized for executive readouts.
  • Regulatory developments to be communicated to affected business functions.
  • Compliance obligations to be translated for the operational owner.

Do not apply when:

  • The user wants to draft text from scratch. Out of scope — the skill rewrites existing text. Drafting from scratch is a different shape (drafting skill candidate; deferred enhancement).
  • The user wants to translate between languages (e.g., English to Spanish). Out of scope.
  • The user wants legal review of someone else's plain-language rewrite. Out of scope; that's review, not rewriting. The user can paste both versions and ask whether the rewrite preserves meaning, but the skill is calibrated for the rewriting task.
  • The text is already plain language and the user wants a different style. Out of scope; that's editing for style, not rewriting for accessibility.
  • The user wants to "make this sound more legal" or "add legal weight." Out of scope — the skill goes from legal to plain, not the other direction. Adding legal precision to plain text is a different task with different risks (introducing meaning the original didn't carry).

Inputs

The skill requires the text and the audience. If audience is not provided:

"Before I rewrite, who is this for? The audience determines tone, length, and detail level. Examples:

  • 'Executive readout for CEO/CFO — single paragraph'
  • 'Sales team — they need to understand what they can say to prospects'
  • 'Customer-facing disclaimer — non-technical consumers'
  • 'Deal team — commercial counsel plus product manager'
  • 'Engineering team — explaining a privacy obligation that affects design'"

Optional inputs (purpose, length_constraint, tone, preserve_specific_terms) refine the output. The most consequential is preserve_specific_terms — without it, the skill may simplify legal terms whose precise wording carries legal weight. The skill flags where simplification occurred so the user can verify.

Workflow

The workflow has three steps.

Step 1: Read the original carefully

Before rewriting:

  • Identify what the text is doing — informing, advising, requiring, warning, summarizing, etc.
  • Identify the legal terms of art, defined terms, and regulatory language that may have precise meaning. These are the candidates for preserve_specific_terms treatment.
  • Identify ambiguities, conditional structures, and qualifications that require interpretation to translate. ("subject to applicable law and regulatory guidance" might mean something specific in context, or might be CYA language that adds little.)
  • Identify the bottom-line point. Plain-language rewrites lead with the bottom line; legal-jargon-heavy text often buries it.

Use reference/legal_to_plain_patterns.md for common transformations.

Step 2: Rewrite for the audience

Apply transformations appropriate to the audience:

  • Sentence length: legal writing often has long compound sentences; plain language uses shorter sentences (typically 15-20 words average).
  • Voice: prefer active over passive ("we must notify the customer" vs. "the customer shall be notified").
  • Word choice: replace legal terms with everyday equivalents where the precise meaning is preserved (for terms where precise meaning matters, see "preserve specific terms" below).
  • Concrete over abstract: "if a customer asks for their data, we have 30 days to respond" vs. "data subject access requests must be fulfilled within applicable statutory timeframes."
  • Direct over indirect: "you can't share customer data with third parties" vs. "third-party data sharing is impermissible absent the requisite authorizations."
  • Lead with the bottom line: the audience's first read should answer their primary question.

Calibrate the level of transformation to the audience:

  • Executive briefing audiences want the bottom line in one sentence and the reasoning in two-three more. Detail goes in an appendix or follow-up if requested.
  • Operational owners (sales, engineering, support) want enough detail to act on the obligation. Include the specific actions and the boundary conditions ("yes you can do X; no you can't do Y; if you encounter Z, escalate to legal").
  • Customer-facing audiences want the substance without the legalese. Use second person ("you can request your data") and direct verbs ("we delete your data within 30 days of your request").
  • Deal-team audiences (commercial counsel, product) often need the legal substance preserved but in efficient prose. Less compression than executive briefing, more compression than the original legal text.

When preserve_specific_terms is provided, those terms appear verbatim in the rewrite. Without preserve_specific_terms, the skill applies judgment about which terms to preserve and flags choices in the explanation.

Show full SKILL.md (531 more words)Show less
Step 3: Produce the rewrite plus explanation

Produce the rewritten text first, followed by a brief explanation of what was changed and why. The explanation:

  • Identifies the structural changes (sentence length, ordering, lead with bottom line, etc.).
  • Notes any terms that were simplified and confirms whether the simplification preserved meaning.
  • Flags any preservation-of-meaning concerns — places where the original was ambiguous, where simplification required interpretation, or where the user should verify the rewrite captures their intent.
  • Suggests follow-up rewrites if the audience pushes back or asks questions.

The explanation should be substantially shorter than the rewrite. The rewrite is the deliverable; the explanation is the show-your-work.

Output

Produce the output in markdown with this structure:

markdown
# Comms Improver: [Brief description of the text]

**Audience:** [from input]
**Purpose:** [from input, or inferred]
**Length constraint:** [from input, or "matched to original"]
**Tone:** [from input, or "neutral businesslike"]

## Rewritten text

[The rewrite. Set off as a code block or quote block so the user can copy it directly. Multiple variants if the user wants alternatives — e.g., "one-sentence version" and "one-paragraph version" for executive briefing audiences.]

## What was changed

[Brief explanation of structural changes — sentence shortening, voice changes, ordering, etc. 2-4 bullets typical.]

## Terms simplified or preserved

[For terms that have legal weight: which were preserved verbatim, which were simplified and why. If `preserve_specific_terms` was provided, confirm those terms appear verbatim. If not provided, flag which terms might need preservation depending on the use case.]

## Preservation-of-meaning concerns

[Any places where the rewrite required interpretation, where the original was ambiguous, or where the user should verify the rewrite captures intent. If none, this section can be a single sentence: "No preservation-of-meaning concerns; the rewrite is a straightforward transformation of the original."]

## Suggested follow-ups

[Brief — typically 1-3 items. What to do if the audience pushes back, how to handle common follow-up questions, whether a longer or shorter version might be useful.]

The output should be proportional to the input. A one-paragraph original produces a brief output (rewrite plus a few-sentence explanation). A multi-page memo produces a longer output. Don't pad short rewrites; don't truncate substantial ones.

Edge cases and refusals

  • Original text is itself unclear or ambiguous. The skill rewrites what's there, flags the ambiguity, and notes that the rewrite cannot be clearer than the source. If the user wants disambiguation, that requires substantive understanding of the source's intent — the skill can ask, or recommend the user clarify the original first.
  • Audience is too vague to calibrate ("just make it simpler"). The skill produces a default audience calibration (neutral businesslike, single-paragraph, mid-detail) and notes the assumption.
  • Original text is very short (a sentence). The skill rewrites and notes that for short text the explanation may be longer than the rewrite — that's appropriate; the explanation surfaces what was preserved.
  • Original text contains specific legal language the user is going to send to a lawyer counterparty. Plain-language rewrite may be inappropriate; the original may have been drafted with that audience in mind. The skill notes this concern and asks the user to confirm the audience.
  • Original text contains text the user shouldn't be sending at all (legally inadvisable, factually inaccurate, or exposing the user's organization to risk). The skill rewrites for plain language but flags substantive concerns separately. The skill is not a substantive review; if substantive concerns are visible, they're flagged but the user is responsible for substantive review.
  • Audience is hostile or adversarial (counterparty in a dispute, regulator, opposing counsel). Plain-language rewrites for adversarial audiences require careful handling — simplification can lose hedging that's protective. The skill notes this consideration and recommends user verification.

What this skill does not do

  • Draft text from scratch. The skill rewrites existing text.
  • Substantive review. Plain-language rewrite is a transformation, not a substantive check on whether the underlying advice is correct.
  • Translation between languages. Out of scope.
  • Style editing for already-plain text. Out of scope.
  • Generate "more legal" versions of plain text. Out of scope; that's a different skill with different risks.
  • Multiple-audience optimization in a single rewrite. Each rewrite targets one audience. If the user has multiple audiences, run the skill multiple times.

Reference materials

  • reference/legal_to_plain_patterns.md — common transformations from legal jargon to plain language.
  • reference/audience_calibration.md — how to calibrate tone, length, and detail for different audience types.
  • examples/example_executive_briefing.md — worked example: contract concern translated for CEO/CFO.
  • examples/example_sales_team.md — worked example: regulatory restriction translated for sales team.
  • examples/example_customer_disclaimer.md — worked example: legal disclaimer rewritten for customer-facing page.

© LegalQuants, Apache-2.0. 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 6 other files in skills/comms-improver of LegalQuants/lq-ai.

  • SKILL.md
  • examples/example_customer_disclaimer.md
  • examples/example_executive_briefing.md
  • examples/example_sales_team.md
  • reference/audience_calibration.md
  • reference/legal_to_plain_patterns.md
  • test-plan.md

Open the folder on GitHubat commit d185a62

Compare with similar skills

Comms Improver 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.

Comms Improver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comms Improver this skillLegalQuants/lq-ai150—~3.8kAutomated safety check: PassApache-2.0
Asd Ste100danyuchn/asd-ste100-skill4.3k—~4.1kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
Ponytail AuditDietrichGebert/ponytail160k—~1.4kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
PgjevrealZachi/pg-jev1.1k—~2.9kAutomated safety check: PassCustom licence

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.3k GitHub stars~4.1k tokensUpdated 7 days ago
    Writing & ContentAuto-check passed

  • 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

  • Ponytail Audit

    DietrichGebert/ponytail

    Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.

    160k GitHub stars~1.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Natural Japanese Business Writing

    coji/natural-japanese

    Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Pgjev

    realZachi/pg-jev

    Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).

    1.1k GitHub stars~2.9k tokensUpdated 4 days ago
    Writing & ContentAuto-check passed

  • Defensive Writing Editor

    lennney/stop-that-shit

    Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

    2.5k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

More from LegalQuants/lq-ai

All 16 skills in this repo

  • Action Items From Client Alert

    LegalQuants/lq-ai

    A skill your agent uses when the user provides a client alert, regulatory bulletin, law firm memo, or similar legal update and wants the time-sensitive action items, deadlines, and obligations…

    150 GitHub stars~4k tokensUpdated today
    Auto-check passed

  • Case Law Research

    LegalQuants/lq-ai

    A skill your agent uses when the user asks to find, read, or cite U.S.

    150 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Contract QA

    LegalQuants/lq-ai

    A skill your agent uses when the user has a contract loaded and asks a specific question about it — what a clause means, where something is addressed, whether a term is unusual, how a provision…

    150 GitHub stars~4k tokensUpdated today
    Auto-check passed

  • Contract Snapshot

    LegalQuants/lq-ai

    A skill your agent uses when the user wants to compare the same handful of terms across N contracts side-by-side in a grid — what is the term, survival period, carveouts, and governing law in each…

    150 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Dpa Checklist Review

    LegalQuants/lq-ai

    A skill your agent uses when the user provides a Data Processing Agreement, Data Processing Addendum, or HIPAA Business Associate Agreement and asks whether it contains the terms required under the…

    150 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

  • Enhance Prompt

    LegalQuants/lq-ai

    A skill your agent uses when the user has typed a short or vague prompt and the system is configured to expand prompts before submission, or when the user explicitly invokes "Enhance Prompt" or asks…

    150 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Comms Improver

What does Comms Improver do?

A skill your agent uses when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience. Comms Improver is an agent skill from LegalQuants/lq-ai. Use when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience.

When should I use Comms Improver?

Comms Improver fits situations like: the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience; tasks that involve Plain language and style rules.

How do I install Comms Improver in Claude Code?

Run `npx skills add LegalQuants/lq-ai --skill comms-improver -a claude-code`. Or copy the skill folder (skills/comms-improver in LegalQuants/lq-ai) into .claude/skills/comms-improver in your project. Claude Code loads it when a task matches its description.

How do I install Comms Improver in Codex?

Run `npx skills add LegalQuants/lq-ai --skill comms-improver -a codex`. Or copy the skill folder (skills/comms-improver in LegalQuants/lq-ai) into .agents/skills/comms-improver in your project. Codex loads it when a task matches its description.

Can I use Comms Improver 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 LegalQuants/lq-ai --skill comms-improver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comms-improver, .gemini/skills/comms-improver, .github/skills/comms-improver and .opencode/skills/comms-improver in your project.

What does Comms Improver need to run?

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

Does Comms Improver 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 Comms Improver 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 Comms Improver use?

Comms Improver is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Comms Improver use?

About 3.8k tokens (SKILL.md is roughly 15k 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 Comms Improver?

Skills that share tags, products or a category with Comms Improver: Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars), Technical Writing Standard (cursor/plugins, 11k stars), Ponytail Audit (DietrichGebert/ponytail, 160k stars) and Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comms Improver?

LegalQuants (a GitHub organization) maintains it in LegalQuants/lq-ai, which has 150 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 11, 2026.

Source: LegalQuants/lq-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.