comms-improver
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.
Skill by LegalQuants
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/legalquants-comms-improver
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, sales, productivity, legal
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/comms-improver
What's inside
- Skill 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.
- License
- Apache-2.0
- Instructions
- 146 lines in SKILL.md · view on GitHub
Files (13)
- SKILL.md
- disclaimer-for-customers.md · acceptance/fixtures/
- indemnity-for-sales.md · acceptance/fixtures/
- memo-for-exec.md · acceptance/fixtures/
- disclaimer-for-customers.golden.json · acceptance/snapshots/
- indemnity-for-sales.golden.json · acceptance/snapshots/
- memo-for-exec.golden.json · acceptance/snapshots/
- example_customer_disclaimer.md · examples/
- example_executive_briefing.md · examples/
- example_sales_team.md · examples/
- audience_calibration.md · reference/
- legal_to_plain_patterns.md · reference/
- test-plan.md
SKILL.md (first lines)
# 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.
### 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.From LegalQuants/lq-ai, Apache-2.0.
More from LegalQuants/lq-ai
- 0.784score
nda-review
LegalQuants
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign.
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
action-items-from-client-alert
LegalQuants
Use when the user provides a client alert, regulatory bulletin, law firm memo, or similar legal update and wants the time-sensitive action items, deadlines…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
playbook-easy-extract
LegalQuants
Use when extracting the negotiated positions from a single prior contract as input to the Easy Playbook auto-generation pipeline.
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
vendor-privacy-policy-first-pass
LegalQuants
Use when the user has a vendor's published privacy policy (URL, PDF, or pasted text) and wants a fast triage assessment to decide whether deeper diligence is…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
dpa-checklist-review
LegalQuants
Use when the user provides a Data Processing Agreement, Data Processing Addendum, or HIPAA Business Associate Agreement and asks whether it contains the terms…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
msa-review-saas
LegalQuants
Use when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
contract-qa
LegalQuants
Use 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…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
msa-review-commercial-purchase
LegalQuants
Use when the user uploads or pastes a Master Purchase Agreement, Master Supply Agreement, Master Goods Agreement, or commercial purchase MSA covering the…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
enhance-prompt
LegalQuants
Use 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…
SkillAFreshness: A★ 156Claude Code +9 - 0.777score
orchestrator-harness
LegalQuants
Demonstrates an approved plan, bounded parallel delegation, progress collection and synthesis using sample findings.
SkillAFreshness: A★ 156Claude Code +9 - 0.777score
saved-notes-demo
LegalQuants
Demonstrate optional saved notes and a bundled helper across skill invocations.
SkillAFreshness: A★ 156Claude Code +9 - 0.777score
orchestration-topic-demo
LegalQuants
Produces a bounded sample topic outcome for the orchestration demonstration.
SkillAFreshness: A★ 156Claude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 156
- Forks
- 67
- Open issues
- 94
- Last commit (this folder)
- Oct 12, 2026 (15 days ago)
- Last release
- Oct 8, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/LegalQuants/lq-ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LegalQuants
- 0.784score
dpa-checklist-review
LegalQuants
Use when the user provides a Data Processing Agreement, Data Processing Addendum, or HIPAA Business Associate Agreement and asks whether it contains the terms…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
enhance-prompt
LegalQuants
Use 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…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
action-items-from-client-alert
LegalQuants
Use when the user provides a client alert, regulatory bulletin, law firm memo, or similar legal update and wants the time-sensitive action items, deadlines…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
contract-qa
LegalQuants
Use 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…
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
nda-review
LegalQuants
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign.
SkillAFreshness: A★ 156Claude Code +9 - 0.784score
msa-review-commercial-purchase
LegalQuants
Use when the user uploads or pastes a Master Purchase Agreement, Master Supply Agreement, Master Goods Agreement, or commercial purchase MSA covering the…
SkillAFreshness: A★ 156Claude Code +9
Cite this page
comms-improver skill. Agent Mart. https://agentmart.dev/skills/legalquants-comms-improver (last updated 2026-10-24)