Skip to content
Agentmart
Submit a tool

unslop

Edit prose for clarity, precision, economy, and consistency.

Skill by AndreaCatalucci

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying unslop?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/andreacatalucci-unslop

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.

We use your email only for this newsletter. Privacy

About

Edit prose for clarity, precision, economy, and consistency. Run on every string a human will read this turn before you show it, and when the user says unslop.

Use cases: writing

No 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/unslop

What's inside

Skill name
unslop
Description
Edit prose for clarity, precision, economy, and consistency. Run on every string a human will read this turn before you show it, and when the user says unslop.
License
MIT
Instructions
59 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Unslop

Edit specific defects while preserving meaning and tone. An already clear sentence needs no change.

## Process

1. Inventory all user-visible text created or changed this turn: chat, document prose, UI labels, help, empty states, and assertions about copy.
2. Find the defects below. When several checks flag one sentence, identify the underlying problem and rewrite it once.
3. Use only facts, actors, mechanisms, and numbers supported by the surrounding context. If detail is unavailable, qualify or remove the claim.
4. Make one final pass for meaning, tone, accuracy, and readability. Revert preference-only edits and stop.

## Cut empty or inflated wording

Remove phrases that add no meaning, precision, or useful rhythm: "in order to," "it is important to note," "has the ability to," and "at its core." Prefer familiar verbs to inflated ones such as "utilize," "facilitate," and "leverage" when the plain term is equally accurate.

Cut appended benefit claims and endings that merely restate what the sentence or response already establishes. Keep consequences that explain an actual effect.

Bad: "The service retries failed requests, improving reliability."
Better: "The service retries failed requests up to three times, which prevents brief network failures from reaching the caller."

## Replace vague claims with evidence

Flag quality claims and weak modifiers such as seamless, robust, powerful, significant, substantially, efficiently, and obviously when the reader cannot tell what supports them. Replace them with an available fact, mechanism, or number. A scoped subjective judgment can remain when no measurement is available.

Name the source behind attributed claims. If "experts believe" or "studies show" cannot be tied to a source, remove the attribution and unsupported claim.

A verdict needs the fact that distinguishes it from plausible alternatives. This applies to "expected," "working as designed," and corrective labels.

Bad: "That is the leak guard working, not a failed inject."
Better: "The injection worked, but the child leaked the value into its output, so the leak guard stopped the process."

## Make responsibility and behavior concrete

Prefer actions to abstract nouns that hide who does what. Replace jargon when a familiar word is equally precise; keep established technical terms when they carry necessary meaning.

Use active voice when it clarifies responsibility. Passive voice is useful when the actor is unknown, irrelevant, or less important than the receiver.

Bad: "This enables improved coordination between workers."
Better: "Workers use the lease to decide which one owns the task."

For technical claims, name the behavior that creates the property. "Validation failures are surfaced clearly" becomes "The process exits with status 1 and prints the failing field."

Keep terminology stable when referring to the same thing. Changing "worker" to "processor" to "execution unit" obscures the reference unless the distinction is real.

## Keep emphasis and structure useful

Use contrast to correct a real misunderstanding or compare actual alternatives. Remove invented opposition such as "This isn't just X. It's Y." when it adds only emphasis.

Use "from X to Y" only for a meaningful scale. A list of unrelated capabilities is not a range.

Let punctuation express syntax. Repeated em dashes, interrupting asides, or punctuation used as emphasis may need a clearer sentence; punctuation itself is not a defect.

Match structure to the information. Use lists for parallel items or steps and headings when they help navigation. Remove repetitive labels, unnecessary introductions, nested lists without useful hierarchy, and conclusions that repeat the answer.

## Final check

For each edit, identify the concrete defect it fixed. Confirm it preserves meaning and tone, adds no unsupported fact, and is easier to understand. If the remaining difference is taste, keep the writer's version.

From AndreaCatalucci/andrea-engineering, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 5, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from AndreaCatalucci

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get unslop running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying unslop?

CallGet help
Cite this page

unslop skill. Agent Mart. https://agentmart.dev/skills/andreacatalucci-unslop (last updated 2026-10-24)