stop-slop

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

108 stars

Best use case

stop-slop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

Teams using stop-slop should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/stop-slop/SKILL.md --create-dirs "https://raw.githubusercontent.com/alfredolopez80/multi-agent-ralph-loop/main/.claude/skills/stop-slop/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/stop-slop/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How stop-slop Compares

Feature / Agentstop-slopStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Stop Slop

## v2.88 Key Changes (MODEL-AGNOSTIC)

- **Model-agnostic**: Uses model configured in `~/.claude/settings.json` or CLI/env vars
- **No flags required**: Works with the configured default model
- **Flexible**: Works with GLM-5, Claude, Minimax, or any configured model
- **Settings-driven**: Model selection via `ANTHROPIC_DEFAULT_*_MODEL` env vars

A skill for removing AI tells from prose. AI writing has patterns—predictable phrases, structures, and rhythms. Once you notice them, you see them everywhere.

## What It Catches

### Banned Phrases

**Throat-clearing openers** — Generic openings that delay the actual content:
- "Certainly!"
- "It is important to note that..."
- "It should be noted that..."
- "It is worth noting that..."
- "In today's fast-paced world..."
- "In the ever-evolving landscape of..."

**Emphasis crutches** — Overused emphasis patterns:
- "plays a crucial role"
- "is absolutely essential"
- "cannot be overstated"
- "is particularly important"

**Business jargon** — Empty corporate speak:
- "leverage the power of"
- "dive right in"
- "moving on to"
- "at the end of the day"

### Structural Clichés

**Binary contrasts** — Forced either/or framings:
- "This isn't just X, it's Y"
- "On one hand... on the other hand..."

**Dramatic fragmentation** — Unnecessary line breaks for emphasis:
- Short sentences after long ones just for effect

**Rhetorical setups** — Predictable question-answer patterns:
- "So what does this mean?"
- "The answer is..."

### Stylistic Habits

**Tripling** — Lists of three as a pattern:
- Examples, evidence, and expertise
- Fast, flexible, and affordable

**Metronomic endings** — Sentences that all end the same way

**Immediate question-answers** — Ask and answer in same paragraph

## Scoring

Rate 1-10 on each dimension:

| Dimension | Question |
|-----------|----------|
| **Directness** | Statements or announcements? |
| **Rhythm** | Varied or metronomic? |
| **Trust** | Respects reader intelligence? |
| **Authenticity** | Sounds human? |
| **Density** | Anything cuttable? |

**Below 35/50:** Revise the content.

## Process

When editing content:

1. **Scan for banned phrases** — Remove throat-clearing openers
2. **Fix structural clichés** — Break binary contrasts, reduce tripling
3. **Check rhythm** — Vary sentence length and structure
4. **Respect trust** — Don't over-explain, don't state obvious
5. **Verify authenticity** — Does it sound like a human wrote it?
6. **Trim density** — Cut anything that doesn't add value

## What to Remove

- Filler phrases and hedging
- Overused transitions (Furthermore, Moreover, Additionally)
- Artificial formality (due to the fact that, in order to)
- Redundant expressions (each and every, various different)
- Meta-commentary (As mentioned above, This demonstrates...)
- Generic openings (Certainly!, In today's fast-paced world...)

## What to Preserve

While removing slop, keep:
- Genuine technical explanations
- Actual insights and analysis
- Meaningful examples and evidence
- The author's authentic voice
- Facts and accurate information

## Anti-Goals

This skill does NOT:
- Dumb down the writing
- Remove all complexity
- Change your personal style
- Eliminate necessary explanations
- Make everything short

## Quick Reference

| AI Pattern | Fix |
|------------|-----|
| "It is important to note that" | Delete or state directly |
| "In conclusion" (as transition) | Just end or summarize |
| "Furthermore/Moreover" | Delete or use specific transition |
| "plays a crucial role" | "is important" or describe role |
| "manner in which" | "how" |
| "due to the fact that" | "because" |
| "each and every" | "each" or "every" |
| "a wide array of" | "many" |
| "As mentioned above" | Just continue |
| "This demonstrates that" | Just state what it demonstrates |

## Transformation Examples

### Example 1

**BEFORE (AI Slop):**
> "It is important to note that consistent practice plays a crucial role in skill development. Furthermore, one must consider that motivation is a key factor in maintaining this consistency. Moreover, this highlights the importance of setting realistic goals."

**AFTER (Human):**
> "Consistent practice develops skills. Motivation keeps you going, so set realistic goals."

### Example 2

**BEFORE (AI Slop):**
> "It should be noted that there are various different approaches to solving this problem. Each approach offers a unique set of advantages and disadvantages. In conclusion, the best choice depends on the specific context."

**AFTER (Human):**
> "Several approaches can solve this problem. Each has pros and cons. Pick what fits your situation."

### Example 3

**BEFORE (AI Slop):**
> "Certainly! Let's dive right in. In today's fast-paced digital landscape, businesses must leverage the power of technology to stay competitive. It's crucial to understand that digital transformation is not just a buzzword."

**AFTER (Human):**
> "Let's dive in. To stay competitive, businesses need technology. Digital transformation matters."

## Usage

**Claude Code:** This folder is a skill. Invoke `@stop-slop` when editing prose.

**Claude Projects:** Upload SKILL.md to project knowledge.

**API calls:** Include SKILL.md in your system prompt.

## Reference Files

For complete lists, see:
- `references/phrases.md` — Full banned phrases list
- `references/structures.md` — Structural patterns to avoid
- `references/examples.md` — More before/after transformations

---

Based on work by [Hardik Pandya](https://hvpandya.com/stop-slop)

Related Skills

deslop

108
from alfredolopez80/multi-agent-ralph-loop

Code quality analyzer that identifies "slop" - code violating established coding principles - and suggests concrete improvements. Analyzes code against principles like KISS, YAGNI, SOLID, DRY, and provides before/after fix examples.

clean-slop

108
from alfredolopez80/multi-agent-ralph-loop

Remove AI-generated code slop from a branch. Use when cleaning up AI-generated code, removing unnecessary comments, defensive checks, or type casts. Checks diff against main and fixes style inconsistencies.

worktree-pr

108
from alfredolopez80/multi-agent-ralph-loop

Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.

vercel-react-best-practices

108
from alfredolopez80/multi-agent-ralph-loop

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

vault

108
from alfredolopez80/multi-agent-ralph-loop

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

testing-anti-patterns

108
from alfredolopez80/multi-agent-ralph-loop

Custom skill for testing-anti-patterns

task-visualizer

108
from alfredolopez80/multi-agent-ralph-loop

Visualize task dependencies and progress (Gastown-style)

task-classifier

108
from alfredolopez80/multi-agent-ralph-loop

Classifies task complexity (1-10) for model and agent routing

task-batch

108
from alfredolopez80/multi-agent-ralph-loop

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature implementation. Triggers: /task-batch, 'batch tasks', 'process PRD', 'run task queue'.

tap-explorer

108
from alfredolopez80/multi-agent-ralph-loop

Tree of Attacks with Pruning for systematic code analysis

spec

108
from alfredolopez80/multi-agent-ralph-loop

Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, 'create spec', 'write specification', 'technical spec'.

smart-fork

108
from alfredolopez80/multi-agent-ralph-loop

Smart Forking - Find and fork from relevant historical sessions using parallel memory search across vault, memvid, handoffs, and ledgers