Stop Slop
SkillDocs & knowledgeApplies the stop slop skill to cut generic AI-writing patterns like filler and padding from your drafts.
Use Stop Slop in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Stop Slop and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Stop Slop skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models
What this skill tells your AI
The instructions your AI receives, as published by aaronnat23/disp8ch in optional-skills/stop-slop/SKILL.md and read by Ahel’s review.
Remove generic AI writing patterns from prose while preserving the user's actual meaning and voice.
Use When
- Drafting, editing, or reviewing prose, docs, blog posts, release notes, marketing copy, or executive summaries.
- The user asks for writing to sound less generic, less AI-written, more direct, or more human.
- A final answer has filler, throat-clearing, formulaic contrast, vague praise, or over-polished phrasing.
Playbook
- Cut filler phrases, throat-clearing, vague setup, and padded transitions.
- Prefer active voice with a real actor doing the action.
- Replace abstract claims with named components, concrete behavior, numbers, or examples.
- Vary sentence length and paragraph endings.
- Remove pull-quote style one-liners unless the user explicitly wants a punchy style.
- Preserve technical precision. Do not simplify away caveats, file names, commands, or evidence.
- Use direct wording instead of explaining that you are about to explain something.
Checks
- Is any sentence announcing the answer instead of giving it?
- Is any claim vague enough that it could fit any product or team?
- Are there repeated three-item lists, binary contrasts, or dramatic fragments?
- Can a reader tell which person, system, file, or process did the action?
- Can a paragraph be shorter without losing meaning?
Guardrails
- Do not remove legally or technically necessary caveats.
- Do not force casual voice into formal documents.
- Do not rewrite user-provided quotes unless asked.
- Do not use this as a default for every answer; enable it for writing-heavy agents or content review work.
Signals
- GitHub stars
- 100
- Forks
- 2
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
stop-slop- Source
- github.com/aaronnat23/disp8ch
More in Docs & knowledge
Skill · mattpocock
More in Docs & knowledgecanvas-design
Skill · anthropics
More in Docs & knowledgedoc-coauthoring
Skill · anthropics
More in Docs & knowledgepopups
Skill · coreyhaines31
More in Docs & knowledgewriting-for-agents
Skill · mattpocock
More in Docs & knowledgespec-driven-development
Skill · addyosmani
More in Docs & knowledge