Removes generic AI mannerisms, inflated phrasing, and repetition from prose while preserving the author's voice. Use when the user asks to deslopify or naturalize a draft.
Scanned 9/10/2026
Install to Claude Code
npx -y skills add iurysza/agent-skills --skill deslopify --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deslopify?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/iurysza-deslopify)More formats (shields.io, HTML) on the badges page.
---
name: deslopify
description: Removes generic AI mannerisms, inflated phrasing, and repetition from prose while preserving the author's voice. Use when the user asks to deslopify or naturalize a draft.
metadata:
category: writing-style
---
# Deslopify
Remove mechanical writing habits without sanding away the author's personality.
## Workflow
1. Identify the audience, purpose, and established voice from the draft or nearby examples.
2. Read [references/editing-checklist.md](references/editing-checklist.md).
3. Mark repeated habits rather than banning isolated words or constructions.
4. Rewrite the smallest span that fixes each problem.
5. Preserve facts, intent, level of certainty, terminology, and deliberate humor.
6. Read the revision for rhythm and remove any new repetition introduced during editing.
7. Return the revised text. Explain changes only when the user asks or when meaning had to change.
## Editing priorities
Apply these in order:
1. correctness and preserved meaning
2. specificity and clear ownership of claims
3. natural sentence and paragraph rhythm
4. concise wording
5. formatting restraint
Do not make every sentence short. Do not replace one recognizable formula with another. A slightly uneven sentence that fits the author's voice is better than polished generic copy.
When the source voice is unavailable, default to direct, concrete prose rather than pretending to imitate a person.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling