Skip to main content
skill CX Codex

unslop-help — Claude Code skill: a reference card for unslop

Prints one card listing every unslop mode, sub-skill and exit phrase. Handy when you forget the syntax but do not want to switch anything on.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add MohamedAbdallah-14/unslop --skill unslop-help -a claude-code
Open on GitHub

What unslop-help does

The skill renders a single reference card: a table of modes (subtle, balanced, full, voice-match, anti-detector), the sub-skills (unslop-commit, unslop-review, unslop-file, unslop-reasoning) and the phrases that turn unslop off. It runs once. No mode gets toggled, no flag file is written, nothing persists.

The card itself is plain prose rather than unslop style, since it counts as documentation. The modes it describes stay active until you change them or the session ends. balanced is the default; UNSLOP_DEFAULT_MODE or ~/.config/unslop/config.json can override it, and the environment variable wins over the file. Setting the value to "off" disables auto-activation altogether.

Install targets include Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. On Claude the file lands at ~/.claude/skills/unslop-help/SKILL.md.

What it helps with

  • recall which unslop modes exist and how they differ
  • find the exact trigger for the commit or review sub-skill
  • look up the phrases that deactivate unslop
  • check how to set a default mode in the config
  • understand what anti-detector does before calling it

Example prompts for the agent

  • Show me the unslop help card
  • What unslop commands are there, and how do I turn it off?
  • Remind me how subtle differs from full

How to install unslop-help

1Skills CLI (Vercel)

npx skills add MohamedAbdallah-14/unslop --skill unslop-help -a claude-code

2Manually: put the files in place

~/.claude/skills/unslop-help/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/unslop-help/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about unslop-help

How do I install unslop-help in Claude Code?

Run npx skills add MohamedAbdallah-14/unslop --skill unslop-help -a claude-code. The skill file ends up at ~/.claude/skills/unslop-help/SKILL.md.

What does unslop-help do?

It shows one reference card covering unslop modes, sub-skills, deactivation phrases and config settings. No mode is switched.

How is unslop-help different from the other unslop sub-skills?

The others rewrite something — commits, reviews, markdown files, reasoning traces. This one only displays documentation and changes nothing.

Source text

SKILL.md · MIT
---
name: unslop-help
description: >
  Quick-reference card for unslop modes, sub-skills, and slash commands.
  One-shot display, not a persistent mode. Trigger: /unslop-help,
  "unslop help", "what unslop commands", "how do I use unslop".
---

# Unslop Help

## Purpose

Show a single reference card for unslop modes, related sub-skills, exit phrases, and config. One-shot. Does not toggle modes. Does not write flag files.

## Output

Render the card below in normal prose (not unslop style — this is documentation).

### Modes

| Mode | Trigger | What it does |
|------|---------|--------------|
| `subtle` | `/unslop subtle` | Light touch. Trim AI tells, keep length and structure. |
| `balanced` | `/unslop` (default) | Cut slop, vary rhythm, restore voice. |
| `full` | `/unslop full` | Strong rewrite. Restructure. Allow opinions. |
| `voice-match` | `/unslop voice-match` | Follow a provided voice/style sample. |
| `anti-detector` | `/unslop anti-detector` | Adversarial paraphrase for detector resistance. Use only when explicitly requested. |

Modes persist until changed or the session ends.

### Sub-skills

| Skill | Trigger | What it does |
|-------|---------|--------------|
| `unslop-commit` | `/unslop-commit`, `/commit`, "write a commit" | Conventional Commits in human voice. |
| `unslop-review` | `/unslop-review`, `/review`, "review this PR" | Direct, kind PR review comments. |
| `unslop-file` | `/unslop-file <filepath>`, "unslop this file", "humanize memory file" | Rewrite a markdown file removing AI-isms while preserving code/URLs/structure. |
| `unslop-reasoning` | `/unslop-reasoning`, "fix this chain of thought", "clean up my reasoning" | Strip AI-slop reasoning patterns (over-hedging, over-decomposing, infinite-loop rationalization) from chain-of-thought traces. |
| `unslop-help` | `/unslop-help`, "unslop help" | This card. |

### Deactivate

- `"stop unslop"` or `"normal mode"` — revert immediately
- Resume with `/unslop` (or any mode flag)

### Configuration

- Default mode: `balanced`
- Override: `UNSLOP_DEFAULT_MODE=full` (env), or `~/.config/unslop/config.json`:
  ```json
  { "defaultMode": "full" }
  ```
- `"off"` disables auto-activation entirely
- Resolution order: env var > config file > `balanced`

### More

Full docs and source: <https://github.com/MohamedAbdallah-14/unslop>

## Boundaries

- One-shot. Do not toggle a mode, write a flag file, or persist any state.
- Do not output in unslop style — this card is reference material.

© MohamedAbdallah-14 · MIT · MohamedAbdallah-14/unslop

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set2

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor