What makes deaiify notable?

1K downloads. Trust evidence available

How should deaiify be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

deaiify

Ban LLM em-dashes and en-dashes before delivery, rewrite via embedded LLM. Skill: deaiify Owner: shawnpetros Summary: Ban LLM em-dashes and en-dashes before delivery, rewrite via embedded LLM. Tags: latest:3.4.1 Version history: v3.4.1 | 2026-04-16T05:03:23.997Z | user Fix VT scanner flag: replace mkdtemp+rm-rf dropper pattern with flat tmp file + unlink v3.4.0 | 2026-04-16T04:54:58.124Z | user v3 rewrite: proper em-dash detection with code-block exclusion, embedded LLM rewrite v3.0.3 | 202

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

3.4.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 3.4.1release · observed Apr 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176znzjztf6tqcd77j882me75848hxc:deaiify

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-shawnpetros-deaiify/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

145,478 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: deaiify
description: "Ban LLM em-dashes and en-dashes before delivery, rewrite via embedded LLM."
homepage: https://github.com/shawnpetros/deaiify
metadata:
  {
    "openclaw":
      {
        "emoji": "🚫",
        "plugin": true
      }
  }
---

# deAIify Plugin

Enforces the "no em dashes" rule across all output by intercepting messages, detecting U+2013 (en dash) and U+2014 (em dash), and forcing a rewrite turn via embedded LLM correction.

## What it does

- Detects U+2013 and U+2014 in outbound messages
- Calls embedded LLM to rewrite without dashes (preserves meaning, tone, style)
- Returns corrected output to user
- Never touches U+002D (hyphen-minus in code)
- Excludes content inside code blocks and inline code

## How it works

1. `before_agent_reply` intercepts the completed assistant text before delivery
2. Detects banned dash characters outside of code blocks
3. Calls `runEmbeddedPiAgent` with a restructuring prompt
4. Verifies the rewrite is sane (word count and length checks)
5. Returns the rewritten reply

## Installation

```bash
openclaw plugin install deaiify
```

## Configuration

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `rewriteTimeoutMs` | integer | `15000` | Timeout in ms for the embedded rewrite call |

The plugin uses the session's default model for rewrites. No model config needed.

README.md

# deAIify

An OpenClaw plugin that removes em-dashes and en-dashes from assistant prose before delivery.

Instead of doing a naive character replacement, deAIify asks an embedded model run to rewrite the affected sentence so the output still reads naturally. If the rewrite fails, the plugin fails open and delivers the original response unchanged.

## What it does

- detects Unicode em-dashes (`\u2014`) and en-dashes (`\u2013`) in assistant replies
- ignores fenced code blocks, inline code, and normal hyphen-minus usage (`-`)
- rewrites only when needed, using `before_agent_reply`
- verifies the rewrite before delivery
- falls back safely if the embedded rewrite does not succeed

## Hooks

- `before_agent_reply`: primary rewrite path
- `message_sending`: last-resort cleanup fallback

## Safety properties

- fail-open on every error path
- no config-driven code execution
- no external network calls beyond the configured model provider
- temporary rewrite session files are removed immediately after use

## Install

```bash
openclaw plugin install deaiify
```

## Optional config

```json
{
  "plugins": {
    "entries": {
      "deaiify": {
        "enabled": true,
        "config": {
          "rewriteTimeoutMs": 15000
        }
      }
    }
  }
}
```

## Development

```bash
npm install
npm run build
npm test
npm run stage-package
```

`npm run stage-package` creates a minimal publishable artifact under `.release/package/` that contains only the runtime files and manifests needed by ClawHub.

## License

MIT

_meta.json

{
  "ownerId": "kn72tv7k399238hfkfptn8apnd848ff7",
  "slug": "deaiify",
  "version": "3.4.1",
  "publishedAt": 1776315803997
}

skill-card.md

## Description:

Ban LLM em-dashes and en-dashes before delivery, rewrite via embedded LLM.

This skill is ready for commercial/non-commercial use.

## Publisher:

[shawnpetros](https://clawhub.ai/user/shawnpetros)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use deaiify to rewrite assistant replies before delivery when Unicode en dash or em dash characters appear outside code. It is intended for OpenClaw sessions where preserving the meaning and tone of the assistant response is more important than simple character replacement.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Assistant output containing sensitive text may be resent through an embedded model run for rewriting.

Mitigation: Install only in sessions where this automatic rewrite behavior is acceptable, and avoid contexts where assistant output should not be submitted to the active model provider again.

Risk: A rewrite can alter meaning, omit detail, or fail to remove all target dash characters.

Mitigation: The skill verifies word-count drift, length expansion, and remaining banned dash characters, then fails open by delivering the original response when verification fails.

Risk: The dev dependency lockfile needs a publisher refresh according to the security guidance.

Mitigation: Prefer an updated release once the publisher refreshes the dev dependency lockfile.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/shawnpetros/skills/deaiify)
- [Publisher profile](https://clawhub.ai/user/shawnpetros)
- [Project homepage](https://github.com/shawnpetros/deaiify)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Guidance]

**Output Format:** [Rewritten assistant reply text, preserving Markdown and code blocks where applicable]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses the active session model for rewrites, applies a configurable timeout, and fails open by delivering the original reply if rewriting or verification fails.]

## Skill Version(s):

3.4.1 (source: evidence.release.version and package.json)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

openclaw.json

{
  "manifest": {
    "name": "deAIify",
    "description": "Ban LLM em-dashes and en-dashes before delivery, rewrite via embedded LLM",
    "version": "3.4.0",
    "main": "./dist/index.js",
    "type": "module"
  }
}

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular