# Defluff

> Use this tool when you need to refine and improve the quality of LLM-generated text by identifying and removing unnecessary phrases, buzzwords, and clichés. Defluff takes in generated text as input and outputs structured lint results, helping to solve problems of clarity, concision, and readability. It is particularly useful in post-processing or quality enforcement pipelines where precise and effective language is required.

Canonical page: https://skillsregistry.net/skills/ahmedak-defluff  
JSON: https://api.skillsregistry.net/v1/skills/ahmedak-defluff

## Description

A deterministic prose linter for LLM-generated text that flags AI slop, filler phrases, buzzwords, hedging language, and clichés. Provides structured lint results for post-processing or quality enforcement pipelines.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-08-31

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ahmedak-defluff)
- **Repository:** <https://github.com/ahmedak/defluff>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ahmedak-defluff"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ahmedak-defluff` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ahmedak-defluff/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt