What makes Defluff notable?

957 downloads. Trust evidence available

How should Defluff 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

Defluff

Reverse the AI in corporate email. Detect whether a message was written by AI, AI-assisted, or by a human. When AI was involved, guess the prompt the sender... Skill: Defluff Owner: yozaz Summary: Reverse the AI in corporate email. Detect whether a message was written by AI, AI-assisted, or by a human. When AI was involved, guess the prompt the sender... Tags: latest:0.0.9 Version history: v0.0.9 | 2026-04-22T19:42:24.388Z | auto Version 0.0.9 - Updated scam pattern definitions for NOISE verdicts, adding more explicit criteria for "likely fake recruiter" and "crypto / Web3

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

957

Updated

Oct 12, 2026

Version

0.0.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 957 downloads reported by the source. Last updated 10/12/2026.

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 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 957 downloadsadoption · observed Oct 12, 2026
Latest release: 0.0.9release · observed Apr 22, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.0.9release
Version 0.0.9 - Updated scam pattern definitions for NOISE verdicts, adding more explicit criteria for "likely fake recruiter" and "crypto / Web3 pitch". - Clarified that a polite reader reply does not change a scam verdict in threads; per-message verdicts now apply single-message rules regardless of conversation flow. - Minor clarifications throughout to improve instruction precision for handling threads and scam scenarios. - Incremented version number to 0.0.9.
Observed Apr 22, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17amaczxfbbms7pzf51n5waa5854m3m:defluff

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-yozaz-defluff/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

79,050 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: defluff
displayName: Defluff
description: Reverse the AI in corporate email. Detect whether a message was written by AI, AI-assisted, or by a human. When AI was involved, guess the prompt the sender probably gave an LLM. Classify urgency, extract the actual intent, name scam patterns (invoice fraud / BEC, phishing, fake recruiters, conference scams, crypto / MLM pitches). Output mirrors the email's language. Handles single messages, threads, and batches.
version: 0.0.9
user-invocable: true
---

# defluff

Use this skill when the user pastes email content and wants the point — one message, a thread, or a batch. Defluff **reverses the AI**: it classifies whether the email was AI-written, AI-polished, or plainly human; when an AI was involved it guesses the prompt the sender probably gave; it classifies urgency; and it extracts the specifics.

## When to trigger

- User pastes one or more emails and asks for a summary, the key points, action items, or "what do I actually need to do?"
- User forwards a long thread and wants only what matters.
- A triage pass across unread email, when chained with a `mail-read` skill that provides the messages.

## Core rule

You are an **AI-reversal tool**. For every email, in order:

1. Decide who wrote it — `AI`, `AI-assisted`, or `human`.
2. If an AI was involved, guess the prompt the sender probably gave it. Skip this step for human-authored emails — there is no prompt to reverse.
3. Classify the email's urgency.
4. Extract the real intent as a short bullet list.

Never add conversational padding of your own. Never write "Here's what I found", "In summary", "I hope this helps".

## Output format — single email

Up to three header lines (Authored is always emitted; Prompt is only emitted when Authored is AI or AI-assisted), then bullets:

```
Authored: [AI | AI-assisted | human] — [one-sentence reasoning naming 1-2 concrete signals, max 15 words]
Prompt: "[short imperative the sender probably gave an AI, in quotes]"
Verdict: [ACTIONABLE | RESPONSE-NEEDED | FYI | NOISE] — [one-sentence reason, max 15 words]

- bullet 1
- bullet 2
- bullet 3
```

For **scam NOISE** (invoice fraud, BEC, phishing, fake recruiter, etc.), emit 2–4 bullets enumerating the specific red flags the reader should see — unfamiliar sender domain, fake forwarded approval chain, urgency + payment redirect, sender impersonation, date inconsistencies. State them plainly, not as accusations. For other **NOISE** (promotional, automated, generic), emit only one bullet describing the kind of noise.

### Authorship definitions

| Authored | When | Typical signals |
|---|---|---|
| **AI** | Clearly LLM-written | Clichéd openers ("I hope this finds you well", "I wanted to reach out"), uniformly polished register, generic superlatives ("incredible", "passionate", "innovative"), symmetric three-part structure, formulaic closing generosity, zero typos, no idiosyncratic voice |
| **AI-assisted** | LLM-polished human content | AI-shaped phrasing mixe

README.md

# @defluff/openclaw-skill

An [Openclaw](https://openclaw.ai) skill that extracts the actual intent of an email into 3–5 bullets, using the same fixed prompt wording as the browser extension and Outlook add-in.

The skill is pure markdown + YAML — no executable code. Openclaw's configured agent follows the instructions in `SKILL.md` using whatever model the user has set up locally.

## Install

From the Openclaw CLI:

```bash
# copy into your local skills directory
mkdir -p ~/.openclaw/workspace/skills/defluff
cp SKILL.md ~/.openclaw/workspace/skills/defluff/
```

Or publish to ClawHub from the repo root:

```bash
pnpm skill:publish
```

This reads the `version:` field from `SKILL.md` frontmatter and invokes `clawhub publish` with the right flags. First time publishing? Run `clawhub login` once before. Bump the version in `SKILL.md` each release.

See the [Openclaw skills docs](https://docs.openclaw.ai/tools/skills) for details on discovery and updates.

## Usage

Once installed, invoke with a chat prompt like:

> /defluff [paste email here]

Or (with `user-invocable: true`, which is set in the frontmatter) as a slash command in Openclaw's chat interface.

The skill handles three input shapes:

| Input | Output |
|---|---|
| **Single email** | 3–5 bullets in priority order (actions → questions → facts → intent) |
| **Thread** (multiple messages, same conversation) | Per-message bullets + consolidated **Actions** section with attribution |
| **Batch** (unrelated emails) | Per-email bullets + **Triage** section (Act now / Reply needed / FYI / Noise) |

Noise comes in two flavors. **Scam NOISE** (invoice fraud / BEC, phishing, fake recruiter, fake interview, conference scam, crypto / MLM pitch) emits 2–4 bullets naming the specific red flags the reader should see — unfamiliar sender domain, fake forwarded approval chain, urgency + payment redirect, sender impersonation, date inconsistencies. **Other NOISE** (newsletters, auto-replies, automated system mail, generic outreach) collapses to a single labelled bullet. The skill will ask "single, thread, or batch?" if the input is ambiguous.

_meta.json

{
  "ownerId": "kn77v4q6jm2ysc21sfehd8nxy985420h",
  "slug": "defluff",
  "version": "0.0.9",
  "publishedAt": 1776886944388
}

skill-card.md

## Description:

Reverse the AI in corporate email by classifying authorship, guessing likely LLM prompts when AI was involved, classifying urgency, extracting actual intent, and naming common scam patterns across single emails, threads, and batches.

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

## Publisher:

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

### License/Terms of Use:

MIT-0

## Use Case:

Employees, external users, and developers use Defluff to triage corporate email by separating action, response, FYI, and noise while surfacing likely AI-authored messages and scam indicators.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Email content may contain sensitive or confidential information that the configured OpenClaw model will inspect.

Mitigation: Install and use only when comfortable sharing the provided email content with the configured local model or agent environment.

Risk: AI-authorship labels, guessed prompts, urgency verdicts, and scam classifications can be wrong or incomplete.

Mitigation: Treat outputs as triage signals and verify important decisions before replying, paying, clicking links, or escalating.

## Reference(s):

- [Openclaw](https://openclaw.ai)
- [Openclaw skills docs](https://docs.openclaw.ai/tools/skills)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Markdown with structured header lines and bullet lists]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Mirrors the input email language while keeping fixed line labels and verdict tokens in English.]

## Skill Version(s):

0.0.9 (source: frontmatter and server release evidence)

## 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.

Github ReposUpdated 3d 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