> ## Documentation Index
> Fetch the complete documentation index at: https://closedloop.sh/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Send Feedback

> Tell the ClosedLoop AI team when a result is wrong, missing, stale, or confusing, without leaving the conversation you noticed it in.

Something in a ClosedLoop AI answer looked wrong, thin, stale, or confusing. This skill sends that straight to the ClosedLoop AI team, with the context of what you were trying to do.

## Usage

```
/closedloop-send-feedback send feedback that this weekly brief missed churn context
/closedloop-send-feedback tell the ClosedLoop AI team that the data looks stale
/closedloop-send-feedback send that as feedback
```

Say it in plain language, or point at something earlier in the conversation.

## What Gets Sent

* What you were trying to do
* What looked wrong, missing, stale, noisy, confusing, or genuinely helpful
* Which skill or MCP tool was involved, when that is known

## Design Principles

**Real context only.** The skill uses what actually happened in the conversation. It never invents a bug, a quote, or a detail.

**Personal details are stripped.** Customer names, emails, transcript text, and customer-specific business details are removed before anything is sent. This is feedback about ClosedLoop AI, not a new piece of customer evidence.

**Any language.** Feedback that is not already in English is translated faithfully, never summarized.

**Sent immediately.** No preview step and no approval queue. One piece of feedback per call.

**Not for your own customers' feedback.** That flows in through your connected sources, and the read skills surface it. This skill only talks to the ClosedLoop AI team about ClosedLoop AI itself.