---
name: social-content-review
description: Review a social account or set of posts to identify which topics and formats perform well and what to test next. Use for social content audits, post performance analysis, or evidence-based content improvement with Toolmu TikHub.
---

# Social media content audit

## Before you start

Read [the shared research contract](../connect-toolmu/references/research-data.md) and [marketplace usage](../connect-toolmu/references/marketplace-usage.md). Use the existing Toolmu connection. The agent performs analysis; Toolmu supplies the evidence.

## Inputs

Public account or post links, platform, date window, and objective such as qualified engagement or website visits.

Ask only for information that changes the task. Accept ordinary links and names; resolve technical identifiers from verified results. Confirm missing market or scope before dependent paid calls.

## Tool selection

Inspect the current contract with Toolmu `get_tool`, then call `execute_tool` only for the steps that need data:

- `get-user-data-by-username-instagram`
- `get-user-posts-instagram`
- `get-post-by-url-instagram`
- `get-post-comments-instagram`
- `xiaohongshu-user-information-xiaohongshu`
- `xiaohongshu-user-notes-xiaohongshu`
- `get-note-comments-xiaohongshu`
- `youtube-channel-videos-youtube`
- `youtube-video-information-v2-youtube`

The catalog's current input and credit ceiling override examples in this document. Do not fabricate parameters, silently use a different supplier, or treat a search snippet as full source content.

## Workflow

1. Resolve account links through the catalog's supported lookup; confirm the account and requested period before collecting posts.

2. Collect a bounded sample, initially up to 20 posts or one returned page. Retain post URL, publish time, format, topic, and available public counters.

3. Compare similar formats and similar time since publication. Use the account's median within that group as a baseline only when enough comparable posts exist.

4. Define every rate with its actual denominator. Public likes or comments do not establish impressions, reach, watch completion, conversions, or revenue.

5. Read examples above and below the baseline and their relevant comments. Explain possible topic, opening, proof, or audience differences as hypotheses, not causes proved by correlation.

6. Propose three controlled content tests changing one meaningful element at a time. State the objective, comparison group, measurement, and evaluation window.

## Deliver

A sampled post table with original URLs, transparent comparison metrics, patterns supported by examples, and three next experiments.

Include source links, actual market/date, returned sample size, missing coverage, run IDs, and confirmed credits. Let the user's agent choose the presentation; do not invoke an MCP App or a render tool.

## Boundaries

Unavailable private analytics remain unknown. A popular post is not proof of sales impact or a reusable viral formula.

## Example request

> Review recent posts from [account link] and suggest [three] experiments for [business goal].