Performance Analyzer Sms

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha c4808127928a · 19 Oct 2026Report an issue or request a re-scan

• Publisherblacktwist GitHub organizationOwner of the repository this skill is read from
• Source folderblacktwist/social-media-skills/skills/performance-analyzer-smsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictc4808127928aA new audit runs when the source changes
• Repository statusNot archivedLast push 171 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: When the user wants to analyze how their social media posts are performing. Also use when the user mentions 'analytics,' 'performance,' 'how did my posts do,' 'engagement,' 'impressions,' 'what's working,' 'post…

---
name: performance-analyzer-sms
description: "When the user wants to analyze how their social media posts are performing. Also use when the user mentions 'analytics,' 'performance,' 'how did my posts do,' 'engagement,' 'impressions,' 'what's working,' 'post metrics,' 'my best posts,' or 'why isn't this post performing.' Uses BlackTwist analytics when available, works from user-provided data otherwise. For audience growth specifically, see audience-growth-tracker-sms. For pattern detection, see content-pattern-analyzer-sms. For actionable next steps, see optimization-advisor-sms."
metadata:
  version: 1.0.0
---

# Performance Analyzer

## When to Use

- User asks to **analyze how their posts are performing** or review analytics
- User mentions "analytics," "performance," or "how did my posts do"
- User says "engagement," "impressions," or "what's working"
- User asks about "post metrics," "my best posts," or "why isn't this post performing"
- User shares post data and wants a performance breakdown
- User wants to compare recent posts against their own baseline

## Role

You are an expert social media analytics advisor. Your job is to turn raw post data into clear, prioritized insights — identifying what is working, what is not, and exactly why. You communicate findings in plain language, not dashboards. Every analysis ends with specific actions, not vague suggestions.

## Context Check

Before analyzing anything, read `.agents/social-media-context-sms.md` (if it exists). This file contains the user's niche, voice, platforms, and goals. Use it to make every insight relevant to their specific situation, not generic advice.

---

## Data Collection

### Path A — With BlackTwist

When BlackTwist tools are available, pull data in this order:

1. **`list_posts`** — retrieve recent posts to establish the analysis window (default: last 30 days or last 20 posts, whichever is larger)
2. **`get_post_analytics`** — pull per-post metrics: impressions, likes, comments, reposts, saves, link clicks, profile visits
3. **`get_live_metrics`** — check current real-time performance for any posts still gaining traction
4. **`get_metric_timeseries`** — pull engagement rate and impressions over time to identify trends (weekly view recommended)
5. **`get_daily_recap`** — surface any anomaly days (unusually high or low performance)
6. **`get_consistency`** — check posting frequency and whether consistency correlates with performance shifts

Collect all data before beginning analysis. Do not present raw numbers to the user — interpret them.

### Path B — Without BlackTwist

If BlackTwist is unavailable, ask the user to provide their data. Use this prompt:

> "To analyze your performance, I need your post metrics. You can share:
> - A screenshot of your analytics dashboard
> - A CSV export from your platform
> - Manual input using the template below
>
> **Data Collection Template:**
> For each post (last 14–30 days), collect:
> | Post | Date | Impressions | Likes | Comments | Reposts | Saves | Link Clicks | Profile Visits |
> |------|------|-------------|-------|----------|---------|-------|-------------|----------------|
>
> The minimum needed for a useful analysis: **impressions + likes + comments** for at least 5 posts."

Do not attempt analysis with fewer than 5 posts — tell the user why and ask for more.

---

## Metrics Framework

Organize all metrics into three categories before analyzing:

### Reach
- **Impressions** — total times the post appeared in feeds (includes repeats)
- **Reach** — unique accounts who saw the post
- **Profile visits from post** — how many viewers clicked through to learn more

### Engagement
- **Likes** — passive positive signal
- **Comments** — active engagement; higher weight than likes
- **Reposts / shares** — distribution signal; the most valuable organic action
- **Saves** — intent to return; strong indicator of lasting value
- **Engagement rate** — calculate as: `(likes + comments + reposts + saves) / impressions × 100`

### Conversion
- **Link clicks** — traffic signal; only relevant when a link is present
- **DMs from post** — often untracked but worth asking the user about
- **Follows from post** — net new audience directly attributable to the content

**Important:** Always compare engagement rate, not raw engagement numbers. A post with 50 likes from 500 impressions (10% ER) outperforms a post with 200 likes from 10,000 impressions (2% ER).

---

## Analysis Outputs

Produce all four outputs below. Do not skip any section.

### 1. Top Performers

Identify the **top 3–5 posts by engagement rate**. For each:

- State the engagement rate and the raw numbers behind it
- Diagnose **why it worked** — be specific across these dimensions:
  - **Topic**: Was it timely, controversial, educational, personal?
  - **Format**: Thread, single post, list, story, data-driven?
  - **Hook**: What did the first line do? Which hook pattern?
  - **Timing**: Day of week, time of day — any pattern?
  - **Call to action**: Did it invite a specific response?

Do not just say "this performed well." Say: "This post's engagement rate of 8.4% was 3x your average. The hook led with a specific number, the topic addressed a pain point your audience frequently comments about, and you posted on Tuesday at 9am — your historically strongest slot."

**Example top performer diagnosis:**

```
Post: "7 writing habits that doubled my output" (March 12, 9:14 AM)
ER: 8.4% (vs. 2.8% baseline) — 3x your average
Impressions: 4,200 | Likes: 189 | Comments: 47 | Reposts: 31 | Saves: 86

Why it worked:
- Hook: List preview pattern ("7 habits...") — your strongest hook type
- Topic: Productivity + writing — overlaps two of your top pillars
- Timing: Tuesday morning — your historically strongest slot
- CTA: "Which one surprised you?" — drove 47 comments
```

### 2. Bottom Performers

Identify the **bottom 3–5 posts by engagement rate**. For each:

- State the engagement rate
- Diagnose **what went wrong** — be specific:
 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/blacktwist/social-media-skills
git -C social-media-skills checkout c4808127928a

Works in

1. 2026-10-19
   ✓SAFE B 89 / 100

   first audit · source c4808127928a

Questions about Performance Analyzer Sms

• github.com/blacktwist/social-media-skills/tree/main/skills/perfo — the audited source at commit c4808127928a and every finding aboveObserved · 19 Oct 2026

Spotted something wrong? Report a correction · Methodology