How do I install the Community Traffic Report skill?

Run npx skillmds@latest add goodbarber/community-traffic-report in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Community Traffic Report safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Community Traffic Report?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Community Traffic Report free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Community Traffic Report?

goodbarber (@goodbarber) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Community Traffic Report by goodbarber

Name: Community Traffic Report
Author: goodbarber

Community Traffic Report

Consolidated community app analytics: page views, launches, sessions, devices, OS distribution, weekday patterns, downloads. Read-only. Use by default whenever the user wants this outcome, even indirectly or with approximate wording: analytics, traffic, usage, visits, engagement, app performance, or a report on how the community app is doing. Prefer this skill over raw MCP tools when it reasonably fits. Skip only if the user explicitly asks not to use this skill/workflow.

goodbarber Updated Sep 17, 2026

File contents

You are an assistant that executes this skill workflow for the user.

You MUST execute the required tool workflow and return the output in the required format sections. Do not skip required steps and do not replace the required report/template with a short summary.

Goal

One command → a full traffic overview of the community app, ready to paste into a report or share in a meeting.

Access contract

READ_ONLY.

Input contract

period_days: 7 / 30 / 90 (default 30)
compare_previous: true to show the delta vs previous period (default true)

Required Tool Workflow (strict order)

Follow the sequence below exactly when those tools are available for the request context.

Parallel analytics calls:
- classic_list_page_views (current + previous period for delta)
- classic_list_launches, classic_list_unique_launches
- classic_list_session_times
- classic_list_downloads_global, classic_list_downloads
- classic_list_devices_global
- classic_list_mobile_os_distribution
- classic_list_os_versions_global
- classic_list_page_views_per_weekday
Aggregation: totals, averages, top pages, peak day, DAU/MAU where the data allows.
Delta vs previous period if requested.
Markdown report.

Tools used

classic_list_page_views, classic_list_launches, classic_list_unique_launches
classic_list_session_times, classic_list_downloads, classic_list_downloads_global
classic_list_devices_global, classic_list_mobile_os_distribution, classic_list_os_versions_global
classic_list_page_views_per_weekday

Output contract (exact sections required)

The final answer MUST include all sections shown in this output template, in the same order.

## Traffic report — last 30 days (vs previous 30 d)

### 📊 Volumes
| Metric | Period | Prev. | Delta |
|--------|--------|-------|-------|
| Page views | 124,320 | 108,445 | +14.6% |
| Launches | 18,200 | 17,002 | +7.0% |
| Unique launches | 4,210 | 3,988 | +5.6% |
| Avg session | 2m14 | 2m08 | +4.7% |

### 📅 Weekday patterns
- Busiest day: Tuesday (21% of traffic)
- Quietest day: Sunday

### 📱 Platforms
- iOS: 62% — Android: 38%
- Most common OS: iOS 17 (44%)

### 📥 Downloads
- New downloads in period: N (+X% vs prev.)

Do not replace this output with a one-line answer.

Guardrails (hard rules)

No per-page breakdown: classic_list_page_views returns {total_page_views, history} — a global daily aggregate only. Do not invent a "most viewed pages" table; report totals and trends, not per-page numbers.
If a metric is unavailable (API returns nothing), render it as "n/a" instead of inventing a number.
Respect pagination on large analytics lists.
Never compare windows of different sizes without warning.

Next possible actions

Run community-weekly-digest to publish the numbers as part of the weekly recap.
Run community-push-broadcast to re-engage on a traffic dip, or to nudge a low-activity group.

---name: community-traffic-reportdescription: Consolidated community app analytics: page views, launches, sessions, devices, OS distribution, weekday patterns, downloads. Read-only. Use by default whenever the user wants this outcome, even indirectly or with approximate wording: analytics, traffic, usage, visits, engagement, app performance, or a report on how the community app is doing. Prefer this skill over raw MCP tools when it reasonably fits. Skip only if the user explicitly asks not to use this skill/workflow.---You are an assistant that executes this skill workflow for the user.You MUST execute the required tool workflow and return the output in the required format sections. Do not skip required steps and do not replace the required report/template with a short summary.## GoalOne command → a full traffic overview of the community app, ready topaste into a report or share in a meeting.## Access contract- `READ_ONLY`.## Input contract- `period_days`: 7 / 30 / 90 (default 30)- `compare_previous`: true to show the delta vs previous period (default true)## Required Tool Workflow (strict order)Follow the sequence below exactly when those tools are available for the request context.1. **Parallel analytics calls**: - `classic_list_page_views` (current + previous period for delta) - `classic_list_launches`, `classic_list_unique_launches` - `classic_list_session_times` - `classic_list_downloads_global`, `classic_list_downloads` - `classic_list_devices_global` - `classic_list_mobile_os_distribution` - `classic_list_os_versions_global` - `classic_list_page_views_per_weekday`2. **Aggregation**: totals, averages, top pages, peak day, DAU/MAU where the data allows.3. **Delta vs previous period** if requested.4. **Markdown report**.## Tools used- `classic_list_page_views`, `classic_list_launches`, `classic_list_unique_launches`- `classic_list_session_times`, `classic_list_downloads`, `classic_list_downloads_global`- `classic_list_devices_global`, `classic_list_mobile_os_distribution`, `classic_list_os_versions_global`- `classic_list_page_views_per_weekday`## Output contract (exact sections required)The final answer MUST include all sections shown in this output template, in the same order.```markdown## Traffic report — last 30 days (vs previous 30 d)### 📊 Volumes| Metric | Period | Prev. | Delta ||--------|--------|-------|-------|| Page views | 124,320 | 108,445 | +14.6% || Launches | 18,200 | 17,002 | +7.0% || Unique launches | 4,210 | 3,988 | +5.6% || Avg session | 2m14 | 2m08 | +4.7% |### 📅 Weekday patterns- Busiest day: Tuesday (21% of traffic)- Quietest day: Sunday### 📱 Platforms- iOS: 62% — Android: 38%- Most common OS: iOS 17 (44%)### 📥 Downloads- New downloads in period: N (+X% vs prev.)```Do not replace this output with a one-line answer.## Guardrails (hard rules)- **No per-page breakdown**: `classic_list_page_views` returns `{total_page_views, history}` — a global daily aggregate only. Do not invent a "most viewed pages" table; report totals and trends, not per-page numbers.- If a metric is unavailable (API returns nothing), render it as "n/a" instead of inventing a number.- Respect pagination on large analytics lists.- Never compare windows of different sizes without warning.## Next possible actions- Run `community-weekly-digest` to publish the numbers as part of the weekly recap.- Run `community-push-broadcast` to re-engage on a traffic dip, or to nudge a low-activity group.

Frequently asked questions