Chalk Labs
Need help deploying performance-diagnostic?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lucaspretti-performance-diagnostic
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/performance-diagnostic
What's inside
- Skill name
performance-diagnostic- Description
- Diagnose page load performance issues. Use when the user asks about slow pages, load times, performance problems, or wants to understand why a site is slow.
- License
- MIT
- Instructions
- 58 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Performance Diagnostic
Analyze page load performance for a Matomo-tracked site.
## Site selection
If $ARGUMENTS contains a site ID or name, use that. If the conversation already has a site in context, use that. Otherwise, call `matomo_list_sites`, present a short numbered list (ID, name, URL), and ask which site to analyze. Do not proceed until a site is selected.
## Steps
1. **Get overall performance** using `matomo_get_page_performance` for the requested period (default: last 7 days, period: day, date: last7)
2. **Identify slow pages** using `matomo_get_top_pages` with limit 20 for the same period. Sort by `avg_page_load_time` to find the slowest pages.
3. **Check device impact** using `matomo_get_devices` to see if performance varies by device type.
4. **Check browser impact** using `matomo_get_browsers` to see if specific browsers are slower.
5. **Mobile-specific drill-down** when the user mentions "mobile", "phone", or "slow on phone": rerun steps 1 and 2 with `device: "mobile"` to get the mobile-only numbers, then compare against the all-devices baseline. Flag any page where mobile is significantly slower than desktop.
6. **Present findings** as a summary:
- Overall avg load time and breakdown (network, server, DOM processing, DOM completion)
- Top 5 slowest pages with their load times
- Device/browser breakdown if significant differences exist
- Mobile vs desktop delta if a mobile drill-down was run
- Identify the bottleneck: is it network, server, or client-side (DOM)?
If $ARGUMENTS contains a specific URL or page path, focus the analysis on that page.
## Fallback when segments return zero
If a `device`-filtered call comes back with all-zero metrics while the same
query without `device` returns normal numbers, the Matomo server is refusing
to aggregate the segment for this API token (it lacks `process_new_segment`
or the segment isn't pre-archived). Do not claim "no mobile traffic" — that's
almost never the real answer.
Try these in order:
1. **Switch to `matomo_count_visits_by_segment`.** It uses the Live API
under the hood and does NOT need segment archiving. For mobile:
`{siteId, period, date, device: "mobile"}` returns
`{visits, byDevice, byCountryTop10}`. Slower than aggregate endpoints for
very large result sets, but always returns real numbers.
2. **Check `matomo_list_segments`** to find saved segments on the instance.
Any segment with `auto_archive=1` is pre-archived and will always return
real numbers when you reference its `definition` string in `segment`.
3. **Open the Matomo UI in a logged-in browser session** as a last resort
— the UI uses the user's permissions, not the token:
```
<matomo-host>/index.php?module=CoreHome&action=index
&idSite=<id>&period=<period>&date=<date>
&segment=deviceType%3D%3Dsmartphone%2CdeviceType%3D%3Dtablet%2CdeviceType%3D%3Dphablet
```
4. **Longer-term fix**: ask the Matomo admin to grant
`process_new_segment` on the token or pre-archive common segments.From lucaspretti/matomo-mcp-client, MIT.
More from lucaspretti/matomo-mcp-client
- 0.565score
discover-sites
lucaspretti
List all available Matomo sites and let the user choose which one to analyze.
SkillAFreshness: AClaude Code +9 - 0.565score
page-events-analysis
lucaspretti
Cross-reference page views with event usage to calculate feature adoption rates.
SkillAFreshness: AClaude Code +9 - 0.565score
search-insights
lucaspretti
Analyze site search behavior and content gaps.
SkillAFreshness: AClaude Code +9 - 0.565score
traffic-report
lucaspretti
Generate a traffic overview report.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Apr 24, 2026 (6 months ago)
- Last release
- Oct 6, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lucaspretti/matomo-mcp-client
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lucaspretti
- 0.565score
discover-sites
lucaspretti
List all available Matomo sites and let the user choose which one to analyze.
SkillAFreshness: AClaude Code +9 - 0.565score
page-events-analysis
lucaspretti
Cross-reference page views with event usage to calculate feature adoption rates.
SkillAFreshness: AClaude Code +9 - 0.565score
search-insights
lucaspretti
Analyze site search behavior and content gaps.
SkillAFreshness: AClaude Code +9 - 0.565score
traffic-report
lucaspretti
Generate a traffic overview report.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get performance-diagnostic running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
performance-diagnostic skill. Agent Mart. https://agentmart.dev/skills/lucaspretti-performance-diagnostic (last updated 2026-10-24)