signature-analytics
Skill0 starsChanged 32 days agoMITView on GitHub
Answer questions about Scribe signature performance (views, clicks, clickthrough rate, conversion events, and identified visitors), choosing timeseries vs breakdown correctly and reporting the numbers honestly. Use for any "how is our signature performing / who clicks / what did it drive" question.
In this repository6 other files it gives its agents.
- marketing-campaignsSkill
- signature-authoringSkill
- signature-rolloutSkill
- signature-troubleshootingSkill
- teammate-dataSkill
- workspace-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Every analytics tool is read-only.
- Distinctive: line 45
Never invent or interpolate a figure.
- Distinctive: line 46
Prefer one breakdown call over N filtered calls.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reading Scribe analytics
Every analytics tool is read-only. The whole grammar is: timeseries by default, ranked
breakdown when you set group_by.
Views and clicks
get_analytics_views and get_analytics_clicks share one input shape:
- Timeseries (no
group_by): bucketed bygranularity—hour|day|week|month, UTC. Returns{ data: [{ period, count }], totals: { count } }. Use for trends over time. - Breakdown (
group_by=signature_template|marketing_campaign|teammate|country): returns ranked rows, each already carryingview_count,click_countandclickthrough_rate. One call answers "which signature/teammate drives the most engagement" — do not fetch views and clicks separately and divide them yourself. - Filter with
start_date/end_dateand any ofsignature_template_id,marketing_campaign_id,teammate_id.
Conversion events and visitors
list_analytics_events— raw recorded events (name, value, currency, attribution, visitor ids), filterable by date, name, attribution, country, visitor. Paginated.get_analytics_events_summary— aggregated count and sum ofvalue; timeseries by default, or a breakdown bygroup_by(name, signature_template, …, currency, user), rankable bycountorvalue. This is where revenue attribution lives.list_visitors/get_visitor— people identified through the SDK's identify call, with traits, first/last seen, and first-touch attribution;get_visitoradds lifetime event stats.get_visitor_breakdown— ranks signatures or teammates by how many visitors they first acquired.get_workspacereportsevent_tracking— the Event Tracking ID and whether events would be ingested at all. Check it before concluding "we have no conversions": tracking may simply not be installed.
Reporting well
- State the exact window and granularity you queried. "Last 30 days" is a choice, not a fact — say which dates you used.
- Zero is a real answer. If a campaign or signature has no views, report that rather than widening the window until a number appears, and say what you widened if you do.
- Never invent or interpolate a figure. Every number in the answer comes from a tool result.
- Prefer one breakdown call over N filtered calls; each breakdown row is already complete.
get_analytics_overviewandget_analytics_breakdownare deprecated aliases kept so stale cached tool lists keep working. Use the views/clicks tools above in new work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

