skills/managing-reminders/SKILL.md
Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be reminded to look at a dashboard, insight, experiment, feature flag, survey, notebook, replay, or error, or wants to list, change, or cancel their reminders. Covers when to pick a reminder over an alert or subscription, the one-off vs recurring vs cron schedule field mappings, timezones, and attaching a resource.
npx skillsauth add posthog/ai-plugin managing-remindersInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill guides you through creating and managing PostHog reminders. A reminder is a private, human-paced nudge to yourself: it fires an in-app notification on a schedule, with no condition attached. It can optionally link to a PostHog resource.
Use this skill when the user:
These three look similar but solve different jobs. Pick the right one:
If there is a condition to evaluate, it is an alert. If there is an export to deliver, it is a subscription. If it is just a timed nudge to a person, it is a reminder.
A reminder uses exactly one of scheduled_at, recurrence_interval, or cron_expression.
Providing zero or more than one is rejected.
Set scheduled_at to a future ISO 8601 timestamp. The reminder fires once, then becomes completed.
| User says | Field |
| --------------------------- | ---------------------------------------------------- |
| "remind me tomorrow at 3pm" | scheduled_at: <tomorrow 15:00 in the user's tz> |
| "remind me on Jan 5 at 9am" | scheduled_at: "2026-01-05T09:00:00" (+ timezone) |
Set recurrence_interval to one of daily, weekly, monthly, yearly.
| User says | Field |
| ------------- | -------------------------------- |
| "every day" | recurrence_interval: "daily" |
| "every week" | recurrence_interval: "weekly" |
| "every month" | recurrence_interval: "monthly" |
| "every year" | recurrence_interval: "yearly" |
Set cron_expression to a 5-field cron string (min hour day-of-month month day-of-week) when
the cadence is a specific weekday or time the presets can't express.
| User says | Field |
| -------------------------- | --------------------------------- |
| "every Monday at 9am" | cron_expression: "0 9 * * 1" |
| "weekdays at 8:30" | cron_expression: "30 8 * * 1-5" |
| "1st of the month at noon" | cron_expression: "0 12 1 * *" |
A reminder may fire at most 4 times per day — a more frequent cron (e.g. hourly) is rejected.
Always pass timezone as the user's IANA zone (e.g. "America/New_York") when you know it, so
wall-clock times like "9am" resolve to the right moment. If omitted, it defaults to the project
timezone. Cron and preset schedules resolve in this zone; scheduled_at is an absolute instant,
so include its offset or rely on the same zone.
To link the reminder to a PostHog object, set resource_type and resource_id together.
The fired notification deep-links to that object. The resource must already exist in the project.
| resource_type | resource_id is the… |
| ---------------- | --------------------- |
| dashboard | numeric id |
| insight | short_id |
| experiment | numeric id |
| feature_flag | numeric id |
| survey | id |
| notebook | short_id |
| replay | session_id |
| error_tracking | issue id |
Resolve the id first if the user gives you a name or URL (e.g. fetch the insight to get its
short_id). Omit both fields for a standalone reminder with no linked resource.
completed after it fires.active until deleted, or until its optional end_date passes
(then it becomes completed).errored — surface this via reminders-list
when reporting on a user's reminders.reminder-create — create a reminderreminders-list — list the user's reminders (schedule, status, next fire time)reminder-get — get one reminder by idreminder-update — update title, message, schedule, timezone, end date, or attached resource
(changing the schedule recomputes the next fire time)reminder-delete — delete a reminder, which stops it firingUser: "Remind me to review the launch dashboard every Monday at 9am."
67).reminder-create:{
"title": "Review the launch dashboard",
"resource_type": "dashboard",
"resource_id": "67",
"cron_expression": "0 9 * * 1",
"timezone": "America/New_York"
}
Confirm back to the user when it will next fire (use next_fire_at from the response), and that
it will keep firing weekly until they delete it.
data-ai
Signals scout for PostHog Tasks, the agent work items a project runs. Two lenses: delivery health (runs failing, clustered by repository and error class, and retry storms) every run, and on a slower rotation demand (recurring asks across human-authored tasks that point at a product gap). Skips the scout fleet's own run rows.
devops
Signals scout for the PostHog Conversations (support inbox) product. Watches the `$conversation_*` ticket-lifecycle events for support-delivery regressions — SLA breach-rate steps, first-response latency blowouts, backlog inflow-vs-resolution imbalance, and channel / assignment concentration — and files each dated regression as a report. Complements the per-ticket product-feedback signals the emission pipeline already fires; does not re-surface individual ticket content.
development
Populates and maintains a project's data catalog (semantic layer): canonical metrics, trust marks (certifications) on warehouse tables/views, and reviewed table relationships. Use when asked to set up / seed / bootstrap the data catalog or semantic layer, to catalog a project's metrics, to certify or deprecate data sources, to propose or review table joins, or to work through the proposal review queue. To *use* an existing catalog to answer a business-number question, see querying-posthog-data instead. Trigger terms: data catalog, semantic layer, canonical metric, certify table, deprecate source, relationship proposal, metric drift, review queue.
tools
Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying. Use when the user asks to "check the logs", asks whether a service, deploy, release, or change is working or broke anything, asks why errors are up or what changed, or wants the root cause of failures visible in logs. Routes the logs MCP tools (services overview, pattern mining, before/after pattern diffing, bucketed counts, facets, raw rows) so investigations start from summaries instead of raw rows or hand-written SQL over the logs table.